diff --git "a/checkpoint-2213280/trainer_state.json" "b/checkpoint-2213280/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2213280/trainer_state.json" @@ -0,0 +1,26189 @@ +{ + "best_metric": 3.8590054512023926, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/superlative-quantifier/transformer/1/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2213280, + "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": 11.1003, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8296, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1836, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9784, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8165, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7061, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6062, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5289, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4503, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4104, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3559, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.303, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2642, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2163, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1754, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1456, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.106, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0844, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0474, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0323, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.013, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.9782, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 4.9525, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 4.9316, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9197, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8934, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.8686, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 4.8494, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8529, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8158, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.8077, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 4.8032, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 4.7852, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7698, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7685, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 4.7497, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 4.7428, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.709, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.7086, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.688, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 4.6821, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6766, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6693, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6512, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6535, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6372, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6374, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6382, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6073, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.5984, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6065, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.6053, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.579, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.573, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5726, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5515, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5627, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5348, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.544, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5368, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5342, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5083, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5253, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4963, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5065, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5056, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4981, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4787, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4711, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4663, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4795, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4731, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4557, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4672, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4715, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4527, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4494, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4393, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4402, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4214, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4257, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4212, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4317, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4201, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3996, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.4058, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4032, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.4062, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.4015, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3903, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3891, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3796, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3708, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3634, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3685, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3767, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3679, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3539, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3549, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3587, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3593, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3512, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3462, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3392, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3465, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3256, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3305, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3347, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3233, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3217, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3218, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3144, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3178, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3152, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3092, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3145, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3129, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.3061, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.3092, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.2981, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.2975, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.2895, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.2871, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2876, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2874, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2847, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.285, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2828, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2691, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2813, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2801, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2609, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2524, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2603, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2736, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.274, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2599, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2577, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2631, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2638, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2547, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2453, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2491, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2436, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2411, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2501, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2359, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.247, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2419, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2257, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.211981773376465, + "eval_runtime": 315.8607, + "eval_samples_per_second": 1208.099, + "eval_steps_per_second": 37.754, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2306, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.221, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2333, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2255, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2291, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2122, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2091, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.1968, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2262, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.214, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2074, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2154, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1999, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1962, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1935, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1923, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1917, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.1862, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1967, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.2026, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1884, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1801, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1814, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1847, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1776, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1679, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1686, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1801, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1566, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1632, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1695, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1681, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1703, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.166, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.1611, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1687, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1455, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1553, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1403, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1464, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1482, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.1504, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.146, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1412, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1413, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1456, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1462, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1324, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1268, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1392, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.1468, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1279, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1305, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.127, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.12, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.1256, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273133586178384e-05, + "loss": 4.1128, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.1257, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825637806996108e-05, + "loss": 4.1253, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.1213, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823960617494004e-05, + "loss": 4.1033, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.1249, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.1008, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821446471121221e-05, + "loss": 4.116, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.1178, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.1168, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.1002, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.0985, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.0987, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.107, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.1078, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147409888735514e-05, + "loss": 4.1021, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139023941224994e-05, + "loss": 4.11, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.1112, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.1073, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811388247749716e-05, + "loss": 4.0949, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810549652998664e-05, + "loss": 4.1037, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.1023, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.0827, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.1013, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807196911874829e-05, + "loss": 4.0881, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.1087, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0957, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.0748, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803844170750995e-05, + "loss": 4.0919, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803005575999943e-05, + "loss": 4.0827, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802166981248891e-05, + "loss": 4.0954, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.0874, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004930675075325e-05, + "loss": 4.0816, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0854, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988158780054285e-05, + "loss": 4.075, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979772832543765e-05, + "loss": 4.0701, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971386885033245e-05, + "loss": 4.0688, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963000937522725e-05, + "loss": 4.0751, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.0853, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794624542130542e-05, + "loss": 4.0764, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.79378594737949e-05, + "loss": 4.0665, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792947352628438e-05, + "loss": 4.0682, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792108757877386e-05, + "loss": 4.0729, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791271801006707e-05, + "loss": 4.0791, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790433206255655e-05, + "loss": 4.0726, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789594611504603e-05, + "loss": 4.069, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788756016753551e-05, + "loss": 4.067, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787917422002499e-05, + "loss": 4.0742, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787078827251447e-05, + "loss": 4.0518, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.064, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.0679, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845646808786646e-05, + "loss": 4.0584, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.0555, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.0569, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.0581, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.0567, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780371707123404e-05, + "loss": 4.0594, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779533112372352e-05, + "loss": 4.0538, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.067, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.0622, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.0573, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.0591, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0552, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774504819626786e-05, + "loss": 4.0523, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.045, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0436, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.0504, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.052, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0475, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0499, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.044, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767797699498743e-05, + "loss": 4.044, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.0457, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.0516, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0364, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0262, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76360800150423e-05, + "loss": 4.0324, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.049, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.0478, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.041, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602552603803946e-05, + "loss": 4.036, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594166656293426e-05, + "loss": 4.047, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585780708782906e-05, + "loss": 4.0425, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577394761272386e-05, + "loss": 4.0403, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569025192565595e-05, + "loss": 4.034, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0336, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552253297544555e-05, + "loss": 4.0346, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0248, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753549778132725e-05, + "loss": 4.0429, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752711183381673e-05, + "loss": 4.0259, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751872588630621e-05, + "loss": 4.0365, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751033993879569e-05, + "loss": 4.0339, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750195399128517e-05, + "loss": 4.0221, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.041590690612793, + "eval_runtime": 316.7556, + "eval_samples_per_second": 1204.686, + "eval_steps_per_second": 37.647, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 4.0258, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0189, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.0291, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.0247, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0321, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 4.0141, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.014, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 4.0013, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0347, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741809451617997e-05, + "loss": 4.0215, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.0117, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.0264, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392985810059604e-05, + "loss": 4.0078, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384599862549084e-05, + "loss": 4.0119, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737621391503856e-05, + "loss": 4.0022, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736782796752804e-05, + "loss": 4.004, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735944202001752e-05, + "loss": 4.0101, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7351056072507e-05, + "loss": 3.9997, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734267012499648e-05, + "loss": 4.0154, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733428417748596e-05, + "loss": 4.02, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325898229975444e-05, + "loss": 4.008, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 4.0041, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 4.0035, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730075676624761e-05, + "loss": 4.0057, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729237081873709e-05, + "loss": 3.9958, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 3.9974, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 3.9919, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726722935500926e-05, + "loss": 4.0083, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9805, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9932, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 3.9989, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723370194377091e-05, + "loss": 4.0013, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 3.9997, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9979, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9925, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200174532532566e-05, + "loss": 4.0012, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191788585022046e-05, + "loss": 3.9846, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 3.9898, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9738, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166647121294215e-05, + "loss": 3.9844, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158261173783695e-05, + "loss": 3.9808, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149875226273175e-05, + "loss": 3.9931, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 3.9848, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133119710055864e-05, + "loss": 3.9826, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712473376254535e-05, + "loss": 3.9852, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711634781503483e-05, + "loss": 3.987, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9863, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709959229881752e-05, + "loss": 3.9737, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091206351307e-05, + "loss": 3.9678, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708282040379648e-05, + "loss": 3.9875, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9886, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706606488757917e-05, + "loss": 3.9766, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705767894006865e-05, + "loss": 3.9762, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704929299255813e-05, + "loss": 3.9714, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9687, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703253747634082e-05, + "loss": 3.9757, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024151528830305e-05, + "loss": 3.9645, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015765581319785e-05, + "loss": 3.9763, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007379633809265e-05, + "loss": 3.9748, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.9701, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.9576, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9787, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9556, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.9687, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.968, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9744, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9552, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693195524262577e-05, + "loss": 3.9602, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692356929511526e-05, + "loss": 3.9513, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691518334760474e-05, + "loss": 3.9662, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690679740009422e-05, + "loss": 3.9674, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.964, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9687, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.969, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9731, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864900420149076e-05, + "loss": 3.9532, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.9644, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9694, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9466, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.963, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9502, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9744, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9608, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.9401, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.954, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9531, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9614, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676431818643403e-05, + "loss": 3.9556, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.9511, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9521, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.9479, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9417, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.9355, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671401888017464e-05, + "loss": 3.9484, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9567, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9493, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.9379, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668049146893629e-05, + "loss": 3.9409, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.9428, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663735952718984e-05, + "loss": 3.9549, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665535000520846e-05, + "loss": 3.9465, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664696405769794e-05, + "loss": 3.9442, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663857811018742e-05, + "loss": 3.9378, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301921626769e-05, + "loss": 3.9495, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621806215166383e-05, + "loss": 3.9261, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613420267655863e-05, + "loss": 3.9418, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9397, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.9383, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658827880392803e-05, + "loss": 3.9304, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657989285641751e-05, + "loss": 3.9368, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657150690890699e-05, + "loss": 3.9367, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9358, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655475139268968e-05, + "loss": 3.9395, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9353, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653797949766864e-05, + "loss": 3.9445, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652959355015812e-05, + "loss": 3.9434, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652122398145134e-05, + "loss": 3.9406, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651283803394082e-05, + "loss": 3.9399, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.65044520864303e-05, + "loss": 3.9367, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649606613891978e-05, + "loss": 3.9302, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648768019140926e-05, + "loss": 3.9288, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647929424389874e-05, + "loss": 3.9305, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647090829638822e-05, + "loss": 3.9285, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.64625223488777e-05, + "loss": 3.9401, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.929, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445766832660386e-05, + "loss": 3.9352, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437380885149866e-05, + "loss": 3.9317, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429011316443075e-05, + "loss": 3.9271, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420625368932555e-05, + "loss": 3.9268, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412239421422035e-05, + "loss": 3.9405, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.922, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639548390520473e-05, + "loss": 3.9194, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638709795769421e-05, + "loss": 3.9142, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637871201018369e-05, + "loss": 3.934, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.63703424414769e-05, + "loss": 3.937, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636195649396638e-05, + "loss": 3.934, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635357054645586e-05, + "loss": 3.9234, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634518459894534e-05, + "loss": 3.9363, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633681503023855e-05, + "loss": 3.9261, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632842908272803e-05, + "loss": 3.9311, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632004313521751e-05, + "loss": 3.9215, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631165718770699e-05, + "loss": 3.9266, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303271240196475e-05, + "loss": 3.9236, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294901671489684e-05, + "loss": 3.9129, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286515723979164e-05, + "loss": 3.9341, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278129776468644e-05, + "loss": 3.9224, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626974382895812e-05, + "loss": 3.9248, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.62613578814476e-05, + "loss": 3.9253, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625297193393708e-05, + "loss": 3.9131, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9674437046051025, + "eval_runtime": 304.1285, + "eval_samples_per_second": 1254.703, + "eval_steps_per_second": 39.21, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624458598642656e-05, + "loss": 3.9209, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623620003891604e-05, + "loss": 3.9139, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227830470209246e-05, + "loss": 3.9211, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219444522698726e-05, + "loss": 3.9184, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621107495399194e-05, + "loss": 3.9303, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620268900648142e-05, + "loss": 3.9106, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.61943030589709e-05, + "loss": 3.9074, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618591711146038e-05, + "loss": 3.8998, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617753116394986e-05, + "loss": 3.9259, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616914521643934e-05, + "loss": 3.9214, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616075926892882e-05, + "loss": 3.9033, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9223, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614402013151524e-05, + "loss": 3.9044, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613563418400472e-05, + "loss": 3.9088, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.61272482364942e-05, + "loss": 3.9028, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611886228898368e-05, + "loss": 3.9023, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611047634147316e-05, + "loss": 3.9043, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610209039396265e-05, + "loss": 3.9002, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609370444645213e-05, + "loss": 3.9152, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085318498941607e-05, + "loss": 3.9185, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.911, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9048, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.9004, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9115, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043405140192735e-05, + "loss": 3.8973, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035019192682215e-05, + "loss": 3.9009, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026633245171695e-05, + "loss": 3.8918, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018263676464904e-05, + "loss": 3.9098, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009894107758114e-05, + "loss": 3.8852, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60015081602476e-05, + "loss": 3.8941, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599312221273708e-05, + "loss": 3.9055, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598473626522656e-05, + "loss": 3.9013, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597636669651977e-05, + "loss": 3.9038, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596798074900925e-05, + "loss": 3.9035, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595959480149873e-05, + "loss": 3.8957, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595120885398821e-05, + "loss": 3.9061, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.8929, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.8866, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592605101145665e-05, + "loss": 3.8819, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591766506394613e-05, + "loss": 3.8903, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590929549523934e-05, + "loss": 3.8853, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900925926532554e-05, + "loss": 3.902, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892539979022034e-05, + "loss": 3.8909, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884154031511514e-05, + "loss": 3.8899, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875768084000994e-05, + "loss": 3.8968, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867382136490474e-05, + "loss": 3.8886, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585901256778368e-05, + "loss": 3.8987, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585062662027316e-05, + "loss": 3.8838, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584224067276264e-05, + "loss": 3.8697, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583385472525212e-05, + "loss": 3.8997, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.58254687777416e-05, + "loss": 3.8933, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817082830231076e-05, + "loss": 3.8926, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580871326152429e-05, + "loss": 3.8838, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580032731401377e-05, + "loss": 3.8818, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579194136650325e-05, + "loss": 3.8777, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578355541899273e-05, + "loss": 3.8873, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577516947148221e-05, + "loss": 3.8766, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576678352397169e-05, + "loss": 3.8819, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575839757646117e-05, + "loss": 3.8922, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575001162895065e-05, + "loss": 3.8798, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574164206024386e-05, + "loss": 3.869, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573325611273334e-05, + "loss": 3.8928, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572487016522282e-05, + "loss": 3.8688, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.57164842177123e-05, + "loss": 3.8755, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570809827020178e-05, + "loss": 3.8847, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569972870149499e-05, + "loss": 3.8875, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691342753984476e-05, + "loss": 3.8653, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682956806473956e-05, + "loss": 3.8754, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674570858963436e-05, + "loss": 3.859, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666184911452916e-05, + "loss": 3.8825, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657815342746125e-05, + "loss": 3.8787, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649429395235605e-05, + "loss": 3.8789, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641043447725085e-05, + "loss": 3.8791, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632657500214565e-05, + "loss": 3.8849, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624271552704045e-05, + "loss": 3.89, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615901983997254e-05, + "loss": 3.8674, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607516036486734e-05, + "loss": 3.8789, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599130088976214e-05, + "loss": 3.8831, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590744141465694e-05, + "loss": 3.862, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558237457275891e-05, + "loss": 3.8806, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557398862524839e-05, + "loss": 3.87, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556560267773787e-05, + "loss": 3.8843, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555721673022735e-05, + "loss": 3.8782, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554884716152056e-05, + "loss": 3.859, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554046121401004e-05, + "loss": 3.8715, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553207526649952e-05, + "loss": 3.8677, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523689318989e-05, + "loss": 3.8795, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551530337147848e-05, + "loss": 3.8688, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550693380277169e-05, + "loss": 3.8681, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549854785526117e-05, + "loss": 3.8696, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549016190775065e-05, + "loss": 3.8694, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548177596024013e-05, + "loss": 3.8619, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547339001272961e-05, + "loss": 3.8532, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5465020444022823e-05, + "loss": 3.8658, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.54566344965123e-05, + "loss": 3.8753, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544824854900178e-05, + "loss": 3.8727, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543986260149126e-05, + "loss": 3.8516, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431476653980736e-05, + "loss": 3.8628, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423090706470216e-05, + "loss": 3.8628, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541472113776343e-05, + "loss": 3.874, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540633519025291e-05, + "loss": 3.8667, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397949242742385e-05, + "loss": 3.8651, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389563295231865e-05, + "loss": 3.858, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381177347721345e-05, + "loss": 3.8712, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537280777901456e-05, + "loss": 3.8472, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536442183150404e-05, + "loss": 3.8633, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535603588399352e-05, + "loss": 3.8586, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347649936483e-05, + "loss": 3.8604, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533926398897248e-05, + "loss": 3.8535, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533087804146196e-05, + "loss": 3.8625, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532249209395144e-05, + "loss": 3.8532, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531412252524465e-05, + "loss": 3.8606, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530573657773413e-05, + "loss": 3.8623, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529735063022361e-05, + "loss": 3.8574, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528896468271309e-05, + "loss": 3.8672, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528057873520257e-05, + "loss": 3.8665, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272209166495786e-05, + "loss": 3.8619, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263823218985266e-05, + "loss": 3.8664, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255437271474746e-05, + "loss": 3.8611, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247051323964226e-05, + "loss": 3.8536, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238665376453706e-05, + "loss": 3.8511, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230279428943186e-05, + "loss": 3.8546, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221893481432665e-05, + "loss": 3.8568, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213507533922145e-05, + "loss": 3.862, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205137965215355e-05, + "loss": 3.8535, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196768396508564e-05, + "loss": 3.8609, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188382448998044e-05, + "loss": 3.8518, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8539, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171610553977003e-05, + "loss": 3.8533, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516324098527022e-05, + "loss": 3.8646, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.51548550377597e-05, + "loss": 3.8501, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514646909024918e-05, + "loss": 3.8455, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513808314273866e-05, + "loss": 3.8388, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512969719522814e-05, + "loss": 3.8574, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512132762652135e-05, + "loss": 3.8608, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511294167901083e-05, + "loss": 3.8612, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510455573150031e-05, + "loss": 3.8516, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509616978398979e-05, + "loss": 3.863, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087800215283e-05, + "loss": 3.853, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507941426777248e-05, + "loss": 3.8548, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507102832026196e-05, + "loss": 3.8503, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506264237275144e-05, + "loss": 3.8541, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054256425240924e-05, + "loss": 3.853, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504588685653413e-05, + "loss": 3.8381, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503751728782734e-05, + "loss": 3.862, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502913134031682e-05, + "loss": 3.8531, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.50207453928063e-05, + "loss": 3.8473, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501235944529578e-05, + "loss": 3.8502, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500397349778526e-05, + "loss": 3.8475, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9266250133514404, + "eval_runtime": 322.5135, + "eval_samples_per_second": 1183.179, + "eval_steps_per_second": 36.975, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499558755027474e-05, + "loss": 3.8461, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987201602764215e-05, + "loss": 3.8437, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978815655253695e-05, + "loss": 3.8513, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970429707743175e-05, + "loss": 3.8471, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496204376023266e-05, + "loss": 3.8592, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495365781272214e-05, + "loss": 3.8441, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494527186521162e-05, + "loss": 3.8335, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49368859177011e-05, + "loss": 3.8336, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492851634899431e-05, + "loss": 3.8511, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492013040148379e-05, + "loss": 3.8491, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491174445397327e-05, + "loss": 3.8365, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490335850646275e-05, + "loss": 3.8499, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489500531655969e-05, + "loss": 3.8393, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488661936904917e-05, + "loss": 3.8394, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487823342153865e-05, + "loss": 3.8318, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486984747402813e-05, + "loss": 3.8338, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486146152651761e-05, + "loss": 3.8329, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853075579007095e-05, + "loss": 3.8303, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844689631496575e-05, + "loss": 3.8462, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836303683986055e-05, + "loss": 3.8486, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827934115279264e-05, + "loss": 3.8432, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819548167768744e-05, + "loss": 3.839, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811162220258224e-05, + "loss": 3.8335, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802776272747704e-05, + "loss": 3.8404, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794390325237184e-05, + "loss": 3.8308, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478602075653039e-05, + "loss": 3.8345, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.8241, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476924886150935e-05, + "loss": 3.8372, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476086291399883e-05, + "loss": 3.8245, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475247696648831e-05, + "loss": 3.8211, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474410739778153e-05, + "loss": 3.8397, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473572145027101e-05, + "loss": 3.8344, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472733550276049e-05, + "loss": 3.8419, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471894955524997e-05, + "loss": 3.8371, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471056360773945e-05, + "loss": 3.8265, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470219403903266e-05, + "loss": 3.8394, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469380809152214e-05, + "loss": 3.8312, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468542214401162e-05, + "loss": 3.82, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.46770361965011e-05, + "loss": 3.8143, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466865024899058e-05, + "loss": 3.823, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466028068028379e-05, + "loss": 3.8218, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465189473277327e-05, + "loss": 3.8369, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464350878526275e-05, + "loss": 3.8252, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463512283775223e-05, + "loss": 3.8244, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462675326904544e-05, + "loss": 3.833, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461836732153492e-05, + "loss": 3.8269, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.46099813740244e-05, + "loss": 3.8306, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460159542651388e-05, + "loss": 3.8153, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459322585780709e-05, + "loss": 3.803, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458483991029657e-05, + "loss": 3.8365, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457645396278605e-05, + "loss": 3.8311, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568068015275525e-05, + "loss": 3.828, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559682067765004e-05, + "loss": 3.8193, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455131249905822e-05, + "loss": 3.8181, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.45429265515477e-05, + "loss": 3.8133, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453454060403718e-05, + "loss": 3.8203, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452615465652666e-05, + "loss": 3.8158, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8186, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509399140309356e-05, + "loss": 3.8277, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450101319279883e-05, + "loss": 3.8189, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449262724528831e-05, + "loss": 3.8068, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8296, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.8061, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446748578156048e-05, + "loss": 3.8076, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445909983404996e-05, + "loss": 3.8236, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.8269, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.8021, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433958370322134e-05, + "loss": 3.8129, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425572422811614e-05, + "loss": 3.7975, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441720285410482e-05, + "loss": 3.8204, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088169065943e-05, + "loss": 3.8209, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440043095908378e-05, + "loss": 3.8127, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439204501157326e-05, + "loss": 3.8191, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438367544286647e-05, + "loss": 3.8214, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437528949535595e-05, + "loss": 3.8332, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436690354784543e-05, + "loss": 3.8067, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435851760033491e-05, + "loss": 3.8194, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435013165282439e-05, + "loss": 3.8225, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434176208411761e-05, + "loss": 3.8001, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433337613660709e-05, + "loss": 3.8224, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432499018909657e-05, + "loss": 3.8105, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431660424158605e-05, + "loss": 3.8209, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308234672879257e-05, + "loss": 3.8175, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299848725368737e-05, + "loss": 3.8005, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291462777858217e-05, + "loss": 3.8057, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283076830347696e-05, + "loss": 3.8063, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274707261640906e-05, + "loss": 3.8244, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266321314130386e-05, + "loss": 3.8092, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257935366619865e-05, + "loss": 3.8071, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249549419109345e-05, + "loss": 3.8104, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424117985040256e-05, + "loss": 3.8122, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423279390289204e-05, + "loss": 3.8048, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422440795538152e-05, + "loss": 3.792, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216022007871e-05, + "loss": 3.8077, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420765243916421e-05, + "loss": 3.815, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419926649165369e-05, + "loss": 3.8145, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419088054414317e-05, + "loss": 3.7919, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418249459663265e-05, + "loss": 3.8039, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417412502792586e-05, + "loss": 3.8055, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416573908041534e-05, + "loss": 3.8113, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415735313290482e-05, + "loss": 3.8119, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41489671853943e-05, + "loss": 3.8063, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414058123788378e-05, + "loss": 3.8005, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132211669176995e-05, + "loss": 3.8118, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123825721666475e-05, + "loss": 3.7898, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115439774155955e-05, + "loss": 3.8049, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107053826645435e-05, + "loss": 3.7986, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098684257938644e-05, + "loss": 3.8088, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090298310428124e-05, + "loss": 3.7902, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081912362917604e-05, + "loss": 3.8085, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073526415407084e-05, + "loss": 3.799, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406515684670029e-05, + "loss": 3.8018, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405677089918977e-05, + "loss": 3.8043, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404838495167925e-05, + "loss": 3.8011, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403999900416873e-05, + "loss": 3.8083, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403162943546195e-05, + "loss": 3.8124, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402324348795143e-05, + "loss": 3.8059, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401485754044091e-05, + "loss": 3.807, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400647159293039e-05, + "loss": 3.8038, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39981020242236e-05, + "loss": 3.7982, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398971607671308e-05, + "loss": 3.7887, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398133012920256e-05, + "loss": 3.8033, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397294418169204e-05, + "loss": 3.7994, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964574612985247e-05, + "loss": 3.8058, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956188665474726e-05, + "loss": 3.7986, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947802717964206e-05, + "loss": 3.8028, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939416770453686e-05, + "loss": 3.7978, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.39310472017469e-05, + "loss": 3.7982, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392266125423638e-05, + "loss": 3.7957, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391427530672586e-05, + "loss": 3.8069, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390588935921534e-05, + "loss": 3.799, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389751979050855e-05, + "loss": 3.7909, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388913384299803e-05, + "loss": 3.7805, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388074789548751e-05, + "loss": 3.8046, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387236194797699e-05, + "loss": 3.804, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386397600046647e-05, + "loss": 3.8069, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385560643175968e-05, + "loss": 3.7982, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384722048424916e-05, + "loss": 3.8054, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383883453673864e-05, + "loss": 3.7996, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383044858922813e-05, + "loss": 3.8038, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822079020521336e-05, + "loss": 3.7932, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813693073010816e-05, + "loss": 3.7992, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805307125500296e-05, + "loss": 3.7955, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796921177989776e-05, + "loss": 3.7902, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788551609282985e-05, + "loss": 3.8062, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780165661772465e-05, + "loss": 3.7992, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771779714261945e-05, + "loss": 3.7953, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763393766751425e-05, + "loss": 3.794, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755024198044634e-05, + "loss": 3.7974, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.901872158050537, + "eval_runtime": 302.6901, + "eval_samples_per_second": 1260.666, + "eval_steps_per_second": 39.397, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746638250534114e-05, + "loss": 3.7912, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738252303023594e-05, + "loss": 3.7899, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372986635551308e-05, + "loss": 3.7984, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372149678680629e-05, + "loss": 3.791, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371311083929577e-05, + "loss": 3.8051, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370472489178525e-05, + "loss": 3.7921, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369633894427473e-05, + "loss": 3.7834, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368796937556794e-05, + "loss": 3.7787, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367958342805742e-05, + "loss": 3.7979, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.36711974805469e-05, + "loss": 3.7951, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366281153303637e-05, + "loss": 3.7868, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365444196432959e-05, + "loss": 3.7943, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.36460723956228e-05, + "loss": 3.7893, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363768644811228e-05, + "loss": 3.7874, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362930050060176e-05, + "loss": 3.782, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362091455309124e-05, + "loss": 3.7778, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361252860558072e-05, + "loss": 3.7818, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.36041426580702e-05, + "loss": 3.7778, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595756710559676e-05, + "loss": 3.7935, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587370763049156e-05, + "loss": 3.798, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357900119434237e-05, + "loss": 3.795, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570615246831845e-05, + "loss": 3.7858, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562229299321325e-05, + "loss": 3.7836, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553843351810805e-05, + "loss": 3.786, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354547378310402e-05, + "loss": 3.7788, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.35370878355935e-05, + "loss": 3.7867, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352870188808298e-05, + "loss": 3.7687, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352031594057246e-05, + "loss": 3.7879, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351194637186568e-05, + "loss": 3.7751, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350356042435515e-05, + "loss": 3.771, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349517447684463e-05, + "loss": 3.7829, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348678852933411e-05, + "loss": 3.7875, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347841896062732e-05, + "loss": 3.7913, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.34700330131168e-05, + "loss": 3.7866, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346164706560628e-05, + "loss": 3.7758, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345326111809576e-05, + "loss": 3.7895, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444891549388975e-05, + "loss": 3.7838, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436505601878455e-05, + "loss": 3.7678, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428119654367935e-05, + "loss": 3.7691, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419733706857415e-05, + "loss": 3.7704, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411364138150624e-05, + "loss": 3.7744, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402978190640104e-05, + "loss": 3.7856, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394592243129584e-05, + "loss": 3.7767, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3386206295619064e-05, + "loss": 3.7729, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337783672691227e-05, + "loss": 3.7843, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336945077940175e-05, + "loss": 3.7746, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336106483189123e-05, + "loss": 3.787, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335267888438071e-05, + "loss": 3.7657, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334430931567393e-05, + "loss": 3.75, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333592336816341e-05, + "loss": 3.7887, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332753742065289e-05, + "loss": 3.7796, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331915147314237e-05, + "loss": 3.7806, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331078190443558e-05, + "loss": 3.7757, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330239595692506e-05, + "loss": 3.7711, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329401000941454e-05, + "loss": 3.7626, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328562406190402e-05, + "loss": 3.7715, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277254493197226e-05, + "loss": 3.7675, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.3268868545686706e-05, + "loss": 3.7701, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260482598176186e-05, + "loss": 3.7783, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252096650665666e-05, + "loss": 3.77, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324372708195888e-05, + "loss": 3.7617, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323534113444836e-05, + "loss": 3.7799, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322695518693784e-05, + "loss": 3.7604, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321858561823105e-05, + "loss": 3.7599, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321019967072053e-05, + "loss": 3.7756, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320181372321001e-05, + "loss": 3.7776, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319342777569949e-05, + "loss": 3.7545, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.31850582069927e-05, + "loss": 3.7654, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317667225948218e-05, + "loss": 3.7526, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316828631197166e-05, + "loss": 3.7685, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315990036446114e-05, + "loss": 3.7719, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315151441695062e-05, + "loss": 3.7693, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143144848243836e-05, + "loss": 3.7703, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134758900733316e-05, + "loss": 3.7725, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3126372953222796e-05, + "loss": 3.7814, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3118003384516005e-05, + "loss": 3.7595, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109617437005485e-05, + "loss": 3.7757, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101231489494965e-05, + "loss": 3.7737, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092845541984445e-05, + "loss": 3.7526, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084475973277654e-05, + "loss": 3.776, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3076090025767134e-05, + "loss": 3.7626, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067704078256614e-05, + "loss": 3.7771, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3059318130746094e-05, + "loss": 3.7701, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.30509485620393e-05, + "loss": 3.7556, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304256261452879e-05, + "loss": 3.7548, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303417666701827e-05, + "loss": 3.7603, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302579071950775e-05, + "loss": 3.7768, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301742115080096e-05, + "loss": 3.7628, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300903520329044e-05, + "loss": 3.7624, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300064925577992e-05, + "loss": 3.7626, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.29922633082694e-05, + "loss": 3.7665, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298389373956261e-05, + "loss": 3.7578, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297550779205209e-05, + "loss": 3.7436, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296712184454157e-05, + "loss": 3.76, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295873589703105e-05, + "loss": 3.768, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950366328324256e-05, + "loss": 3.7692, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294198038081374e-05, + "loss": 3.7493, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293359443330322e-05, + "loss": 3.7558, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.29252084857927e-05, + "loss": 3.7603, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291683891708591e-05, + "loss": 3.7622, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290845296957539e-05, + "loss": 3.77, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290006702206487e-05, + "loss": 3.7565, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289168107455435e-05, + "loss": 3.7594, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288331150584756e-05, + "loss": 3.7648, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287492555833704e-05, + "loss": 3.7472, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286653961082652e-05, + "loss": 3.7584, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858153663316e-05, + "loss": 3.7515, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284978409460921e-05, + "loss": 3.7646, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.28413981470987e-05, + "loss": 3.7483, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283301219958818e-05, + "loss": 3.7632, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282462625207766e-05, + "loss": 3.753, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816256683370866e-05, + "loss": 3.7575, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807870735860346e-05, + "loss": 3.7576, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799484788349826e-05, + "loss": 3.7593, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791098840839306e-05, + "loss": 3.7577, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782729272132515e-05, + "loss": 3.7708, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774343324621995e-05, + "loss": 3.7605, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765957377111475e-05, + "loss": 3.765, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757571429600955e-05, + "loss": 3.7551, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749201860894164e-05, + "loss": 3.7594, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274081591338365e-05, + "loss": 3.7452, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273242996587313e-05, + "loss": 3.7535, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272404401836261e-05, + "loss": 3.7563, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271567444965582e-05, + "loss": 3.7616, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.27072885021453e-05, + "loss": 3.7584, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269890255463478e-05, + "loss": 3.7551, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269051660712426e-05, + "loss": 3.753, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268214703841747e-05, + "loss": 3.7556, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267376109090695e-05, + "loss": 3.7546, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266537514339643e-05, + "loss": 3.7599, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265698919588591e-05, + "loss": 3.7535, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264861962717912e-05, + "loss": 3.7502, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640233679668604e-05, + "loss": 3.7345, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631847732158084e-05, + "loss": 3.7624, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623461784647564e-05, + "loss": 3.7599, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261509221594077e-05, + "loss": 3.7618, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260670626843025e-05, + "loss": 3.753, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259832032091973e-05, + "loss": 3.76, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258993437340921e-05, + "loss": 3.7534, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258156480470242e-05, + "loss": 3.7655, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.25731788571919e-05, + "loss": 3.7496, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256479290968138e-05, + "loss": 3.754, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255640696217086e-05, + "loss": 3.7509, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254803739346407e-05, + "loss": 3.7507, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253965144595356e-05, + "loss": 3.7643, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253126549844304e-05, + "loss": 3.7524, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252287955093252e-05, + "loss": 3.7592, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251450998222573e-05, + "loss": 3.7457, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250612403471521e-05, + "loss": 3.7557, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8863143920898438, + "eval_runtime": 302.4746, + "eval_samples_per_second": 1261.564, + "eval_steps_per_second": 39.425, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249773808720469e-05, + "loss": 3.755, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248935213969417e-05, + "loss": 3.7485, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248096619218364e-05, + "loss": 3.754, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247258024467312e-05, + "loss": 3.7498, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.24641942971626e-05, + "loss": 3.7613, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245580834965208e-05, + "loss": 3.7474, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244742240214156e-05, + "loss": 3.7422, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243903645463104e-05, + "loss": 3.7351, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430666885924255e-05, + "loss": 3.7556, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422280938413735e-05, + "loss": 3.752, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413894990903215e-05, + "loss": 3.7443, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405509043392695e-05, + "loss": 3.7527, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239715585348964e-05, + "loss": 3.7482, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388769905979114e-05, + "loss": 3.7453, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380383958468593e-05, + "loss": 3.7373, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371998010958073e-05, + "loss": 3.7369, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363612063447553e-05, + "loss": 3.7392, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235522611593703e-05, + "loss": 3.7386, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234684016842651e-05, + "loss": 3.7486, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233845422091599e-05, + "loss": 3.7565, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233008465220921e-05, + "loss": 3.7534, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232169870469869e-05, + "loss": 3.747, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231331275718817e-05, + "loss": 3.7421, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230492680967765e-05, + "loss": 3.7433, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229655724097086e-05, + "loss": 3.7406, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228817129346034e-05, + "loss": 3.7451, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227978534594982e-05, + "loss": 3.7243, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.22713993984393e-05, + "loss": 3.75, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226302982973251e-05, + "loss": 3.7369, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225464388222199e-05, + "loss": 3.7307, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224625793471147e-05, + "loss": 3.7391, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223787198720095e-05, + "loss": 3.7484, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222950241849416e-05, + "loss": 3.7455, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222111647098364e-05, + "loss": 3.7454, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221273052347312e-05, + "loss": 3.7332, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.22043445759626e-05, + "loss": 3.7507, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219597500725581e-05, + "loss": 3.7429, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218758905974529e-05, + "loss": 3.7289, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217920311223477e-05, + "loss": 3.7281, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217081716472425e-05, + "loss": 3.7292, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216244759601746e-05, + "loss": 3.7358, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215406164850694e-05, + "loss": 3.7452, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214567570099642e-05, + "loss": 3.7338, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.21372897534859e-05, + "loss": 3.7346, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128920184779116e-05, + "loss": 3.7388, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120534237268596e-05, + "loss": 3.7336, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112148289758076e-05, + "loss": 3.7482, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103762342247556e-05, + "loss": 3.73, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2095392773540765e-05, + "loss": 3.7079, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2087006826030245e-05, + "loss": 3.7491, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078620878519725e-05, + "loss": 3.7409, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070251309812934e-05, + "loss": 3.7417, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061865362302414e-05, + "loss": 3.7345, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053479414791894e-05, + "loss": 3.7291, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045093467281374e-05, + "loss": 3.7234, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203672389857459e-05, + "loss": 3.7336, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202833795106407e-05, + "loss": 3.7288, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201995200355355e-05, + "loss": 3.7285, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201156605604303e-05, + "loss": 3.7383, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200319648733624e-05, + "loss": 3.7338, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199481053982572e-05, + "loss": 3.7197, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19864245923152e-05, + "loss": 3.7388, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197803864480468e-05, + "loss": 3.7216, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196966907609789e-05, + "loss": 3.7234, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196128312858737e-05, + "loss": 3.737, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195289718107685e-05, + "loss": 3.738, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194451123356633e-05, + "loss": 3.7167, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936141664859544e-05, + "loss": 3.7256, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927755717349024e-05, + "loss": 3.7131, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919369769838504e-05, + "loss": 3.7304, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910983822327984e-05, + "loss": 3.733, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190261425362119e-05, + "loss": 3.7328, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189422830611067e-05, + "loss": 3.7305, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188584235860015e-05, + "loss": 3.7333, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187745641108963e-05, + "loss": 3.7439, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186908684238284e-05, + "loss": 3.7208, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186070089487232e-05, + "loss": 3.7355, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.18523149473618e-05, + "loss": 3.7354, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184392899985128e-05, + "loss": 3.7185, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.18355594311445e-05, + "loss": 3.7334, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182718986243771e-05, + "loss": 3.7291, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818803914927187e-05, + "loss": 3.7325, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1810417967416667e-05, + "loss": 3.7333, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1802032019906146e-05, + "loss": 3.7182, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793646072395626e-05, + "loss": 3.7173, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1785260124885106e-05, + "loss": 3.7244, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776874177374586e-05, + "loss": 3.7331, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768504608667795e-05, + "loss": 3.7265, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760118661157275e-05, + "loss": 3.7238, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751732713646755e-05, + "loss": 3.7279, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743346766136235e-05, + "loss": 3.7294, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173497719742945e-05, + "loss": 3.7203, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172659124991893e-05, + "loss": 3.7053, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171820530240841e-05, + "loss": 3.7265, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170983573370162e-05, + "loss": 3.7271, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.17014497861911e-05, + "loss": 3.7313, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169306383868058e-05, + "loss": 3.712, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168467789117006e-05, + "loss": 3.7176, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167629194365954e-05, + "loss": 3.7245, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166790599614902e-05, + "loss": 3.7237, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165952004863849e-05, + "loss": 3.7327, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165113410112797e-05, + "loss": 3.721, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164276453242119e-05, + "loss": 3.7206, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163437858491067e-05, + "loss": 3.7272, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162599263740015e-05, + "loss": 3.7091, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161760668988963e-05, + "loss": 3.7217, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609237121182845e-05, + "loss": 3.7089, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160085117367232e-05, + "loss": 3.7325, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.15924652261618e-05, + "loss": 3.7104, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158407927865128e-05, + "loss": 3.7242, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575709709944494e-05, + "loss": 3.7186, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156732376243397e-05, + "loss": 3.7196, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155893781492345e-05, + "loss": 3.7227, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155055186741293e-05, + "loss": 3.7225, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154218229870614e-05, + "loss": 3.7217, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153379635119562e-05, + "loss": 3.7322, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15254104036851e-05, + "loss": 3.7192, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151702445617458e-05, + "loss": 3.7323, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150865488746779e-05, + "loss": 3.7176, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150026893995727e-05, + "loss": 3.7204, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149188299244675e-05, + "loss": 3.713, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148349704493623e-05, + "loss": 3.7136, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147512747622944e-05, + "loss": 3.7165, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146674152871892e-05, + "loss": 3.7265, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.14583555812084e-05, + "loss": 3.7197, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144996963369788e-05, + "loss": 3.7215, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441600064991096e-05, + "loss": 3.7182, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433214117480576e-05, + "loss": 3.7217, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424828169970056e-05, + "loss": 3.722, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416442222459536e-05, + "loss": 3.7182, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1408072653752745e-05, + "loss": 3.7165, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399686706242225e-05, + "loss": 3.7159, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1391300758731705e-05, + "loss": 3.699, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382914811221185e-05, + "loss": 3.7257, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374545242514394e-05, + "loss": 3.7222, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366159295003874e-05, + "loss": 3.7275, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357773347493354e-05, + "loss": 3.7132, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134940377878656e-05, + "loss": 3.7263, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134101783127604e-05, + "loss": 3.7208, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133263188376553e-05, + "loss": 3.7283, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132424593625501e-05, + "loss": 3.7126, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131587636754822e-05, + "loss": 3.7157, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.13074904200377e-05, + "loss": 3.7175, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129910447252718e-05, + "loss": 3.7169, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129073490382039e-05, + "loss": 3.723, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128234895630987e-05, + "loss": 3.72, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127396300879935e-05, + "loss": 3.7208, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126557706128883e-05, + "loss": 3.7115, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125719111377831e-05, + "loss": 3.7223, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.875913143157959, + "eval_runtime": 310.5555, + "eval_samples_per_second": 1228.737, + "eval_steps_per_second": 38.399, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124880516626779e-05, + "loss": 3.7114, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124041921875727e-05, + "loss": 3.7162, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123203327124675e-05, + "loss": 3.7135, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223663702539964e-05, + "loss": 3.7126, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1215277755029444e-05, + "loss": 3.7257, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120690818632265e-05, + "loss": 3.7148, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119852223881213e-05, + "loss": 3.7092, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119013629130161e-05, + "loss": 3.7036, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118175034379109e-05, + "loss": 3.7143, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117336439628057e-05, + "loss": 3.7202, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116497844877005e-05, + "loss": 3.709, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115659250125953e-05, + "loss": 3.7166, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114822293255274e-05, + "loss": 3.7184, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113983698504222e-05, + "loss": 3.707, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.11314510375317e-05, + "loss": 3.7059, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112306509002118e-05, + "loss": 3.7013, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111467914251067e-05, + "loss": 3.7051, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110629319500015e-05, + "loss": 3.7046, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109790724748963e-05, + "loss": 3.7081, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.10895212999791e-05, + "loss": 3.7242, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108115173127232e-05, + "loss": 3.7197, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.10727657837618e-05, + "loss": 3.7131, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106437983625127e-05, + "loss": 3.7066, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105599388874075e-05, + "loss": 3.7068, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047624320033966e-05, + "loss": 3.7076, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039238372523446e-05, + "loss": 3.7082, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103085242501292e-05, + "loss": 3.6924, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1022466477502406e-05, + "loss": 3.7152, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101409690879562e-05, + "loss": 3.702, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.10057109612851e-05, + "loss": 3.6973, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997325013774575e-05, + "loss": 3.6977, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988939066264055e-05, + "loss": 3.7175, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098056949755727e-05, + "loss": 3.7133, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972183550046744e-05, + "loss": 3.7103, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963797602536224e-05, + "loss": 3.6994, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955411655025704e-05, + "loss": 3.7115, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094704208631892e-05, + "loss": 3.7124, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093865613880839e-05, + "loss": 3.6966, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093027019129787e-05, + "loss": 3.6942, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092188424378736e-05, + "loss": 3.6942, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913514675080575e-05, + "loss": 3.7016, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090512872757005e-05, + "loss": 3.7077, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089674278005953e-05, + "loss": 3.7062, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888373211352744e-05, + "loss": 3.6995, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087998726384222e-05, + "loss": 3.7053, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.08716013163317e-05, + "loss": 3.7014, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.0863231747624913e-05, + "loss": 3.7095, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085484580011439e-05, + "loss": 3.6998, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.0846459852603867e-05, + "loss": 3.6756, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0838073905093346e-05, + "loss": 3.7128, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829687957582826e-05, + "loss": 3.7058, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082130201007231e-05, + "loss": 3.7113, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081291606256179e-05, + "loss": 3.7012, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080453011505127e-05, + "loss": 3.6949, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079616054634448e-05, + "loss": 3.6925, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078777459883396e-05, + "loss": 3.6994, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077938865132344e-05, + "loss": 3.7016, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077100270381292e-05, + "loss": 3.6892, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.07626167563024e-05, + "loss": 3.7057, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075423080879188e-05, + "loss": 3.7018, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074584486128136e-05, + "loss": 3.6857, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073745891377084e-05, + "loss": 3.7066, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072908934506405e-05, + "loss": 3.6903, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072070339755353e-05, + "loss": 3.6862, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071231745004301e-05, + "loss": 3.7012, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070393150253249e-05, + "loss": 3.7046, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069556193382571e-05, + "loss": 3.684, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068717598631519e-05, + "loss": 3.6926, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678790038804667e-05, + "loss": 3.6812, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6965, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0662034522587356e-05, + "loss": 3.7009, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653648575076836e-05, + "loss": 3.6987, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645262627566316e-05, + "loss": 3.6966, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636876680055796e-05, + "loss": 3.7007, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628507111349005e-05, + "loss": 3.7127, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620121163838485e-05, + "loss": 3.6855, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611735216327965e-05, + "loss": 3.704, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060336564762118e-05, + "loss": 3.7025, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059497970011066e-05, + "loss": 3.6855, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058659375260014e-05, + "loss": 3.7019, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057820780508962e-05, + "loss": 3.6975, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056983823638283e-05, + "loss": 3.6993, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056145228887231e-05, + "loss": 3.7044, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055306634136179e-05, + "loss": 3.6827, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054468039385127e-05, + "loss": 3.6874, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053629444634075e-05, + "loss": 3.6908, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052790849883023e-05, + "loss": 3.7011, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.05195225513197e-05, + "loss": 3.6918, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051113660380918e-05, + "loss": 3.6974, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.05027670351024e-05, + "loss": 3.697, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049438108759188e-05, + "loss": 3.6918, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048599514008136e-05, + "loss": 3.6911, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047760919257084e-05, + "loss": 3.6745, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469239623864054e-05, + "loss": 3.6916, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046087005515726e-05, + "loss": 3.6937, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045248410764674e-05, + "loss": 3.7008, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044409816013622e-05, + "loss": 3.6803, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.04357122126257e-05, + "loss": 3.6833, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427326265115176e-05, + "loss": 3.692, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418940317604656e-05, + "loss": 3.6905, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410554370094136e-05, + "loss": 3.696, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040216842258362e-05, + "loss": 3.6929, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039379885387683e-05, + "loss": 3.6909, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038541290636631e-05, + "loss": 3.6926, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037702695885579e-05, + "loss": 3.6822, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368657390149e-05, + "loss": 3.6865, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036027144263848e-05, + "loss": 3.6799, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035188549512796e-05, + "loss": 3.7003, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034349954761744e-05, + "loss": 3.6788, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033511360010692e-05, + "loss": 3.6907, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.03267276525964e-05, + "loss": 3.6846, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031834170508588e-05, + "loss": 3.692, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030995575757536e-05, + "loss": 3.689, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301586188868576e-05, + "loss": 3.6903, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293200241358056e-05, + "loss": 3.688, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.7021, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276444725140745e-05, + "loss": 3.6862, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268058777630225e-05, + "loss": 3.7018, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259672830119705e-05, + "loss": 3.6861, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.6892, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242917313902394e-05, + "loss": 3.6826, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234531366391874e-05, + "loss": 3.687, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226145418881354e-05, + "loss": 3.6826, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217759471370834e-05, + "loss": 3.6924, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020938990266404e-05, + "loss": 3.6856, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020102033395726e-05, + "loss": 3.6892, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019263438644674e-05, + "loss": 3.6917, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018424843893622e-05, + "loss": 3.6866, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.01758624914257e-05, + "loss": 3.6904, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016747654391518e-05, + "loss": 3.6927, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015909059640466e-05, + "loss": 3.6804, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015070464889414e-05, + "loss": 3.6879, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014231870138362e-05, + "loss": 3.6646, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013394913267683e-05, + "loss": 3.6943, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012556318516631e-05, + "loss": 3.6919, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011717723765579e-05, + "loss": 3.6974, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108807668949e-05, + "loss": 3.6831, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0100421721438484e-05, + "loss": 3.6929, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0092035773927964e-05, + "loss": 3.6906, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0083649826417444e-05, + "loss": 3.6957, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007528025771065e-05, + "loss": 3.6828, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006689431020013e-05, + "loss": 3.6872, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005850836268961e-05, + "loss": 3.6857, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005012241517909e-05, + "loss": 3.69, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004173646766857e-05, + "loss": 3.6899, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003335052015805e-05, + "loss": 3.686, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002496457264753e-05, + "loss": 3.6931, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016578625137006e-05, + "loss": 3.6778, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000820905643022e-05, + "loss": 3.696, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.869211435317993, + "eval_runtime": 322.4131, + "eval_samples_per_second": 1183.547, + "eval_steps_per_second": 36.987, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.99998231089197e-05, + "loss": 3.6833, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999143716140918e-05, + "loss": 3.6832, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998305121389866e-05, + "loss": 3.6867, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997466526638814e-05, + "loss": 3.6841, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996627931887762e-05, + "loss": 3.6965, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995790975017084e-05, + "loss": 3.6848, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994952380266031e-05, + "loss": 3.6776, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994113785514979e-05, + "loss": 3.6737, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993275190763927e-05, + "loss": 3.6816, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992436596012875e-05, + "loss": 3.6912, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991598001261823e-05, + "loss": 3.6824, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990759406510771e-05, + "loss": 3.6823, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989922449640092e-05, + "loss": 3.6873, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.98908385488904e-05, + "loss": 3.6777, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882452601379886e-05, + "loss": 3.6754, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874066653869366e-05, + "loss": 3.6702, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865697085162575e-05, + "loss": 3.6782, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857311137652055e-05, + "loss": 3.6718, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848925190141535e-05, + "loss": 3.6803, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840539242631015e-05, + "loss": 3.692, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832153295120495e-05, + "loss": 3.6905, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823767347609975e-05, + "loss": 3.6798, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815381400099455e-05, + "loss": 3.6781, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806995452588935e-05, + "loss": 3.6796, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9798625883882144e-05, + "loss": 3.676, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790239936371624e-05, + "loss": 3.6795, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978187036766484e-05, + "loss": 3.6646, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977348442015432e-05, + "loss": 3.6863, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97650984726438e-05, + "loss": 3.6744, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975671252513328e-05, + "loss": 3.6657, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974832657762276e-05, + "loss": 3.6702, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973994063011224e-05, + "loss": 3.6869, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973157106140545e-05, + "loss": 3.6856, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972318511389493e-05, + "loss": 3.6819, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971479916638441e-05, + "loss": 3.6719, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970641321887389e-05, + "loss": 3.6753, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969802727136337e-05, + "loss": 3.6875, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968964132385284e-05, + "loss": 3.6678, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968125537634232e-05, + "loss": 3.6647, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967286942883181e-05, + "loss": 3.6694, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664499860125024e-05, + "loss": 3.6706, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.96561139126145e-05, + "loss": 3.6797, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964772796510398e-05, + "loss": 3.6707, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963934201759346e-05, + "loss": 3.6775, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963097244888667e-05, + "loss": 3.6709, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622586501376146e-05, + "loss": 3.67, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961421693266936e-05, + "loss": 3.6857, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960583098515884e-05, + "loss": 3.6683, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597445037648315e-05, + "loss": 3.6499, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9589059090137795e-05, + "loss": 3.6807, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580673142627275e-05, + "loss": 3.6744, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957228719511676e-05, + "loss": 3.6831, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956391762640997e-05, + "loss": 3.6757, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955553167889945e-05, + "loss": 3.6642, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954714573138893e-05, + "loss": 3.6632, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953875978387841e-05, + "loss": 3.6685, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953037383636789e-05, + "loss": 3.6756, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952198788885737e-05, + "loss": 3.6579, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951360194134685e-05, + "loss": 3.6802, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950521599383633e-05, + "loss": 3.6717, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949684642512954e-05, + "loss": 3.6574, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948846047761902e-05, + "loss": 3.6763, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.94800745301085e-05, + "loss": 3.6605, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947170496140171e-05, + "loss": 3.6596, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463319013891195e-05, + "loss": 3.6719, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454933066380675e-05, + "loss": 3.6821, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446547118870155e-05, + "loss": 3.6494, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438177550163364e-05, + "loss": 3.669, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429791602652844e-05, + "loss": 3.6532, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421405655142324e-05, + "loss": 3.669, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413019707631804e-05, + "loss": 3.6744, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940465013892501e-05, + "loss": 3.6657, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939626419141449e-05, + "loss": 3.6743, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938787824390397e-05, + "loss": 3.6685, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937949229639345e-05, + "loss": 3.6878, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937110634888293e-05, + "loss": 3.6555, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936273678017615e-05, + "loss": 3.6776, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935435083266563e-05, + "loss": 3.6705, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934596488515511e-05, + "loss": 3.6628, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933757893764459e-05, + "loss": 3.6737, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.93292093689378e-05, + "loss": 3.6691, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932082342142728e-05, + "loss": 3.67, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931243747391676e-05, + "loss": 3.6764, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930405152640624e-05, + "loss": 3.6533, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929566557889572e-05, + "loss": 3.6599, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928729601018893e-05, + "loss": 3.6635, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927891006267841e-05, + "loss": 3.6741, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927052411516789e-05, + "loss": 3.6622, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926213816765737e-05, + "loss": 3.6674, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925376859895058e-05, + "loss": 3.6704, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924538265144006e-05, + "loss": 3.6657, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923699670392954e-05, + "loss": 3.6616, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922861075641902e-05, + "loss": 3.6458, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.6628, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921185524020171e-05, + "loss": 3.6663, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920346929269119e-05, + "loss": 3.673, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919508334518067e-05, + "loss": 3.6551, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918669739767015e-05, + "loss": 3.6562, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178311450159625e-05, + "loss": 3.6627, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169925502649105e-05, + "loss": 3.6673, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916155593394232e-05, + "loss": 3.6695, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.91531699864318e-05, + "loss": 3.6651, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914478403892128e-05, + "loss": 3.6667, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913639809141076e-05, + "loss": 3.6582, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912801214390024e-05, + "loss": 3.6598, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911964257519345e-05, + "loss": 3.6552, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911125662768293e-05, + "loss": 3.6568, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910287068017241e-05, + "loss": 3.6753, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909448473266189e-05, + "loss": 3.6522, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.90861151639551e-05, + "loss": 3.6617, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907772921644458e-05, + "loss": 3.6523, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906934326893406e-05, + "loss": 3.6672, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906095732142354e-05, + "loss": 3.6617, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052571373913025e-05, + "loss": 3.6624, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044185426402505e-05, + "loss": 3.6621, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035799478891985e-05, + "loss": 3.6744, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027413531381465e-05, + "loss": 3.6624, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019043962674674e-05, + "loss": 3.6714, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010658015164154e-05, + "loss": 3.6602, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002272067653634e-05, + "loss": 3.6629, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993886120143114e-05, + "loss": 3.6555, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985500172632594e-05, + "loss": 3.6588, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977114225122074e-05, + "loss": 3.6547, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968728277611554e-05, + "loss": 3.6633, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896035870890476e-05, + "loss": 3.6593, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895197276139424e-05, + "loss": 3.6631, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894358681388372e-05, + "loss": 3.6621, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.89352008663732e-05, + "loss": 3.6634, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892681491886269e-05, + "loss": 3.6618, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891842897135217e-05, + "loss": 3.6664, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891005940264538e-05, + "loss": 3.6532, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890167345513486e-05, + "loss": 3.6647, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889328750762434e-05, + "loss": 3.6363, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888490156011381e-05, + "loss": 3.6708, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887651561260329e-05, + "loss": 3.665, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886812966509277e-05, + "loss": 3.6731, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885976009638599e-05, + "loss": 3.6537, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885137414887546e-05, + "loss": 3.6686, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884298820136494e-05, + "loss": 3.6614, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883460225385443e-05, + "loss": 3.6741, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882621630634391e-05, + "loss": 3.6538, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817846737637116e-05, + "loss": 3.6577, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8809460790126596e-05, + "loss": 3.657, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801074842616076e-05, + "loss": 3.6699, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792688895105556e-05, + "loss": 3.6588, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784302947595036e-05, + "loss": 3.6596, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775917000084516e-05, + "loss": 3.6661, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767547431377725e-05, + "loss": 3.6568, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759161483867205e-05, + "loss": 3.668, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8647994995117188, + "eval_runtime": 309.3167, + "eval_samples_per_second": 1233.658, + "eval_steps_per_second": 38.553, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750775536356685e-05, + "loss": 3.6501, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742389588846165e-05, + "loss": 3.66, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734003641335645e-05, + "loss": 3.656, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872563407262886e-05, + "loss": 3.6608, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871724812511834e-05, + "loss": 3.6718, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870886217760782e-05, + "loss": 3.6559, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.87004762300973e-05, + "loss": 3.6505, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869209028258678e-05, + "loss": 3.649, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868372071387999e-05, + "loss": 3.6575, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867533476636947e-05, + "loss": 3.664, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866694881885895e-05, + "loss": 3.6521, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865856287134843e-05, + "loss": 3.6566, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865019330264164e-05, + "loss": 3.662, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864180735513112e-05, + "loss": 3.6524, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.86334214076206e-05, + "loss": 3.649, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862503546011008e-05, + "loss": 3.642, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616649512599565e-05, + "loss": 3.655, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608263565089045e-05, + "loss": 3.6493, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599877617578525e-05, + "loss": 3.6488, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591491670068e-05, + "loss": 3.6633, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858313848016494e-05, + "loss": 3.6629, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857475253265442e-05, + "loss": 3.6578, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.85663665851439e-05, + "loss": 3.6519, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855798063763338e-05, + "loss": 3.6533, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854959469012286e-05, + "loss": 3.6531, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854120874261234e-05, + "loss": 3.6536, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853283917390555e-05, + "loss": 3.6375, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852445322639503e-05, + "loss": 3.6571, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851606727888452e-05, + "loss": 3.6507, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507681331374e-05, + "loss": 3.6404, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849929538386347e-05, + "loss": 3.6464, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849090943635295e-05, + "loss": 3.6549, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848253986764617e-05, + "loss": 3.6586, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847415392013565e-05, + "loss": 3.6588, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846576797262512e-05, + "loss": 3.6504, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.84573820251146e-05, + "loss": 3.6474, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844901245640782e-05, + "loss": 3.6645, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.84406265088973e-05, + "loss": 3.6418, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843224056138677e-05, + "loss": 3.64, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842385461387626e-05, + "loss": 3.6421, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841546866636574e-05, + "loss": 3.6459, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840708271885522e-05, + "loss": 3.6508, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398696771344697e-05, + "loss": 3.6477, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390327202637906e-05, + "loss": 3.6515, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381941255127386e-05, + "loss": 3.6462, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373555307616866e-05, + "loss": 3.6444, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365185738910075e-05, + "loss": 3.6562, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356799791399555e-05, + "loss": 3.6474, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348413843889035e-05, + "loss": 3.6255, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340027896378515e-05, + "loss": 3.6543, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331641948867994e-05, + "loss": 3.6508, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323256001357474e-05, + "loss": 3.6589, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831488643265069e-05, + "loss": 3.6478, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830650048514017e-05, + "loss": 3.6417, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829811453762965e-05, + "loss": 3.6352, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828972859011913e-05, + "loss": 3.6425, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828134264260861e-05, + "loss": 3.6498, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827295669509809e-05, + "loss": 3.6353, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826457074758757e-05, + "loss": 3.6513, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825618480007705e-05, + "loss": 3.6469, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824781523137026e-05, + "loss": 3.6381, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823942928385974e-05, + "loss": 3.6468, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823104333634922e-05, + "loss": 3.6348, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.82226573888387e-05, + "loss": 3.6365, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821428782013191e-05, + "loss": 3.6422, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820590187262139e-05, + "loss": 3.654, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197515925110875e-05, + "loss": 3.6317, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189146356404084e-05, + "loss": 3.6453, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180760408893564e-05, + "loss": 3.6259, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172374461383044e-05, + "loss": 3.6437, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816400489267625e-05, + "loss": 3.6478, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815561894516573e-05, + "loss": 3.6453, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814723299765521e-05, + "loss": 3.643, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813884705014469e-05, + "loss": 3.6456, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813046110263417e-05, + "loss": 3.6595, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812209153392738e-05, + "loss": 3.6343, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811370558641686e-05, + "loss": 3.6524, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810531963890634e-05, + "loss": 3.6397, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809693369139583e-05, + "loss": 3.6412, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808854774388531e-05, + "loss": 3.6481, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808017817517852e-05, + "loss": 3.6415, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071792227668e-05, + "loss": 3.647, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806340628015748e-05, + "loss": 3.6549, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805502033264696e-05, + "loss": 3.6253, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046650763940166e-05, + "loss": 3.6375, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038264816429646e-05, + "loss": 3.6385, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029878868919126e-05, + "loss": 3.649, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.80214929214086e-05, + "loss": 3.6354, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801310697389808e-05, + "loss": 3.6467, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004721026387566e-05, + "loss": 3.6434, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799635145768078e-05, + "loss": 3.6424, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987965510170255e-05, + "loss": 3.6368, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979579562659735e-05, + "loss": 3.623, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971193615149215e-05, + "loss": 3.6349, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796282404644243e-05, + "loss": 3.6439, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954438098931904e-05, + "loss": 3.6498, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946052151421384e-05, + "loss": 3.6279, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937666203910864e-05, + "loss": 3.6335, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929280256400344e-05, + "loss": 3.6385, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792091068769355e-05, + "loss": 3.6391, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791252474018303e-05, + "loss": 3.6433, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790413879267252e-05, + "loss": 3.6425, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895752845162e-05, + "loss": 3.6392, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788738327645521e-05, + "loss": 3.6353, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787899732894469e-05, + "loss": 3.6385, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787061138143417e-05, + "loss": 3.629, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786222543392365e-05, + "loss": 3.6328, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785383948641313e-05, + "loss": 3.6461, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784545353890261e-05, + "loss": 3.6325, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783706759139209e-05, + "loss": 3.6359, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.78286980226853e-05, + "loss": 3.6283, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782031207517478e-05, + "loss": 3.6383, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781192612766426e-05, + "loss": 3.6382, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780354018015374e-05, + "loss": 3.6382, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779515423264322e-05, + "loss": 3.6389, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786768285132704e-05, + "loss": 3.6529, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778382337622184e-05, + "loss": 3.6383, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777001276891539e-05, + "loss": 3.6423, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776162682140487e-05, + "loss": 3.6422, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775324087389435e-05, + "loss": 3.6342, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774485492638383e-05, + "loss": 3.6383, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773646897887331e-05, + "loss": 3.6303, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772809941016652e-05, + "loss": 3.6322, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719713462656e-05, + "loss": 3.6394, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771132751514548e-05, + "loss": 3.6377, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770294156763496e-05, + "loss": 3.6404, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769455562012444e-05, + "loss": 3.6352, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768618605141765e-05, + "loss": 3.6424, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767780010390714e-05, + "loss": 3.6324, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766941415639662e-05, + "loss": 3.6447, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766102820888609e-05, + "loss": 3.633, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765265864017931e-05, + "loss": 3.6356, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764427269266879e-05, + "loss": 3.6109, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763588674515827e-05, + "loss": 3.6461, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762750079764774e-05, + "loss": 3.639, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761911485013722e-05, + "loss": 3.6513, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610745281430436e-05, + "loss": 3.6308, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760235933391991e-05, + "loss": 3.6434, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759397338640939e-05, + "loss": 3.6339, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585587438898876e-05, + "loss": 3.6535, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757721787019209e-05, + "loss": 3.631, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568831922681565e-05, + "loss": 3.6354, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7560445975171045e-05, + "loss": 3.634, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7552060027660525e-05, + "loss": 3.6444, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543674080150005e-05, + "loss": 3.6358, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535304511443214e-05, + "loss": 3.635, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526918563932694e-05, + "loss": 3.6387, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518532616422174e-05, + "loss": 3.6359, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510146668911654e-05, + "loss": 3.6404, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.861380100250244, + "eval_runtime": 307.7051, + "eval_samples_per_second": 1240.119, + "eval_steps_per_second": 38.755, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501760721401134e-05, + "loss": 3.6259, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493374773890614e-05, + "loss": 3.6345, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484988826380093e-05, + "loss": 3.6357, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476602878869573e-05, + "loss": 3.6362, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746823331016279e-05, + "loss": 3.6483, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745984736265227e-05, + "loss": 3.6318, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745146141514175e-05, + "loss": 3.6307, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744307546763123e-05, + "loss": 3.6248, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743468952012071e-05, + "loss": 3.6305, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742631995141392e-05, + "loss": 3.6369, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.74179340039034e-05, + "loss": 3.6365, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740954805639288e-05, + "loss": 3.6327, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740117848768609e-05, + "loss": 3.6415, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739279254017557e-05, + "loss": 3.6287, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738440659266505e-05, + "loss": 3.6248, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737602064515453e-05, + "loss": 3.617, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367634697644014e-05, + "loss": 3.6324, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359248750133494e-05, + "loss": 3.6268, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350862802622974e-05, + "loss": 3.6278, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342476855112454e-05, + "loss": 3.6395, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733409090760193e-05, + "loss": 3.6424, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732572133889514e-05, + "loss": 3.6332, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731733539138462e-05, + "loss": 3.6263, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308949443874096e-05, + "loss": 3.6321, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300563496363576e-05, + "loss": 3.6305, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729219392765679e-05, + "loss": 3.6316, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728380798014627e-05, + "loss": 3.6153, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727542203263575e-05, + "loss": 3.6331, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726703608512523e-05, + "loss": 3.6301, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725865013761471e-05, + "loss": 3.6157, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725026419010419e-05, + "loss": 3.6254, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.72418946213974e-05, + "loss": 3.6347, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723350867388688e-05, + "loss": 3.6302, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722512272637636e-05, + "loss": 3.6392, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721673677886584e-05, + "loss": 3.6253, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720835083135532e-05, + "loss": 3.6221, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719998126264853e-05, + "loss": 3.6467, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719159531513801e-05, + "loss": 3.6142, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718320936762749e-05, + "loss": 3.6166, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717482342011697e-05, + "loss": 3.6219, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166453851410185e-05, + "loss": 3.6209, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158067903899665e-05, + "loss": 3.6243, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149681956389145e-05, + "loss": 3.6285, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141296008878625e-05, + "loss": 3.6292, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132910061368105e-05, + "loss": 3.6251, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124524113857585e-05, + "loss": 3.621, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116154545150794e-05, + "loss": 3.6308, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107768597640274e-05, + "loss": 3.6243, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7099382650129754e-05, + "loss": 3.6056, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7090996702619234e-05, + "loss": 3.6296, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7082610755108714e-05, + "loss": 3.6277, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074224807598194e-05, + "loss": 3.6355, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.70658552388914e-05, + "loss": 3.6253, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705746929138088e-05, + "loss": 3.6229, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704908334387037e-05, + "loss": 3.6107, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704069739635985e-05, + "loss": 3.616, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703231144884933e-05, + "loss": 3.6292, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702392550133881e-05, + "loss": 3.6135, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701553955382828e-05, + "loss": 3.6251, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700715360631776e-05, + "loss": 3.6248, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699878403761098e-05, + "loss": 3.6166, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699041446890419e-05, + "loss": 3.6246, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698202852139367e-05, + "loss": 3.6124, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697364257388315e-05, + "loss": 3.6154, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696525662637263e-05, + "loss": 3.6197, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695687067886211e-05, + "loss": 3.6317, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694848473135159e-05, + "loss": 3.6092, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.69401151626448e-05, + "loss": 3.6239, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693172921513428e-05, + "loss": 3.6036, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923343267623756e-05, + "loss": 3.6212, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6914957320113236e-05, + "loss": 3.624, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690658775140645e-05, + "loss": 3.627, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689820180389593e-05, + "loss": 3.6206, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889815856385405e-05, + "loss": 3.6206, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881429908874885e-05, + "loss": 3.639, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873043961364365e-05, + "loss": 3.6113, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686467439265758e-05, + "loss": 3.634, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685628844514706e-05, + "loss": 3.6155, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684790249763654e-05, + "loss": 3.6166, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683951655012602e-05, + "loss": 3.6262, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.68311306026155e-05, + "loss": 3.619, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682276103390871e-05, + "loss": 3.6261, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681437508639819e-05, + "loss": 3.6311, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680598913888767e-05, + "loss": 3.6109, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679760319137715e-05, + "loss": 3.6105, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678923362267036e-05, + "loss": 3.6149, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678084767515984e-05, + "loss": 3.6241, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677246172764932e-05, + "loss": 3.6153, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.67640757801388e-05, + "loss": 3.6237, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675568983262828e-05, + "loss": 3.6233, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747320263921495e-05, + "loss": 3.621, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738934316410975e-05, + "loss": 3.6119, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730548368900455e-05, + "loss": 3.6056, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722162421389935e-05, + "loss": 3.6093, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713792852683144e-05, + "loss": 3.6233, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6705406905172624e-05, + "loss": 3.6263, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6697020957662104e-05, + "loss": 3.6061, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6688635010151584e-05, + "loss": 3.6109, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680249062641064e-05, + "loss": 3.6155, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667187949393427e-05, + "loss": 3.6203, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666349354642375e-05, + "loss": 3.6223, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665510759891323e-05, + "loss": 3.6177, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664672165140271e-05, + "loss": 3.617, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663835208269593e-05, + "loss": 3.6142, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662996613518541e-05, + "loss": 3.6133, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662158018767489e-05, + "loss": 3.6096, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661319424016437e-05, + "loss": 3.6138, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660480829265385e-05, + "loss": 3.6201, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659643872394706e-05, + "loss": 3.6119, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658805277643654e-05, + "loss": 3.6153, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657966682892602e-05, + "loss": 3.6061, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.65712808814155e-05, + "loss": 3.6154, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562911312708706e-05, + "loss": 3.618, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6554525365198186e-05, + "loss": 3.615, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6546139417687666e-05, + "loss": 3.6174, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653775347017715e-05, + "loss": 3.6316, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652936752266663e-05, + "loss": 3.6184, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652099795395984e-05, + "loss": 3.6204, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651261200644932e-05, + "loss": 3.6214, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.65042260589388e-05, + "loss": 3.6135, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649584011142828e-05, + "loss": 3.6181, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648747054272149e-05, + "loss": 3.6045, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647908459521097e-05, + "loss": 3.6098, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647069864770045e-05, + "loss": 3.6198, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646231270018993e-05, + "loss": 3.6194, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645394313148314e-05, + "loss": 3.6137, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644555718397262e-05, + "loss": 3.6162, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.64371712364621e-05, + "loss": 3.6174, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428785288951587e-05, + "loss": 3.6139, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420399341441067e-05, + "loss": 3.6192, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412029772734276e-05, + "loss": 3.614, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403643825223756e-05, + "loss": 3.6128, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395257877713236e-05, + "loss": 3.5915, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386871930202715e-05, + "loss": 3.6245, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6378502361495925e-05, + "loss": 3.6146, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6370116413985405e-05, + "loss": 3.6296, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6361730466474884e-05, + "loss": 3.6104, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635334451896436e-05, + "loss": 3.6186, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634495857145384e-05, + "loss": 3.6154, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336589002747053e-05, + "loss": 3.6342, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632820305523654e-05, + "loss": 3.605, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319817107726013e-05, + "loss": 3.614, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631143116021549e-05, + "loss": 3.6132, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630304521270497e-05, + "loss": 3.6225, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629467564399819e-05, + "loss": 3.6149, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628628969648766e-05, + "loss": 3.6147, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627790374897714e-05, + "loss": 3.6153, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626951780146662e-05, + "loss": 3.6219, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626114823275983e-05, + "loss": 3.619, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.86030912399292, + "eval_runtime": 311.1738, + "eval_samples_per_second": 1226.295, + "eval_steps_per_second": 38.323, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625276228524931e-05, + "loss": 3.6082, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624437633773879e-05, + "loss": 3.6121, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623599039022828e-05, + "loss": 3.614, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622762082152149e-05, + "loss": 3.617, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621923487401097e-05, + "loss": 3.6206, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621084892650045e-05, + "loss": 3.6114, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620246297898993e-05, + "loss": 3.6139, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619407703147941e-05, + "loss": 3.6045, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185707462772616e-05, + "loss": 3.6082, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177321515262096e-05, + "loss": 3.617, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6168935567751576e-05, + "loss": 3.6158, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160549620241056e-05, + "loss": 3.6101, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152180051534265e-05, + "loss": 3.625, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6143794104023745e-05, + "loss": 3.6017, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613540815651323e-05, + "loss": 3.6067, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612702220900271e-05, + "loss": 3.5975, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611865264029592e-05, + "loss": 3.614, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.61102666927854e-05, + "loss": 3.604, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610188074527488e-05, + "loss": 3.6088, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609349479776436e-05, + "loss": 3.6183, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608510885025384e-05, + "loss": 3.6211, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607673928154705e-05, + "loss": 3.6151, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606835333403653e-05, + "loss": 3.6059, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605996738652601e-05, + "loss": 3.6124, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605158143901549e-05, + "loss": 3.6109, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.60432118703087e-05, + "loss": 3.6087, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034825922798185e-05, + "loss": 3.5964, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026439975287665e-05, + "loss": 3.6104, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6018054027777145e-05, + "loss": 3.6076, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009668080266625e-05, + "loss": 3.5939, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001282132756105e-05, + "loss": 3.6064, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992912564049314e-05, + "loss": 3.6131, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5984526616538794e-05, + "loss": 3.6081, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5976140669028274e-05, + "loss": 3.6182, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.5967754721517754e-05, + "loss": 3.606, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595938515281096e-05, + "loss": 3.6034, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595099920530044e-05, + "loss": 3.6278, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594261325778992e-05, + "loss": 3.5919, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.59342273102794e-05, + "loss": 3.5982, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592585774157262e-05, + "loss": 3.6024, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.59174717940621e-05, + "loss": 3.599, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590908584655158e-05, + "loss": 3.6032, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590069989904106e-05, + "loss": 3.612, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589233033033427e-05, + "loss": 3.6052, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588394438282375e-05, + "loss": 3.6057, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587555843531323e-05, + "loss": 3.5975, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586717248780271e-05, + "loss": 3.6099, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585878654029219e-05, + "loss": 3.6068, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585040059278167e-05, + "loss": 3.5836, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584201464527114e-05, + "loss": 3.6095, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583362869776062e-05, + "loss": 3.6095, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582525912905384e-05, + "loss": 3.612, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581688956034705e-05, + "loss": 3.6035, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580850361283653e-05, + "loss": 3.6, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580011766532601e-05, + "loss": 3.5974, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579173171781549e-05, + "loss": 3.5942, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.57833621491087e-05, + "loss": 3.6108, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577497620159818e-05, + "loss": 3.5925, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576659025408766e-05, + "loss": 3.6061, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575820430657714e-05, + "loss": 3.6018, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5749818359066615e-05, + "loss": 3.5988, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574144879035983e-05, + "loss": 3.5996, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573306284284931e-05, + "loss": 3.5973, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572467689533879e-05, + "loss": 3.5981, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571629094782827e-05, + "loss": 3.5908, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570790500031775e-05, + "loss": 3.6137, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569951905280723e-05, + "loss": 3.5947, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569114948410044e-05, + "loss": 3.5943, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568276353658992e-05, + "loss": 3.5877, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.56743775890794e-05, + "loss": 3.5991, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566599164156888e-05, + "loss": 3.6032, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565762207286209e-05, + "loss": 3.6056, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564923612535157e-05, + "loss": 3.6022, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564085017784105e-05, + "loss": 3.6016, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563246423033053e-05, + "loss": 3.6151, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562407828282001e-05, + "loss": 3.5938, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615708714113224e-05, + "loss": 3.6152, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607322766602704e-05, + "loss": 3.5961, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598936819092184e-05, + "loss": 3.5978, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590550871581664e-05, + "loss": 3.6039, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582164924071144e-05, + "loss": 3.5969, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557379535536435e-05, + "loss": 3.6061, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556540940785383e-05, + "loss": 3.6147, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555702346034331e-05, + "loss": 3.5949, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554863751283279e-05, + "loss": 3.5857, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5540267944126e-05, + "loss": 3.5965, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553188199661548e-05, + "loss": 3.6018, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552349604910496e-05, + "loss": 3.5971, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551511010159445e-05, + "loss": 3.6006, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550674053288766e-05, + "loss": 3.603, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549835458537714e-05, + "loss": 3.6024, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548996863786662e-05, + "loss": 3.592, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.54815826903561e-05, + "loss": 3.5849, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547319674284558e-05, + "loss": 3.5923, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464827174138787e-05, + "loss": 3.5977, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456441226628266e-05, + "loss": 3.6132, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448055279117746e-05, + "loss": 3.583, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439669331607226e-05, + "loss": 3.5923, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431299762900436e-05, + "loss": 3.5984, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422913815389915e-05, + "loss": 3.5961, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.54145278678794e-05, + "loss": 3.6025, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540614192036888e-05, + "loss": 3.5978, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539775597285836e-05, + "loss": 3.6008, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538938640415157e-05, + "loss": 3.5928, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538100045664105e-05, + "loss": 3.5932, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537261450913053e-05, + "loss": 3.5907, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536422856162001e-05, + "loss": 3.5945, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535585899291322e-05, + "loss": 3.6008, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.53474730454027e-05, + "loss": 3.5946, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533908709789218e-05, + "loss": 3.5927, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533070115038166e-05, + "loss": 3.5835, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532231520287114e-05, + "loss": 3.5953, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313945634164356e-05, + "loss": 3.6005, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305559686653836e-05, + "loss": 3.5987, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5297173739143316e-05, + "loss": 3.5949, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5288787791632796e-05, + "loss": 3.6049, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280401844122276e-05, + "loss": 3.6023, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5272032275415485e-05, + "loss": 3.6033, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5263646327904965e-05, + "loss": 3.6018, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5255260380394445e-05, + "loss": 3.5948, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5246874432883925e-05, + "loss": 3.5957, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238504864177134e-05, + "loss": 3.5874, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230118916666614e-05, + "loss": 3.591, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5221732969156094e-05, + "loss": 3.5982, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213347021645574e-05, + "loss": 3.5993, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5204961074135054e-05, + "loss": 3.5931, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519659150542827e-05, + "loss": 3.5962, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518820555791775e-05, + "loss": 3.5976, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517981961040722e-05, + "loss": 3.5937, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517145004170044e-05, + "loss": 3.6006, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516306409418992e-05, + "loss": 3.5964, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.51546781466794e-05, + "loss": 3.5963, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514629219916887e-05, + "loss": 3.5699, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513790625165835e-05, + "loss": 3.6048, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512953668295157e-05, + "loss": 3.5943, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512115073544105e-05, + "loss": 3.6092, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511276478793053e-05, + "loss": 3.5955, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510437884042001e-05, + "loss": 3.5949, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509599289290949e-05, + "loss": 3.5983, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508760694539897e-05, + "loss": 3.61, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079237376692176e-05, + "loss": 3.5862, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5070851429181656e-05, + "loss": 3.5983, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062465481671136e-05, + "loss": 3.5929, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5054079534160616e-05, + "loss": 3.5983, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5045693586650096e-05, + "loss": 3.6, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037324017943305e-05, + "loss": 3.5942, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028938070432785e-05, + "loss": 3.5936, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020552122922265e-05, + "loss": 3.601, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012166175411745e-05, + "loss": 3.5962, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8590054512023926, + "eval_runtime": 309.8859, + "eval_samples_per_second": 1231.392, + "eval_steps_per_second": 38.482, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003780227901225e-05, + "loss": 3.6015, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499539428039071e-05, + "loss": 3.5917, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498700833288019e-05, + "loss": 3.593, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497862238536967e-05, + "loss": 3.5992, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497025281666288e-05, + "loss": 3.5998, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496186686915236e-05, + "loss": 3.597, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495348092164184e-05, + "loss": 3.5938, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494509497413132e-05, + "loss": 3.5818, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493672540542453e-05, + "loss": 3.5866, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492833945791401e-05, + "loss": 3.6038, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491995351040349e-05, + "loss": 3.5926, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491156756289297e-05, + "loss": 3.588, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490319799418618e-05, + "loss": 3.6088, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894812046675665e-05, + "loss": 3.582, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886426099165145e-05, + "loss": 3.5871, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878040151654625e-05, + "loss": 3.58, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869654204144105e-05, + "loss": 3.5934, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861284635437314e-05, + "loss": 3.5834, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4852898687926794e-05, + "loss": 3.589, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4844512740416274e-05, + "loss": 3.5991, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4836126792905754e-05, + "loss": 3.5976, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482775722419896e-05, + "loss": 3.5981, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481937127668844e-05, + "loss": 3.5838, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481098532917792e-05, + "loss": 3.592, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48025993816674e-05, + "loss": 3.5963, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479422981296062e-05, + "loss": 3.5862, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.47858438654501e-05, + "loss": 3.5777, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477745791793958e-05, + "loss": 3.5887, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476907197042906e-05, + "loss": 3.5909, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476068602291853e-05, + "loss": 3.5744, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475231645421175e-05, + "loss": 3.5864, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474393050670123e-05, + "loss": 3.5889, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473554455919071e-05, + "loss": 3.5952, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472715861168018e-05, + "loss": 3.5964, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.47187890429734e-05, + "loss": 3.5866, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471040309546288e-05, + "loss": 3.5919, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470201714795236e-05, + "loss": 3.6041, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469363120044184e-05, + "loss": 3.5742, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468524525293132e-05, + "loss": 3.5796, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467687568422453e-05, + "loss": 3.587, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668489736714006e-05, + "loss": 3.5755, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660103789203486e-05, + "loss": 3.5869, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4651717841692966e-05, + "loss": 3.5919, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464334827298618e-05, + "loss": 3.5866, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4634962325475655e-05, + "loss": 3.5863, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626576377965135e-05, + "loss": 3.5834, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618190430454615e-05, + "loss": 3.5884, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609804482944095e-05, + "loss": 3.5943, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460143491423731e-05, + "loss": 3.5601, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459304896672679e-05, + "loss": 3.5864, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458466301921627e-05, + "loss": 3.5946, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457627707170575e-05, + "loss": 3.5922, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456789112419523e-05, + "loss": 3.5887, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455952155548844e-05, + "loss": 3.5781, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455113560797792e-05, + "loss": 3.5804, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.45427496604674e-05, + "loss": 3.5743, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453436371295688e-05, + "loss": 3.59, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452599414425009e-05, + "loss": 3.574, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451760819673957e-05, + "loss": 3.5899, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450922224922905e-05, + "loss": 3.5809, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450083630171853e-05, + "loss": 3.5821, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4492466733011744e-05, + "loss": 3.5765, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484080785501224e-05, + "loss": 3.5833, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475694837990704e-05, + "loss": 3.5775, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467308890480184e-05, + "loss": 3.5745, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458922942969664e-05, + "loss": 3.5907, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450536995459144e-05, + "loss": 3.5824, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444216742675235e-05, + "loss": 3.5736, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443378147924183e-05, + "loss": 3.5676, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442539553173131e-05, + "loss": 3.5851, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441700958422079e-05, + "loss": 3.581, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408640015514e-05, + "loss": 3.5901, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440025406800348e-05, + "loss": 3.5813, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439186812049296e-05, + "loss": 3.5861, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438348217298245e-05, + "loss": 3.5945, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437511260427566e-05, + "loss": 3.5781, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436672665676514e-05, + "loss": 3.5921, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435834070925462e-05, + "loss": 3.5829, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.43499547617441e-05, + "loss": 3.5758, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434158519303731e-05, + "loss": 3.5867, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433319924552679e-05, + "loss": 3.5803, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324813298016267e-05, + "loss": 3.5835, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316427350505747e-05, + "loss": 3.5976, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308057781798956e-05, + "loss": 3.5799, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4299671834288436e-05, + "loss": 3.5673, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291285886777916e-05, + "loss": 3.5755, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282899939267396e-05, + "loss": 3.5812, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427453037056061e-05, + "loss": 3.5841, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426614442305009e-05, + "loss": 3.5806, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425775847553957e-05, + "loss": 3.5865, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424937252802905e-05, + "loss": 3.5844, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424098658051853e-05, + "loss": 3.5713, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423261701181174e-05, + "loss": 3.5638, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422423106430122e-05, + "loss": 3.5734, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.42158451167907e-05, + "loss": 3.5779, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420745916928018e-05, + "loss": 3.5978, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419908960057339e-05, + "loss": 3.5654, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419070365306287e-05, + "loss": 3.573, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418231770555235e-05, + "loss": 3.5806, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4173931758041836e-05, + "loss": 3.5785, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165545810531316e-05, + "loss": 3.5853, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157176241824525e-05, + "loss": 3.5809, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4148790294314005e-05, + "loss": 3.5749, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140404346803485e-05, + "loss": 3.5785, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413201839929296e-05, + "loss": 3.5743, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123648830586174e-05, + "loss": 3.5712, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115262883075654e-05, + "loss": 3.5796, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4106876935565134e-05, + "loss": 3.5836, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409849098805461e-05, + "loss": 3.577, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409010504054409e-05, + "loss": 3.5726, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.40817354718373e-05, + "loss": 3.5706, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407334952432679e-05, + "loss": 3.5741, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406496357681626e-05, + "loss": 3.5812, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405657762930574e-05, + "loss": 3.5786, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404820806059896e-05, + "loss": 3.5762, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403982211308843e-05, + "loss": 3.5834, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403143616557791e-05, + "loss": 3.5898, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402305021806739e-05, + "loss": 3.5808, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401466427055687e-05, + "loss": 3.584, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400629470185008e-05, + "loss": 3.5804, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790875433956e-05, + "loss": 3.5736, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398952280682904e-05, + "loss": 3.571, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398113685931853e-05, + "loss": 3.5758, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3972767290611736e-05, + "loss": 3.5809, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3964381343101216e-05, + "loss": 3.5792, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3955995395590696e-05, + "loss": 3.5788, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947609448080176e-05, + "loss": 3.5781, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939239879373385e-05, + "loss": 3.5757, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3930853931862865e-05, + "loss": 3.575, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922467984352345e-05, + "loss": 3.5857, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914082036841825e-05, + "loss": 3.5757, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905712468135034e-05, + "loss": 3.5795, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897326520624514e-05, + "loss": 3.5549, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888940573113994e-05, + "loss": 3.5816, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388055462560348e-05, + "loss": 3.5808, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387218505689669e-05, + "loss": 3.5888, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386379910938617e-05, + "loss": 3.5785, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385541316187565e-05, + "loss": 3.5727, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384702721436513e-05, + "loss": 3.5836, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383864126685461e-05, + "loss": 3.595, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383025531934409e-05, + "loss": 3.5686, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.38218857506373e-05, + "loss": 3.5834, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381349980312678e-05, + "loss": 3.576, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380511385561626e-05, + "loss": 3.581, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379672790810574e-05, + "loss": 3.5804, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378835833939895e-05, + "loss": 3.5755, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3779972391888435e-05, + "loss": 3.5765, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771586444377915e-05, + "loss": 3.5834, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763200496867395e-05, + "loss": 3.5817, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8600692749023438, + "eval_runtime": 308.6681, + "eval_samples_per_second": 1236.25, + "eval_steps_per_second": 38.634, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3754814549356875e-05, + "loss": 3.5736, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3746428601846355e-05, + "loss": 3.5778, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3738042654335834e-05, + "loss": 3.572, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3729656706825314e-05, + "loss": 3.582, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721270759314794e-05, + "loss": 3.5848, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3712901190608003e-05, + "loss": 3.5769, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3704515243097483e-05, + "loss": 3.5749, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696129295586963e-05, + "loss": 3.5638, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368775972688017e-05, + "loss": 3.5711, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367937377936965e-05, + "loss": 3.5822, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367098783185913e-05, + "loss": 3.5741, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366260188434861e-05, + "loss": 3.5746, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365423231564183e-05, + "loss": 3.5891, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364584636813131e-05, + "loss": 3.5668, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363746042062079e-05, + "loss": 3.569, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362907447311027e-05, + "loss": 3.5618, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362070490440348e-05, + "loss": 3.5765, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361231895689296e-05, + "loss": 3.5675, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360393300938244e-05, + "loss": 3.5709, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359554706187192e-05, + "loss": 3.5791, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.3587177493165126e-05, + "loss": 3.582, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578791545654606e-05, + "loss": 3.5788, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3570405598144086e-05, + "loss": 3.5688, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3562019650633566e-05, + "loss": 3.5708, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355365008192678e-05, + "loss": 3.5813, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354526413441626e-05, + "loss": 3.5704, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353687818690574e-05, + "loss": 3.5596, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3528492239395215e-05, + "loss": 3.5721, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352012267068843e-05, + "loss": 3.5655, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351173672317791e-05, + "loss": 3.5612, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350335077566739e-05, + "loss": 3.5694, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.3494964828156864e-05, + "loss": 3.5717, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348659525945008e-05, + "loss": 3.5766, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347820931193956e-05, + "loss": 3.5784, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346982336442904e-05, + "loss": 3.5712, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346143741691852e-05, + "loss": 3.5727, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.3453067848211736e-05, + "loss": 3.5864, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.3444681900701216e-05, + "loss": 3.5591, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343629595319069e-05, + "loss": 3.5632, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342791000568017e-05, + "loss": 3.5681, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3419540436973385e-05, + "loss": 3.5539, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411154489462864e-05, + "loss": 3.5718, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340276854195234e-05, + "loss": 3.5732, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339438259444182e-05, + "loss": 3.5695, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.33859966469313e-05, + "loss": 3.568, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337761069942078e-05, + "loss": 3.5699, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369241130713993e-05, + "loss": 3.568, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336085518320347e-05, + "loss": 3.5741, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335246923569295e-05, + "loss": 3.5464, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334408328818243e-05, + "loss": 3.5636, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333571371947564e-05, + "loss": 3.581, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332732777196512e-05, + "loss": 3.575, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.33189418244546e-05, + "loss": 3.5713, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331055587694408e-05, + "loss": 3.558, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330218630823729e-05, + "loss": 3.5638, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329380036072677e-05, + "loss": 3.5558, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328541441321625e-05, + "loss": 3.5737, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327702846570573e-05, + "loss": 3.5578, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326864251819521e-05, + "loss": 3.5699, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.32602565706847e-05, + "loss": 3.5664, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325188700197791e-05, + "loss": 3.5665, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324350105446739e-05, + "loss": 3.56, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323511510695687e-05, + "loss": 3.5665, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322672915944635e-05, + "loss": 3.556, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218359590739556e-05, + "loss": 3.5547, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3209973643229036e-05, + "loss": 3.5748, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.3201587695718516e-05, + "loss": 3.5679, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3193201748207996e-05, + "loss": 3.5553, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184832179501205e-05, + "loss": 3.5519, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176446231990685e-05, + "loss": 3.5659, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.3168060284480165e-05, + "loss": 3.5661, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315967433696965e-05, + "loss": 3.5742, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315130476826286e-05, + "loss": 3.5618, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314291882075234e-05, + "loss": 3.5701, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313453287324182e-05, + "loss": 3.5774, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.31261469257313e-05, + "loss": 3.5587, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311776097822078e-05, + "loss": 3.5708, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310939140951399e-05, + "loss": 3.5695, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310100546200347e-05, + "loss": 3.5639, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309261951449295e-05, + "loss": 3.5657, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308424994578616e-05, + "loss": 3.5624, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307586399827564e-05, + "loss": 3.5707, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306747805076512e-05, + "loss": 3.5798, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3059092103254605e-05, + "loss": 3.5617, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3050706155744085e-05, + "loss": 3.5484, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3042336587037294e-05, + "loss": 3.5618, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3033950639526774e-05, + "loss": 3.5645, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.3025564692016254e-05, + "loss": 3.5671, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3017178744505734e-05, + "loss": 3.5682, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300880917579894e-05, + "loss": 3.5662, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300042322828842e-05, + "loss": 3.5703, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.29920372807779e-05, + "loss": 3.5527, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298365133326738e-05, + "loss": 3.5502, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297528176456059e-05, + "loss": 3.5569, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296689581705007e-05, + "loss": 3.5575, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295850986953956e-05, + "loss": 3.5731, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295012392202904e-05, + "loss": 3.5549, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294173797451852e-05, + "loss": 3.5557, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293336840581173e-05, + "loss": 3.5667, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292498245830121e-05, + "loss": 3.5578, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291659651079069e-05, + "loss": 3.5676, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290821056328017e-05, + "loss": 3.5673, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289982461576964e-05, + "loss": 3.5585, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289145504706286e-05, + "loss": 3.5584, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288306909955234e-05, + "loss": 3.5639, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287468315204182e-05, + "loss": 3.5535, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.28662972045313e-05, + "loss": 3.5566, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285792763582451e-05, + "loss": 3.5676, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284954168831399e-05, + "loss": 3.5603, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284115574080347e-05, + "loss": 3.5553, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.2832769793292946e-05, + "loss": 3.5543, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282440022458616e-05, + "loss": 3.5579, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281601427707564e-05, + "loss": 3.565, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.2807628329565115e-05, + "loss": 3.5631, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.2799242382054595e-05, + "loss": 3.5583, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279087281334781e-05, + "loss": 3.5684, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278248686583729e-05, + "loss": 3.568, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2774100918326764e-05, + "loss": 3.5644, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276571497081625e-05, + "loss": 3.5693, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275734540210946e-05, + "loss": 3.5635, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.2748959454598946e-05, + "loss": 3.5583, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274057350708842e-05, + "loss": 3.5527, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.27321875595779e-05, + "loss": 3.5603, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2723817990871115e-05, + "loss": 3.5572, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271543204336059e-05, + "loss": 3.5655, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270704609585007e-05, + "loss": 3.5648, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269866014833955e-05, + "loss": 3.5636, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.269027420082903e-05, + "loss": 3.5593, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268190463212224e-05, + "loss": 3.5559, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267351868461172e-05, + "loss": 3.5689, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.26651327371012e-05, + "loss": 3.5613, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2656746789590684e-05, + "loss": 3.5633, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264837722088389e-05, + "loss": 3.5356, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.263999127337337e-05, + "loss": 3.5621, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263160532586285e-05, + "loss": 3.5656, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262321937835233e-05, + "loss": 3.5728, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261484980964554e-05, + "loss": 3.5624, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260646386213502e-05, + "loss": 3.5565, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.25980779146245e-05, + "loss": 3.5632, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258969196711398e-05, + "loss": 3.579, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258130601960346e-05, + "loss": 3.5543, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257293645089667e-05, + "loss": 3.5667, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256455050338615e-05, + "loss": 3.5584, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255616455587564e-05, + "loss": 3.5638, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254777860836512e-05, + "loss": 3.5654, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253940903965833e-05, + "loss": 3.559, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253102309214781e-05, + "loss": 3.5565, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2522637144637287e-05, + "loss": 3.5698, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.2514251197126767e-05, + "loss": 3.5625, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.859924077987671, + "eval_runtime": 315.3374, + "eval_samples_per_second": 1210.104, + "eval_steps_per_second": 37.817, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2505881628419976e-05, + "loss": 3.5539, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497495680909456e-05, + "loss": 3.5603, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489109733398936e-05, + "loss": 3.5565, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480723785888416e-05, + "loss": 3.567, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472354217181625e-05, + "loss": 3.5647, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2463968269671105e-05, + "loss": 3.5652, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245558232216059e-05, + "loss": 3.5544, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244719637465007e-05, + "loss": 3.5455, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243882680594328e-05, + "loss": 3.5544, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243044085843276e-05, + "loss": 3.5675, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242205491092224e-05, + "loss": 3.5563, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241366896341172e-05, + "loss": 3.5561, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240529939470493e-05, + "loss": 3.5745, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239691344719441e-05, + "loss": 3.551, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238852749968389e-05, + "loss": 3.5517, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238014155217337e-05, + "loss": 3.5445, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237175560466285e-05, + "loss": 3.5581, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236338603595606e-05, + "loss": 3.5517, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355000088445545e-05, + "loss": 3.5537, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346614140935025e-05, + "loss": 3.5609, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338244572228234e-05, + "loss": 3.5724, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2329858624717714e-05, + "loss": 3.561, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321472677207194e-05, + "loss": 3.5536, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313086729696674e-05, + "loss": 3.5579, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304700782186154e-05, + "loss": 3.5586, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229633121347936e-05, + "loss": 3.5583, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228794526596884e-05, + "loss": 3.5427, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227955931845832e-05, + "loss": 3.5524, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.22711733709478e-05, + "loss": 3.5517, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226280380224101e-05, + "loss": 3.5456, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.22544178547305e-05, + "loss": 3.5479, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224603190721998e-05, + "loss": 3.5602, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223764595970946e-05, + "loss": 3.5534, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222927639100267e-05, + "loss": 3.5642, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222089044349215e-05, + "loss": 3.5552, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221250449598163e-05, + "loss": 3.5554, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220411854847111e-05, + "loss": 3.5646, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219573260096059e-05, + "loss": 3.5474, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187363032253797e-05, + "loss": 3.5503, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2178977084743277e-05, + "loss": 3.5488, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170591137232756e-05, + "loss": 3.5417, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162205189722236e-05, + "loss": 3.5544, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215383562101545e-05, + "loss": 3.5571, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214544967350493e-05, + "loss": 3.5504, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213706372599441e-05, + "loss": 3.5545, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212867777848389e-05, + "loss": 3.5515, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.21203082097771e-05, + "loss": 3.5559, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211192226226658e-05, + "loss": 3.5542, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210353631475606e-05, + "loss": 3.5327, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209515036724554e-05, + "loss": 3.5484, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208678079853875e-05, + "loss": 3.5621, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207839485102823e-05, + "loss": 3.5585, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207000890351771e-05, + "loss": 3.5552, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206162295600719e-05, + "loss": 3.5419, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2053253387300406e-05, + "loss": 3.5511, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2044867439789886e-05, + "loss": 3.5412, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036481492279366e-05, + "loss": 3.5537, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028095544768846e-05, + "loss": 3.5413, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201970959725832e-05, + "loss": 3.5548, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011340028551535e-05, + "loss": 3.5525, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2002954081041015e-05, + "loss": 3.5461, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994568133530495e-05, + "loss": 3.5422, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986198564823704e-05, + "loss": 3.5522, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1977812617313184e-05, + "loss": 3.5399, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969426669802664e-05, + "loss": 3.5428, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961040722292144e-05, + "loss": 3.5536, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952654774781624e-05, + "loss": 3.5529, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194428520607484e-05, + "loss": 3.5408, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193589925856432e-05, + "loss": 3.5359, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192751331105379e-05, + "loss": 3.5491, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191912736354327e-05, + "loss": 3.5496, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191075779483649e-05, + "loss": 3.5554, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190237184732596e-05, + "loss": 3.5454, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189398589981544e-05, + "loss": 3.5557, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188559995230492e-05, + "loss": 3.5571, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187723038359814e-05, + "loss": 3.5482, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186884443608761e-05, + "loss": 3.5532, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186045848857709e-05, + "loss": 3.5493, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185207254106658e-05, + "loss": 3.5524, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184370297235979e-05, + "loss": 3.5471, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835317024849266e-05, + "loss": 3.5479, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1826931077338746e-05, + "loss": 3.5511, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818545129828226e-05, + "loss": 3.5621, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810175561121435e-05, + "loss": 3.5452, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801789613610915e-05, + "loss": 3.5345, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793403666100395e-05, + "loss": 3.5461, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785017718589875e-05, + "loss": 3.5475, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776648149883084e-05, + "loss": 3.5507, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768262202372564e-05, + "loss": 3.5507, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1759876254862044e-05, + "loss": 3.5509, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175149030735153e-05, + "loss": 3.5519, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174310435984101e-05, + "loss": 3.5382, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173473479113422e-05, + "loss": 3.5346, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.17263488436237e-05, + "loss": 3.5386, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171796289611318e-05, + "loss": 3.5427, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170957694860266e-05, + "loss": 3.5594, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170120737989587e-05, + "loss": 3.5402, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169282143238535e-05, + "loss": 3.5354, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168443548487483e-05, + "loss": 3.5531, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167604953736431e-05, + "loss": 3.5441, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166767996865752e-05, + "loss": 3.5534, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1659294021147e-05, + "loss": 3.5499, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1650908073636485e-05, + "loss": 3.5396, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642522126125965e-05, + "loss": 3.545, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634152557419174e-05, + "loss": 3.5481, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625766609908654e-05, + "loss": 3.5343, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617380662398134e-05, + "loss": 3.543, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1608994714887614e-05, + "loss": 3.5501, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160062514618082e-05, + "loss": 3.5469, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.15922391986703e-05, + "loss": 3.5396, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158385325115978e-05, + "loss": 3.5424, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157546730364926e-05, + "loss": 3.5402, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156709773494247e-05, + "loss": 3.5467, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155871178743195e-05, + "loss": 3.5487, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155032583992144e-05, + "loss": 3.5401, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154193989241092e-05, + "loss": 3.5526, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153357032370413e-05, + "loss": 3.5536, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152518437619361e-05, + "loss": 3.5464, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151679842868309e-05, + "loss": 3.5502, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150841248117257e-05, + "loss": 3.5499, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500042912465776e-05, + "loss": 3.5414, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491656964955256e-05, + "loss": 3.5325, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483271017444736e-05, + "loss": 3.5466, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1474885069934216e-05, + "loss": 3.5433, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466515501227425e-05, + "loss": 3.5495, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458129553716905e-05, + "loss": 3.5447, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144974360620639e-05, + "loss": 3.5499, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144135765869587e-05, + "loss": 3.5399, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143298808998908e-05, + "loss": 3.5401, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142460214247856e-05, + "loss": 3.5552, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141621619496804e-05, + "loss": 3.5485, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140783024745752e-05, + "loss": 3.5477, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139946067875073e-05, + "loss": 3.5249, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139107473124021e-05, + "loss": 3.5434, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138268878372969e-05, + "loss": 3.5511, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137430283621917e-05, + "loss": 3.5553, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136593326751238e-05, + "loss": 3.5463, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135754732000186e-05, + "loss": 3.5391, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349161372491346e-05, + "loss": 3.5475, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1340775424980826e-05, + "loss": 3.5612, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332389477470306e-05, + "loss": 3.5428, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324019908763515e-05, + "loss": 3.5472, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315633961252995e-05, + "loss": 3.5437, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307248013742475e-05, + "loss": 3.5475, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1298862066231955e-05, + "loss": 3.5475, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290492497525164e-05, + "loss": 3.5449, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282106550014644e-05, + "loss": 3.5402, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273720602504124e-05, + "loss": 3.556, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265334654993604e-05, + "loss": 3.544, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8614697456359863, + "eval_runtime": 569.7375, + "eval_samples_per_second": 669.766, + "eval_steps_per_second": 20.931, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125696508628681e-05, + "loss": 3.5411, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.12485791387763e-05, + "loss": 3.5454, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124019319126578e-05, + "loss": 3.5396, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123180724375526e-05, + "loss": 3.5543, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122343767504847e-05, + "loss": 3.5497, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121505172753795e-05, + "loss": 3.5524, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120666578002743e-05, + "loss": 3.5381, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119829621132064e-05, + "loss": 3.5316, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118991026381012e-05, + "loss": 3.5334, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11815243162996e-05, + "loss": 3.5575, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117313836878908e-05, + "loss": 3.5393, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116475242127856e-05, + "loss": 3.5417, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156382852571766e-05, + "loss": 3.5517, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114799690506125e-05, + "loss": 3.545, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113961095755073e-05, + "loss": 3.5351, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113122501004021e-05, + "loss": 3.5347, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112283906252969e-05, + "loss": 3.5346, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.11144694938229e-05, + "loss": 3.5371, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110608354631238e-05, + "loss": 3.5392, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109769759880186e-05, + "loss": 3.5449, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108931165129134e-05, + "loss": 3.5589, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108094208258455e-05, + "loss": 3.5455, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107255613507403e-05, + "loss": 3.5399, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106417018756351e-05, + "loss": 3.5384, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105578424005299e-05, + "loss": 3.5446, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.10474146713462e-05, + "loss": 3.5374, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103902872383569e-05, + "loss": 3.5311, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103064277632517e-05, + "loss": 3.5351, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102225682881464e-05, + "loss": 3.5374, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1013887260107856e-05, + "loss": 3.5306, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005501312597336e-05, + "loss": 3.5319, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997115365086816e-05, + "loss": 3.5471, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098872941757629e-05, + "loss": 3.5392, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980359848869505e-05, + "loss": 3.544, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0971973901358985e-05, + "loss": 3.5475, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096358795384846e-05, + "loss": 3.5401, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095520200633794e-05, + "loss": 3.5453, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0946832437631154e-05, + "loss": 3.5343, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093844649012064e-05, + "loss": 3.5357, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930060542610114e-05, + "loss": 3.531, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921674595099593e-05, + "loss": 3.5305, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091330502639281e-05, + "loss": 3.5332, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090491907888229e-05, + "loss": 3.5464, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089653313137176e-05, + "loss": 3.5308, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088814718386124e-05, + "loss": 3.5429, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087977761515446e-05, + "loss": 3.5356, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087139166764393e-05, + "loss": 3.54, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086300572013341e-05, + "loss": 3.5408, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085461977262289e-05, + "loss": 3.5197, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084625020391611e-05, + "loss": 3.5306, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083786425640559e-05, + "loss": 3.5434, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082947830889507e-05, + "loss": 3.5461, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082109236138455e-05, + "loss": 3.5339, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081272279267776e-05, + "loss": 3.5303, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804336845167236e-05, + "loss": 3.5374, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0795950897656716e-05, + "loss": 3.5247, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787564950146196e-05, + "loss": 3.5393, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779179002635676e-05, + "loss": 3.5263, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0770809433928885e-05, + "loss": 3.5422, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762423486418365e-05, + "loss": 3.5363, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754037538907845e-05, + "loss": 3.5355, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074565159139733e-05, + "loss": 3.5248, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073728202269054e-05, + "loss": 3.5381, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072889607518002e-05, + "loss": 3.5241, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.07205101276695e-05, + "loss": 3.5301, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071212418015898e-05, + "loss": 3.5395, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070375461145219e-05, + "loss": 3.5406, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069536866394167e-05, + "loss": 3.5242, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068698271643115e-05, + "loss": 3.5247, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067859676892063e-05, + "loss": 3.5331, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067022720021384e-05, + "loss": 3.5328, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066184125270332e-05, + "loss": 3.5419, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.06534553051928e-05, + "loss": 3.5289, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645069357682285e-05, + "loss": 3.5437, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636683410171765e-05, + "loss": 3.5388, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628313841464975e-05, + "loss": 3.5346, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0619927893954454e-05, + "loss": 3.5386, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611541946443934e-05, + "loss": 3.5355, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603155998933414e-05, + "loss": 3.5397, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0594786430226623e-05, + "loss": 3.5305, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586400482716103e-05, + "loss": 3.5336, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578014535205583e-05, + "loss": 3.5347, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056962858769506e-05, + "loss": 3.5481, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056125901898827e-05, + "loss": 3.5295, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055287307147775e-05, + "loss": 3.5263, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054448712396724e-05, + "loss": 3.5255, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053610117645672e-05, + "loss": 3.5363, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052773160774993e-05, + "loss": 3.5324, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051934566023941e-05, + "loss": 3.5392, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0510959712728888e-05, + "loss": 3.5333, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502573765218368e-05, + "loss": 3.5364, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494204196511577e-05, + "loss": 3.5236, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485818249001057e-05, + "loss": 3.523, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477432301490537e-05, + "loss": 3.5195, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469046353980017e-05, + "loss": 3.5266, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.046067678527323e-05, + "loss": 3.5422, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045229083776271e-05, + "loss": 3.5313, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044390489025219e-05, + "loss": 3.5211, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043551894274167e-05, + "loss": 3.5341, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042714937403488e-05, + "loss": 3.5315, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418763426524362e-05, + "loss": 3.5377, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410377479013842e-05, + "loss": 3.5349, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0401991531503322e-05, + "loss": 3.5262, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039362196279653e-05, + "loss": 3.5306, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038523601528601e-05, + "loss": 3.5365, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037685006777549e-05, + "loss": 3.5176, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036846412026497e-05, + "loss": 3.5267, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360094551558183e-05, + "loss": 3.537, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351708604047663e-05, + "loss": 3.5264, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343322656537143e-05, + "loss": 3.5254, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334936709026623e-05, + "loss": 3.5302, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326550761516103e-05, + "loss": 3.5244, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318181192809315e-05, + "loss": 3.5344, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309795245298795e-05, + "loss": 3.5331, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301409297788275e-05, + "loss": 3.5249, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293023350277755e-05, + "loss": 3.5418, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284637402767235e-05, + "loss": 3.5392, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276267834060444e-05, + "loss": 3.531, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267881886549924e-05, + "loss": 3.5388, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259495939039408e-05, + "loss": 3.5337, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251109991528888e-05, + "loss": 3.5253, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242740422822097e-05, + "loss": 3.523, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234354475311577e-05, + "loss": 3.5262, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0225968527801057e-05, + "loss": 3.5302, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217582580290537e-05, + "loss": 3.5336, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209196632780013e-05, + "loss": 3.5271, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020082706407323e-05, + "loss": 3.5362, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019244111656271e-05, + "loss": 3.5274, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018405516905219e-05, + "loss": 3.5236, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175669221541662e-05, + "loss": 3.5377, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167299652834878e-05, + "loss": 3.5346, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015891370532436e-05, + "loss": 3.5323, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015052775781384e-05, + "loss": 3.5142, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142141810303314e-05, + "loss": 3.5275, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013377224159653e-05, + "loss": 3.5372, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012538629408601e-05, + "loss": 3.5389, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117000346575487e-05, + "loss": 3.529, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108614399064967e-05, + "loss": 3.5241, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100228451554447e-05, + "loss": 3.5372, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091858882847663e-05, + "loss": 3.5452, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083472935337136e-05, + "loss": 3.5278, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075086987826616e-05, + "loss": 3.5351, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.00667010403161e-05, + "loss": 3.5267, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058331471609315e-05, + "loss": 3.5321, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049945524098788e-05, + "loss": 3.5324, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041559576588268e-05, + "loss": 3.538, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033173629077748e-05, + "loss": 3.5246, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002480406037096e-05, + "loss": 3.5403, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001641811286044e-05, + "loss": 3.5321, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000803216534992e-05, + "loss": 3.5279, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8617100715637207, + "eval_runtime": 560.8408, + "eval_samples_per_second": 680.391, + "eval_steps_per_second": 21.263, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.99996462178394e-05, + "loss": 3.5315, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999126027032888e-05, + "loss": 3.5258, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998287432281836e-05, + "loss": 3.5382, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997450475411157e-05, + "loss": 3.5311, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966118806601053e-05, + "loss": 3.5397, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957732859090533e-05, + "loss": 3.5234, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949346911580013e-05, + "loss": 3.5166, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940960964069493e-05, + "loss": 3.5185, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932591395362702e-05, + "loss": 3.5431, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924205447852182e-05, + "loss": 3.5283, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915819500341662e-05, + "loss": 3.5222, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990743355283114e-05, + "loss": 3.5359, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899063984124354e-05, + "loss": 3.5291, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890678036613834e-05, + "loss": 3.5205, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882292089103314e-05, + "loss": 3.5231, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9873906141592794e-05, + "loss": 3.5172, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865536572886006e-05, + "loss": 3.5237, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857150625375486e-05, + "loss": 3.5227, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848764677864966e-05, + "loss": 3.5335, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840378730354446e-05, + "loss": 3.5438, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832009161647655e-05, + "loss": 3.5298, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823623214137135e-05, + "loss": 3.5226, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815237266626615e-05, + "loss": 3.528, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806851319116095e-05, + "loss": 3.5309, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798481750409308e-05, + "loss": 3.5206, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790095802898788e-05, + "loss": 3.5177, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781709855388268e-05, + "loss": 3.5182, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773323907877748e-05, + "loss": 3.5312, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9764954339170957e-05, + "loss": 3.5134, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975656839166044e-05, + "loss": 3.5155, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974818244414992e-05, + "loss": 3.5313, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.97397964966394e-05, + "loss": 3.5285, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.973142692793261e-05, + "loss": 3.5284, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972304098042209e-05, + "loss": 3.532, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971465503291157e-05, + "loss": 3.5247, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970626908540105e-05, + "loss": 3.5313, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969789951669426e-05, + "loss": 3.5194, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.968951356918374e-05, + "loss": 3.5226, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968112762167322e-05, + "loss": 3.5164, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.96727416741627e-05, + "loss": 3.5152, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966437210545591e-05, + "loss": 3.5212, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655986157945394e-05, + "loss": 3.5304, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647600210434874e-05, + "loss": 3.5176, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639214262924354e-05, + "loss": 3.5244, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630844694217563e-05, + "loss": 3.5228, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622458746707043e-05, + "loss": 3.5257, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614072799196523e-05, + "loss": 3.527, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605686851686003e-05, + "loss": 3.5112, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597317282979215e-05, + "loss": 3.5131, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588931335468695e-05, + "loss": 3.5284, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580545387958175e-05, + "loss": 3.5323, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572159440447655e-05, + "loss": 3.5165, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563789871740864e-05, + "loss": 3.5191, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555403924230347e-05, + "loss": 3.5231, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547017976719827e-05, + "loss": 3.5095, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538632029209307e-05, + "loss": 3.5227, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530262460502516e-05, + "loss": 3.5135, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521876512991996e-05, + "loss": 3.5241, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513490565481476e-05, + "loss": 3.5243, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505104617970956e-05, + "loss": 3.5217, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949673504926417e-05, + "loss": 3.507, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948834910175365e-05, + "loss": 3.5278, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.947996315424313e-05, + "loss": 3.5084, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.947157720673261e-05, + "loss": 3.5182, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463207638025818e-05, + "loss": 3.5243, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.94548216905153e-05, + "loss": 3.5281, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944643574300478e-05, + "loss": 3.5094, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943804979549426e-05, + "loss": 3.5129, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942968022678747e-05, + "loss": 3.5126, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942129427927695e-05, + "loss": 3.524, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941290833176643e-05, + "loss": 3.5217, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940452238425591e-05, + "loss": 3.5169, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396152815549122e-05, + "loss": 3.5273, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387766868038602e-05, + "loss": 3.5317, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379380920528082e-05, + "loss": 3.5182, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9370994973017562e-05, + "loss": 3.5211, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936262540431077e-05, + "loss": 3.5215, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354239456800255e-05, + "loss": 3.527, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345853509289735e-05, + "loss": 3.5131, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337467561779215e-05, + "loss": 3.5208, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329097993072424e-05, + "loss": 3.5178, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320712045561904e-05, + "loss": 3.5349, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312326098051384e-05, + "loss": 3.5182, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930394015054086e-05, + "loss": 3.5072, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295570581834076e-05, + "loss": 3.5114, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287184634323556e-05, + "loss": 3.5186, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278798686813036e-05, + "loss": 3.5233, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.927041273930251e-05, + "loss": 3.5236, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262026791791993e-05, + "loss": 3.5179, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925365722308521e-05, + "loss": 3.5216, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924527127557469e-05, + "loss": 3.5109, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923688532806416e-05, + "loss": 3.5078, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.922849938055364e-05, + "loss": 3.5046, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220129811846857e-05, + "loss": 3.5178, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211743864336334e-05, + "loss": 3.5257, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203357916825814e-05, + "loss": 3.5166, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194971969315294e-05, + "loss": 3.51, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918660240060851e-05, + "loss": 3.5159, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178216453097983e-05, + "loss": 3.5197, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169830505587463e-05, + "loss": 3.5213, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161444558076946e-05, + "loss": 3.5213, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153074989370162e-05, + "loss": 3.5154, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144689041859635e-05, + "loss": 3.5118, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136303094349115e-05, + "loss": 3.5248, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127917146838595e-05, + "loss": 3.5055, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119547578131808e-05, + "loss": 3.5113, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111161630621288e-05, + "loss": 3.524, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102775683110768e-05, + "loss": 3.515, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094389735600248e-05, + "loss": 3.51, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086020166893457e-05, + "loss": 3.517, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077634219382937e-05, + "loss": 3.5127, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069248271872417e-05, + "loss": 3.5176, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.90608623243619e-05, + "loss": 3.5162, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905249275565511e-05, + "loss": 3.5119, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904410680814459e-05, + "loss": 3.5251, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903572086063407e-05, + "loss": 3.5256, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902733491312355e-05, + "loss": 3.5171, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901896534441676e-05, + "loss": 3.5267, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901057939690624e-05, + "loss": 3.5207, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900219344939572e-05, + "loss": 3.5119, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.89938075018852e-05, + "loss": 3.5059, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898543793317841e-05, + "loss": 3.513, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897705198566789e-05, + "loss": 3.516, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896866603815737e-05, + "loss": 3.5187, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896028009064685e-05, + "loss": 3.5158, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951910521940063e-05, + "loss": 3.5201, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943524574429543e-05, + "loss": 3.5173, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935138626919023e-05, + "loss": 3.5083, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926752679408503e-05, + "loss": 3.523, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918383110701715e-05, + "loss": 3.5205, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8909997163191195e-05, + "loss": 3.5156, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901611215680675e-05, + "loss": 3.502, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893225268170155e-05, + "loss": 3.5112, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8884855699463364e-05, + "loss": 3.5243, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876469751952844e-05, + "loss": 3.5267, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868083804442324e-05, + "loss": 3.511, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859697856931804e-05, + "loss": 3.5128, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851311909421287e-05, + "loss": 3.5276, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8842942340714496e-05, + "loss": 3.5255, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834556393203976e-05, + "loss": 3.5187, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826170445693456e-05, + "loss": 3.5173, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817784498182936e-05, + "loss": 3.5141, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880941492947615e-05, + "loss": 3.517, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.880102898196563e-05, + "loss": 3.5148, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.879264303445511e-05, + "loss": 3.5263, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878425708694459e-05, + "loss": 3.513, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775887518237798e-05, + "loss": 3.5274, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767501570727278e-05, + "loss": 3.5183, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759115623216758e-05, + "loss": 3.5119, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.863530158996582, + "eval_runtime": 315.1455, + "eval_samples_per_second": 1210.841, + "eval_steps_per_second": 37.84, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.875072967570624e-05, + "loss": 3.5177, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874236010699945e-05, + "loss": 3.5138, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873397415948893e-05, + "loss": 3.523, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872558821197841e-05, + "loss": 3.5179, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871720226446789e-05, + "loss": 3.5265, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708832695761102e-05, + "loss": 3.5097, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700446748250582e-05, + "loss": 3.5051, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692060800740062e-05, + "loss": 3.5011, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683674853229542e-05, + "loss": 3.5302, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867530528452275e-05, + "loss": 3.5163, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866691933701223e-05, + "loss": 3.5072, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865853338950171e-05, + "loss": 3.5228, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650163820794924e-05, + "loss": 3.5128, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641777873284404e-05, + "loss": 3.508, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633391925773884e-05, + "loss": 3.5058, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625005978263364e-05, + "loss": 3.5092, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616620030752843e-05, + "loss": 3.5074, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608234083242323e-05, + "loss": 3.5066, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599848135731803e-05, + "loss": 3.5216, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591478567025016e-05, + "loss": 3.5294, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583092619514496e-05, + "loss": 3.516, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574706672003976e-05, + "loss": 3.5092, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566320724493456e-05, + "loss": 3.5135, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557951155786665e-05, + "loss": 3.518, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549565208276148e-05, + "loss": 3.5105, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541179260765628e-05, + "loss": 3.5048, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532793313255108e-05, + "loss": 3.5063, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524407365744588e-05, + "loss": 3.5177, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516037797037797e-05, + "loss": 3.4957, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507651849527277e-05, + "loss": 3.5023, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499265902016757e-05, + "loss": 3.5165, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849087995450624e-05, + "loss": 3.5147, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.848251038579945e-05, + "loss": 3.5186, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847412443828893e-05, + "loss": 3.5122, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.846573849077841e-05, + "loss": 3.5098, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457352543267886e-05, + "loss": 3.5178, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8448982974561102e-05, + "loss": 3.5066, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440597027050582e-05, + "loss": 3.5112, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432211079540062e-05, + "loss": 3.5001, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423825132029535e-05, + "loss": 3.5045, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841545556332275e-05, + "loss": 3.5078, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840706961581223e-05, + "loss": 3.5153, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.839868366830171e-05, + "loss": 3.5109, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390297720791187e-05, + "loss": 3.5078, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381928152084403e-05, + "loss": 3.5107, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373542204573883e-05, + "loss": 3.5097, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365156257063356e-05, + "loss": 3.5118, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835677030955284e-05, + "loss": 3.4987, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348400740846056e-05, + "loss": 3.4988, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340014793335535e-05, + "loss": 3.5131, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833162884582501e-05, + "loss": 3.5187, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832324289831449e-05, + "loss": 3.5065, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314873329607704e-05, + "loss": 3.5055, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306487382097184e-05, + "loss": 3.5073, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829810143458666e-05, + "loss": 3.4997, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.828971548707614e-05, + "loss": 3.5062, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281345918369357e-05, + "loss": 3.4998, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827295997085883e-05, + "loss": 3.5093, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826457402334831e-05, + "loss": 3.5112, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256188075837793e-05, + "loss": 3.5076, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824781850713101e-05, + "loss": 3.4936, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239432559620482e-05, + "loss": 3.5146, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231046612109962e-05, + "loss": 3.4933, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222660664599442e-05, + "loss": 3.5052, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214291095892658e-05, + "loss": 3.5122, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205905148382135e-05, + "loss": 3.5111, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197519200871615e-05, + "loss": 3.4966, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189133253361095e-05, + "loss": 3.4993, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180763684654304e-05, + "loss": 3.4985, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172377737143784e-05, + "loss": 3.5075, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8163991789633264e-05, + "loss": 3.5073, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155605842122747e-05, + "loss": 3.5052, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147236273415956e-05, + "loss": 3.5139, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138850325905436e-05, + "loss": 3.5149, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130464378394916e-05, + "loss": 3.5113, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122078430884396e-05, + "loss": 3.5016, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811370886217761e-05, + "loss": 3.5138, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810532291466709e-05, + "loss": 3.5114, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809693696715657e-05, + "loss": 3.496, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808855101964605e-05, + "loss": 3.516, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080181450939257e-05, + "loss": 3.5039, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071795503428737e-05, + "loss": 3.5244, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063409555918217e-05, + "loss": 3.5064, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055023608407697e-05, + "loss": 3.4886, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804663766089718e-05, + "loss": 3.5037, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803826809219039e-05, + "loss": 3.5014, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802988214467987e-05, + "loss": 3.5127, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802149619716935e-05, + "loss": 3.5056, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801311024965883e-05, + "loss": 3.5069, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004740680952042e-05, + "loss": 3.5084, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996354733441522e-05, + "loss": 3.4977, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7987968785931002e-05, + "loss": 3.4949, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979582838420482e-05, + "loss": 3.4917, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797121326971369e-05, + "loss": 3.5023, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796282732220317e-05, + "loss": 3.5131, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795444137469265e-05, + "loss": 3.5037, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946055427182134e-05, + "loss": 3.4964, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937685858475343e-05, + "loss": 3.5024, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929299910964823e-05, + "loss": 3.5043, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920913963454303e-05, + "loss": 3.5092, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912528015943783e-05, + "loss": 3.506, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904158447236996e-05, + "loss": 3.501, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895772499726476e-05, + "loss": 3.5022, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887386552215956e-05, + "loss": 3.5107, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879000604705436e-05, + "loss": 3.4905, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870631035998645e-05, + "loss": 3.5029, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862245088488125e-05, + "loss": 3.5085, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853859140977605e-05, + "loss": 3.4993, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845473193467088e-05, + "loss": 3.4966, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837103624760297e-05, + "loss": 3.5021, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828717677249777e-05, + "loss": 3.5012, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820331729739257e-05, + "loss": 3.5028, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811945782228737e-05, + "loss": 3.505, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780357621352195e-05, + "loss": 3.4972, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779519026601143e-05, + "loss": 3.5124, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778680431850091e-05, + "loss": 3.5107, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777841837099039e-05, + "loss": 3.5046, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.77700488022836e-05, + "loss": 3.5098, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776166285477308e-05, + "loss": 3.5088, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753276907262558e-05, + "loss": 3.4983, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774489095975204e-05, + "loss": 3.4951, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773652139104525e-05, + "loss": 3.4974, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772813544353473e-05, + "loss": 3.5049, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771974949602421e-05, + "loss": 3.5082, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771136354851369e-05, + "loss": 3.5035, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7702993979806903e-05, + "loss": 3.5075, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694608032296383e-05, + "loss": 3.4998, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686222084785863e-05, + "loss": 3.5016, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677836137275343e-05, + "loss": 3.5022, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669466568568552e-05, + "loss": 3.5112, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661080621058032e-05, + "loss": 3.5035, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652694673547512e-05, + "loss": 3.4914, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644308726036995e-05, + "loss": 3.4942, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635939157330204e-05, + "loss": 3.5107, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627553209819684e-05, + "loss": 3.5115, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619167262309164e-05, + "loss": 3.5049, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610781314798644e-05, + "loss": 3.498, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602411746091857e-05, + "loss": 3.5148, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594025798581337e-05, + "loss": 3.51, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585639851070817e-05, + "loss": 3.5075, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577253903560297e-05, + "loss": 3.5052, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568884334853506e-05, + "loss": 3.5018, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560498387342986e-05, + "loss": 3.5035, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552112439832466e-05, + "loss": 3.4993, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754372649232195e-05, + "loss": 3.5154, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535356923615158e-05, + "loss": 3.5008, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7526970976104638e-05, + "loss": 3.5117, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518585028594118e-05, + "loss": 3.5055, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510199081083598e-05, + "loss": 3.4993, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8644309043884277, + "eval_runtime": 305.2151, + "eval_samples_per_second": 1250.236, + "eval_steps_per_second": 39.071, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501813133573078e-05, + "loss": 3.5052, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493427186062558e-05, + "loss": 3.5029, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485041238552034e-05, + "loss": 3.5082, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476655291041514e-05, + "loss": 3.5042, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746828572233473e-05, + "loss": 3.5148, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.745989977482421e-05, + "loss": 3.4983, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451513827313687e-05, + "loss": 3.4939, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443127879803167e-05, + "loss": 3.4834, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434758311096383e-05, + "loss": 3.5161, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426372363585856e-05, + "loss": 3.5035, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417986416075336e-05, + "loss": 3.4913, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409600468564816e-05, + "loss": 3.5136, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740123089985803e-05, + "loss": 3.4961, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392844952347508e-05, + "loss": 3.5021, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384459004836988e-05, + "loss": 3.4915, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376073057326468e-05, + "loss": 3.4955, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367703488619677e-05, + "loss": 3.4978, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359317541109157e-05, + "loss": 3.4922, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735093159359864e-05, + "loss": 3.508, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734254564608812e-05, + "loss": 3.5134, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733417607738133e-05, + "loss": 3.5012, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732579012987081e-05, + "loss": 3.4966, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731740418236029e-05, + "loss": 3.5018, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730901823484977e-05, + "loss": 3.5032, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300648666142982e-05, + "loss": 3.4943, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292262718632462e-05, + "loss": 3.4953, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283876771121942e-05, + "loss": 3.4893, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727549082361142e-05, + "loss": 3.5058, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726712125490463e-05, + "loss": 3.4807, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725873530739411e-05, + "loss": 3.4933, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250349359883594e-05, + "loss": 3.5014, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7241963412373074e-05, + "loss": 3.5044, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233593843666283e-05, + "loss": 3.5038, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225207896155763e-05, + "loss": 3.5004, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216821948645243e-05, + "loss": 3.4949, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208436001134723e-05, + "loss": 3.5061, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200066432427935e-05, + "loss": 3.4966, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191680484917415e-05, + "loss": 3.4972, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183294537406895e-05, + "loss": 3.4852, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174908589896375e-05, + "loss": 3.4941, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166539021189584e-05, + "loss": 3.49, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158153073679064e-05, + "loss": 3.5048, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149767126168544e-05, + "loss": 3.4956, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141381178658028e-05, + "loss": 3.4958, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133011609951237e-05, + "loss": 3.5013, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124625662440717e-05, + "loss": 3.4977, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116239714930197e-05, + "loss": 3.497, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107853767419677e-05, + "loss": 3.4862, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709948419871289e-05, + "loss": 3.4819, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709109825120237e-05, + "loss": 3.505, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708271230369185e-05, + "loss": 3.5034, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707432635618133e-05, + "loss": 3.4955, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7065956787474538e-05, + "loss": 3.4932, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057570839964018e-05, + "loss": 3.491, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049184892453498e-05, + "loss": 3.4884, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704079894494298e-05, + "loss": 3.4934, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703241299743246e-05, + "loss": 3.4886, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702404342872567e-05, + "loss": 3.4975, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701565748121515e-05, + "loss": 3.4969, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700727153370463e-05, + "loss": 3.4912, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699888558619411e-05, + "loss": 3.4827, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990516017487323e-05, + "loss": 3.5023, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982130069976803e-05, + "loss": 3.4833, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973744122466283e-05, + "loss": 3.4915, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965358174955763e-05, + "loss": 3.4949, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956988606248972e-05, + "loss": 3.5015, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694860265873845e-05, + "loss": 3.4814, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940216711227935e-05, + "loss": 3.4885, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931830763717415e-05, + "loss": 3.4797, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923461195010624e-05, + "loss": 3.4963, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915075247500104e-05, + "loss": 3.4962, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906689299989584e-05, + "loss": 3.4948, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898303352479064e-05, + "loss": 3.4992, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6889933783772276e-05, + "loss": 3.4991, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881547836261756e-05, + "loss": 3.502, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873161888751236e-05, + "loss": 3.4873, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864775941240716e-05, + "loss": 3.4993, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856406372533925e-05, + "loss": 3.5015, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848020425023405e-05, + "loss": 3.4845, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683963447751289e-05, + "loss": 3.4977, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683124853000237e-05, + "loss": 3.487, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822878961295578e-05, + "loss": 3.5131, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814493013785058e-05, + "loss": 3.4945, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806107066274538e-05, + "loss": 3.4762, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797721118764018e-05, + "loss": 3.489, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.678935155005723e-05, + "loss": 3.4919, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.678096560254671e-05, + "loss": 3.498, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677257965503619e-05, + "loss": 3.4969, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676419370752567e-05, + "loss": 3.492, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.675582413881888e-05, + "loss": 3.4945, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674743819130836e-05, + "loss": 3.4884, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739052243797842e-05, + "loss": 3.4836, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730666296287322e-05, + "loss": 3.475, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672229672758053e-05, + "loss": 3.4903, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671391078007001e-05, + "loss": 3.4985, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670552483255949e-05, + "loss": 3.492, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669713888504897e-05, + "loss": 3.483, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688769316342184e-05, + "loss": 3.49, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680383368831664e-05, + "loss": 3.4882, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6671997421321144e-05, + "loss": 3.4994, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663611473810624e-05, + "loss": 3.4921, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655241905103833e-05, + "loss": 3.4929, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646855957593313e-05, + "loss": 3.4858, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638470010082796e-05, + "loss": 3.4996, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630084062572276e-05, + "loss": 3.4772, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621714493865485e-05, + "loss": 3.4913, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613328546354965e-05, + "loss": 3.4893, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6604942598844445e-05, + "loss": 3.4914, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596556651333925e-05, + "loss": 3.4834, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588187082627137e-05, + "loss": 3.4924, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579801135116617e-05, + "loss": 3.4861, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571415187606097e-05, + "loss": 3.4895, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563029240095577e-05, + "loss": 3.4921, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554659671388786e-05, + "loss": 3.4887, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546273723878266e-05, + "loss": 3.4959, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653788777636775e-05, + "loss": 3.4985, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.652950182885723e-05, + "loss": 3.4947, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.652113226015044e-05, + "loss": 3.4958, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.651274631263992e-05, + "loss": 3.4931, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.65043603651294e-05, + "loss": 3.4817, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.649597441761888e-05, + "loss": 3.4841, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648760484891209e-05, + "loss": 3.4879, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647921890140157e-05, + "loss": 3.4893, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.647083295389105e-05, + "loss": 3.4988, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646244700638053e-05, + "loss": 3.4886, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.645407743767374e-05, + "loss": 3.4945, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644569149016322e-05, + "loss": 3.4862, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.64373055426527e-05, + "loss": 3.488, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6428919595142177e-05, + "loss": 3.4898, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420550026435392e-05, + "loss": 3.5016, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412164078924872e-05, + "loss": 3.4893, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403778131414352e-05, + "loss": 3.4836, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639539218390383e-05, + "loss": 3.4762, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387022615197045e-05, + "loss": 3.4953, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378636667686525e-05, + "loss": 3.4987, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370250720176005e-05, + "loss": 3.4953, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361864772665478e-05, + "loss": 3.4874, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353495203958694e-05, + "loss": 3.5027, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345109256448174e-05, + "loss": 3.4934, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633672330893765e-05, + "loss": 3.4966, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632833736142713e-05, + "loss": 3.4913, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6319967792720346e-05, + "loss": 3.4914, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311581845209826e-05, + "loss": 3.4899, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303195897699303e-05, + "loss": 3.4831, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294809950188783e-05, + "loss": 3.5002, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286440381482e-05, + "loss": 3.4921, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627805443397148e-05, + "loss": 3.4944, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626966848646095e-05, + "loss": 3.4942, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626128253895043e-05, + "loss": 3.4836, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.864975929260254, + "eval_runtime": 311.4498, + "eval_samples_per_second": 1225.209, + "eval_steps_per_second": 38.289, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.625289659143991e-05, + "loss": 3.4921, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624451064392939e-05, + "loss": 3.4894, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236124696418875e-05, + "loss": 3.4929, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227738748908355e-05, + "loss": 3.4912, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219369180201564e-05, + "loss": 3.5036, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6210983232691044e-05, + "loss": 3.487, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202597285180524e-05, + "loss": 3.4792, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194211337670004e-05, + "loss": 3.4726, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6185841768963216e-05, + "loss": 3.4994, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177455821452696e-05, + "loss": 3.4955, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169069873942176e-05, + "loss": 3.4728, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160683926431656e-05, + "loss": 3.4995, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152314357724865e-05, + "loss": 3.4872, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6143928410214345e-05, + "loss": 3.4867, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.613554246270383e-05, + "loss": 3.481, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.612715651519331e-05, + "loss": 3.4843, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6118786946486518e-05, + "loss": 3.4848, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110400998975997e-05, + "loss": 3.4777, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102015051465477e-05, + "loss": 3.4949, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093629103954957e-05, + "loss": 3.4995, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.608525953524817e-05, + "loss": 3.491, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.607687358773765e-05, + "loss": 3.4856, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.606848764022713e-05, + "loss": 3.4857, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.606010169271661e-05, + "loss": 3.4947, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.605173212400982e-05, + "loss": 3.4805, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.60433461764993e-05, + "loss": 3.484, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6034960228988782e-05, + "loss": 3.4798, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026574281478262e-05, + "loss": 3.491, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601820471277147e-05, + "loss": 3.4711, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.600981876526095e-05, + "loss": 3.4806, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.600143281775043e-05, + "loss": 3.4908, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599304687023991e-05, + "loss": 3.4887, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984677301533124e-05, + "loss": 3.4908, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976291354022603e-05, + "loss": 3.489, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5967905406512083e-05, + "loss": 3.4852, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959519459001563e-05, + "loss": 3.4932, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951149890294772e-05, + "loss": 3.487, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5942763942784252e-05, + "loss": 3.4783, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934377995273736e-05, + "loss": 3.4766, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5925992047763216e-05, + "loss": 3.4812, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917622479056425e-05, + "loss": 3.4786, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909236531545905e-05, + "loss": 3.4933, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5900850584035385e-05, + "loss": 3.4817, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892464636524865e-05, + "loss": 3.4823, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884095067818077e-05, + "loss": 3.4923, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5875709120307557e-05, + "loss": 3.4828, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867323172797037e-05, + "loss": 3.4902, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5858937225286517e-05, + "loss": 3.4721, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850567656579726e-05, + "loss": 3.4641, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842181709069206e-05, + "loss": 3.4939, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583379576155869e-05, + "loss": 3.4894, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.582540981404817e-05, + "loss": 3.4887, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.581704024534138e-05, + "loss": 3.4793, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580865429783086e-05, + "loss": 3.4791, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.580026835032034e-05, + "loss": 3.4757, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.579188240280982e-05, + "loss": 3.4808, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.578351283410303e-05, + "loss": 3.4777, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.577512688659251e-05, + "loss": 3.4776, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.576674093908199e-05, + "loss": 3.4912, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.575835499157147e-05, + "loss": 3.4775, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.574998542286468e-05, + "loss": 3.4686, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.574159947535416e-05, + "loss": 3.4933, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733213527843643e-05, + "loss": 3.4706, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724827580333123e-05, + "loss": 3.4734, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716458011626332e-05, + "loss": 3.4869, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708072064115812e-05, + "loss": 3.4877, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5699686116605292e-05, + "loss": 3.4698, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691300169094772e-05, + "loss": 3.4782, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5682930600387985e-05, + "loss": 3.4657, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674544652877464e-05, + "loss": 3.4879, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666158705366944e-05, + "loss": 3.4805, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5657772757856424e-05, + "loss": 3.4819, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649403189149633e-05, + "loss": 3.4849, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641017241639113e-05, + "loss": 3.4876, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632631294128597e-05, + "loss": 3.4936, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624245346618077e-05, + "loss": 3.4747, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5615875777911286e-05, + "loss": 3.4877, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607489830400766e-05, + "loss": 3.4886, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599103882890246e-05, + "loss": 3.4692, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590717935379726e-05, + "loss": 3.4856, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582348366672938e-05, + "loss": 3.478, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5573962419162418e-05, + "loss": 3.4939, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565576471651898e-05, + "loss": 3.4823, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557190524141378e-05, + "loss": 3.4662, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548820955434587e-05, + "loss": 3.476, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540435007924067e-05, + "loss": 3.4782, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532049060413547e-05, + "loss": 3.4865, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552366311290303e-05, + "loss": 3.4812, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.551529354419624e-05, + "loss": 3.4756, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.550690759668572e-05, + "loss": 3.4814, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.54985216491752e-05, + "loss": 3.4802, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490135701664676e-05, + "loss": 3.4737, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481766132957892e-05, + "loss": 3.4636, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473380185447372e-05, + "loss": 3.4777, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5464994237936852e-05, + "loss": 3.4871, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456608290426325e-05, + "loss": 3.4842, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.544823872171954e-05, + "loss": 3.4651, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.543985277420902e-05, + "loss": 3.4811, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431466826698497e-05, + "loss": 3.4728, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423080879187977e-05, + "loss": 3.4863, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414711310481193e-05, + "loss": 3.4793, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406325362970673e-05, + "loss": 3.4813, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5397939415460146e-05, + "loss": 3.4736, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538955346794963e-05, + "loss": 3.4893, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381183899242846e-05, + "loss": 3.4646, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5372797951732325e-05, + "loss": 3.4798, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.53644120042218e-05, + "loss": 3.4735, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535602605671128e-05, + "loss": 3.479, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347656488004494e-05, + "loss": 3.4704, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.533927054049397e-05, + "loss": 3.4836, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.533088459298345e-05, + "loss": 3.4702, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.532249864547293e-05, + "loss": 3.4776, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314129076766147e-05, + "loss": 3.479, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.530574312925562e-05, + "loss": 3.4767, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.52973571817451e-05, + "loss": 3.4843, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5288971234234583e-05, + "loss": 3.4854, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.52806016655278e-05, + "loss": 3.4809, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272215718017272e-05, + "loss": 3.4856, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5263829770506752e-05, + "loss": 3.4802, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255443822996232e-05, + "loss": 3.4732, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247074254289445e-05, + "loss": 3.4707, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238688306778925e-05, + "loss": 3.4747, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230302359268405e-05, + "loss": 3.478, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5221916411757885e-05, + "loss": 3.4833, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213546843051094e-05, + "loss": 3.4755, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205160895540574e-05, + "loss": 3.4833, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196774948030054e-05, + "loss": 3.474, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188389000519537e-05, + "loss": 3.4748, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180019431812746e-05, + "loss": 3.4768, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171633484302226e-05, + "loss": 3.4897, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163247536791706e-05, + "loss": 3.4798, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5154861589281186e-05, + "loss": 3.4705, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.51464920205744e-05, + "loss": 3.4625, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.513810607306388e-05, + "loss": 3.482, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.512972012555336e-05, + "loss": 3.4867, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121334178042838e-05, + "loss": 3.4855, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5112964609336047e-05, + "loss": 3.4763, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104578661825527e-05, + "loss": 3.4902, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096192714315007e-05, + "loss": 3.4801, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.508780676680449e-05, + "loss": 3.4818, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.50794371980977e-05, + "loss": 3.4788, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.507105125058718e-05, + "loss": 3.4776, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.506266530307666e-05, + "loss": 3.4814, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.505427935556614e-05, + "loss": 3.4697, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5045909786859352e-05, + "loss": 3.487, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037523839348832e-05, + "loss": 3.4838, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029137891838312e-05, + "loss": 3.4785, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020751944327792e-05, + "loss": 3.4775, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012382375621e-05, + "loss": 3.4751, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8681185245513916, + "eval_runtime": 308.8019, + "eval_samples_per_second": 1235.715, + "eval_steps_per_second": 38.617, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500399642811048e-05, + "loss": 3.478, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499561048059996e-05, + "loss": 3.4778, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987224533089444e-05, + "loss": 3.4829, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978838585578924e-05, + "loss": 3.4777, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970469016872133e-05, + "loss": 3.4897, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962083069361613e-05, + "loss": 3.4788, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953697121851093e-05, + "loss": 3.4643, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945311174340573e-05, + "loss": 3.4644, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936941605633786e-05, + "loss": 3.4835, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928555658123266e-05, + "loss": 3.4825, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920169710612746e-05, + "loss": 3.4651, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911783763102226e-05, + "loss": 3.4835, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903414194395435e-05, + "loss": 3.476, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895028246884915e-05, + "loss": 3.4729, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886642299374398e-05, + "loss": 3.4691, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878256351863878e-05, + "loss": 3.4712, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869886783157087e-05, + "loss": 3.4695, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861500835646567e-05, + "loss": 3.4677, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853114888136047e-05, + "loss": 3.4843, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844728940625527e-05, + "loss": 3.4862, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483635937191874e-05, + "loss": 3.481, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482797342440822e-05, + "loss": 3.4758, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.48195874768977e-05, + "loss": 3.4725, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481120152938718e-05, + "loss": 3.4809, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480283196068039e-05, + "loss": 3.4716, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.479444601316987e-05, + "loss": 3.4731, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.478606006565935e-05, + "loss": 3.4658, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477767411814883e-05, + "loss": 3.4758, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476930454944204e-05, + "loss": 3.4651, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476091860193152e-05, + "loss": 3.4653, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752532654421e-05, + "loss": 3.4806, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474414670691048e-05, + "loss": 3.4734, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735777138203693e-05, + "loss": 3.4836, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727391190693173e-05, + "loss": 3.4773, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719005243182653e-05, + "loss": 3.4701, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710619295672133e-05, + "loss": 3.4801, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702249726965342e-05, + "loss": 3.4782, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693863779454822e-05, + "loss": 3.465, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685477831944305e-05, + "loss": 3.4594, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677091884433785e-05, + "loss": 3.465, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668722315726994e-05, + "loss": 3.4671, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660336368216474e-05, + "loss": 3.4832, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651950420705954e-05, + "loss": 3.4702, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464356447319543e-05, + "loss": 3.471, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635194904488647e-05, + "loss": 3.4782, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626808956978127e-05, + "loss": 3.4729, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618423009467607e-05, + "loss": 3.4755, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610037061957083e-05, + "loss": 3.4608, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601667493250296e-05, + "loss": 3.4489, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593281545739776e-05, + "loss": 3.483, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584895598229256e-05, + "loss": 3.4805, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576509650718736e-05, + "loss": 3.4758, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568140082011948e-05, + "loss": 3.469, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559754134501428e-05, + "loss": 3.4649, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551368186990905e-05, + "loss": 3.4606, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542982239480385e-05, + "loss": 3.4678, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.45346126707736e-05, + "loss": 3.4677, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452622672326308e-05, + "loss": 3.4662, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517840775752557e-05, + "loss": 3.4774, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509454828242037e-05, + "loss": 3.4705, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.450108525953525e-05, + "loss": 3.4585, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.449269931202473e-05, + "loss": 3.4822, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448431336451421e-05, + "loss": 3.459, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447592741700369e-05, + "loss": 3.4576, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467557848296902e-05, + "loss": 3.4769, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459171900786378e-05, + "loss": 3.4779, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450785953275858e-05, + "loss": 3.4545, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442400005765338e-05, + "loss": 3.4692, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434030437058554e-05, + "loss": 3.4532, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442564448954803e-05, + "loss": 3.4739, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441725854203751e-05, + "loss": 3.4739, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440887259452699e-05, + "loss": 3.4643, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400503025820203e-05, + "loss": 3.4746, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392117078309683e-05, + "loss": 3.4734, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383731130799163e-05, + "loss": 3.4858, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375345183288643e-05, + "loss": 3.4613, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366975614581852e-05, + "loss": 3.4748, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358589667071332e-05, + "loss": 3.476, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350203719560812e-05, + "loss": 3.4578, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341817772050292e-05, + "loss": 3.4755, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333448203343504e-05, + "loss": 3.469, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325062255832984e-05, + "loss": 3.4793, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316676308322464e-05, + "loss": 3.4739, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308290360811944e-05, + "loss": 3.4564, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299920792105153e-05, + "loss": 3.4596, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291534844594637e-05, + "loss": 3.4637, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283148897084117e-05, + "loss": 3.4797, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274762949573597e-05, + "loss": 3.4663, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266393380866806e-05, + "loss": 3.4651, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258007433356286e-05, + "loss": 3.4693, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249621485845766e-05, + "loss": 3.4693, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241235538335246e-05, + "loss": 3.4608, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232865969628458e-05, + "loss": 3.4498, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224480022117938e-05, + "loss": 3.467, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216094074607418e-05, + "loss": 3.4735, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207708127096898e-05, + "loss": 3.4733, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199338558390107e-05, + "loss": 3.4521, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.419095261087959e-05, + "loss": 3.4673, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.418256666336907e-05, + "loss": 3.4631, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417418071585855e-05, + "loss": 3.472, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416581114715176e-05, + "loss": 3.4712, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415742519964124e-05, + "loss": 3.4694, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414903925213072e-05, + "loss": 3.4633, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.41406533046202e-05, + "loss": 3.4719, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.413228373591341e-05, + "loss": 3.4537, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412389778840289e-05, + "loss": 3.4684, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411551184089237e-05, + "loss": 3.4595, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410712589338185e-05, + "loss": 3.4722, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409875632467506e-05, + "loss": 3.4537, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409037037716454e-05, + "loss": 3.4737, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4081984429654024e-05, + "loss": 3.4624, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073598482143504e-05, + "loss": 3.4664, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065228913436713e-05, + "loss": 3.4667, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056842965926193e-05, + "loss": 3.4668, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048457018415673e-05, + "loss": 3.4712, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040071070905153e-05, + "loss": 3.4767, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031701502198365e-05, + "loss": 3.4709, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023315554687845e-05, + "loss": 3.4726, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014929607177325e-05, + "loss": 3.4685, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006543659666802e-05, + "loss": 3.4621, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998174090960014e-05, + "loss": 3.4543, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989788143449494e-05, + "loss": 3.4687, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981402195938978e-05, + "loss": 3.4643, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973016248428454e-05, + "loss": 3.4713, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964646679721667e-05, + "loss": 3.4641, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956260732211147e-05, + "loss": 3.4677, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947874784700627e-05, + "loss": 3.4656, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939488837190107e-05, + "loss": 3.4642, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393111926848332e-05, + "loss": 3.4616, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.39227333209728e-05, + "loss": 3.4746, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914347373462276e-05, + "loss": 3.4686, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905961425951755e-05, + "loss": 3.4612, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897591857244968e-05, + "loss": 3.4496, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889205909734448e-05, + "loss": 3.4711, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880819962223928e-05, + "loss": 3.4733, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872434014713408e-05, + "loss": 3.4718, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386406444600662e-05, + "loss": 3.4671, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.38556784984961e-05, + "loss": 3.4769, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847292550985577e-05, + "loss": 3.4672, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838922982278793e-05, + "loss": 3.4731, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830537034768273e-05, + "loss": 3.4648, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382215108725775e-05, + "loss": 3.468, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381376513974723e-05, + "loss": 3.4665, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380539557104044e-05, + "loss": 3.4608, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379700962352992e-05, + "loss": 3.4741, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.37886236760194e-05, + "loss": 3.474, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378023772850888e-05, + "loss": 3.4678, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771868159802094e-05, + "loss": 3.4645, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763482212291574e-05, + "loss": 3.467, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.868180274963379, + "eval_runtime": 304.6167, + "eval_samples_per_second": 1252.692, + "eval_steps_per_second": 39.148, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.375509626478105e-05, + "loss": 3.4699, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374671031727053e-05, + "loss": 3.4663, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738324369760014e-05, + "loss": 3.4696, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3729938422249494e-05, + "loss": 3.4639, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721568853542703e-05, + "loss": 3.4797, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713182906032183e-05, + "loss": 3.4674, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3704796958521663e-05, + "loss": 3.4542, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696411011011143e-05, + "loss": 3.4525, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3688041442304355e-05, + "loss": 3.4714, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679655494793835e-05, + "loss": 3.4696, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671269547283315e-05, + "loss": 3.4585, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3662883599772795e-05, + "loss": 3.4694, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654530409869737e-05, + "loss": 3.4661, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646144462359217e-05, + "loss": 3.4608, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3637758514848697e-05, + "loss": 3.4572, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629372567338177e-05, + "loss": 3.4546, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3620986619827657e-05, + "loss": 3.4576, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612600672317137e-05, + "loss": 3.4578, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604214724806616e-05, + "loss": 3.4691, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3595828777296096e-05, + "loss": 3.4772, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.358745920858931e-05, + "loss": 3.4722, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357907326107879e-05, + "loss": 3.4656, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.357068731356827e-05, + "loss": 3.4637, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356230136605775e-05, + "loss": 3.4667, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3553931797350958e-05, + "loss": 3.4601, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545545849840438e-05, + "loss": 3.464, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537159902329918e-05, + "loss": 3.4485, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.35287739548194e-05, + "loss": 3.4643, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.352040438611261e-05, + "loss": 3.4558, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351201843860209e-05, + "loss": 3.4537, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350363249109157e-05, + "loss": 3.4614, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.349526292238478e-05, + "loss": 3.4674, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486876974874263e-05, + "loss": 3.4721, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478491027363743e-05, + "loss": 3.4635, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470105079853223e-05, + "loss": 3.4566, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.346173551114643e-05, + "loss": 3.4685, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345334956363591e-05, + "loss": 3.4688, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.344496361612539e-05, + "loss": 3.4529, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343657766861487e-05, + "loss": 3.4513, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428208099908084e-05, + "loss": 3.4538, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419822152397564e-05, + "loss": 3.4599, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411436204887044e-05, + "loss": 3.4683, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403050257376524e-05, + "loss": 3.4612, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394680688669733e-05, + "loss": 3.4548, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386294741159216e-05, + "loss": 3.469, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3377908793648696e-05, + "loss": 3.4598, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369522846138173e-05, + "loss": 3.4682, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361153277431385e-05, + "loss": 3.447, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3352767329920865e-05, + "loss": 3.4336, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344381382410345e-05, + "loss": 3.4759, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3335995434899825e-05, + "loss": 3.4663, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327625866193038e-05, + "loss": 3.4635, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319239918682518e-05, + "loss": 3.4612, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3310853971171998e-05, + "loss": 3.4575, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302468023661474e-05, + "loss": 3.4485, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294098454954687e-05, + "loss": 3.4531, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328571250744417e-05, + "loss": 3.4553, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277326559933646e-05, + "loss": 3.4561, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3268940612423126e-05, + "loss": 3.4627, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.326057104371634e-05, + "loss": 3.4573, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.325218509620582e-05, + "loss": 3.4498, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.32437991486953e-05, + "loss": 3.4667, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.323541320118478e-05, + "loss": 3.4496, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322704363247799e-05, + "loss": 3.4466, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321865768496747e-05, + "loss": 3.4651, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3210271737456948e-05, + "loss": 3.4671, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3201885789946428e-05, + "loss": 3.4443, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319351622123964e-05, + "loss": 3.457, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318513027372912e-05, + "loss": 3.4434, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.31767443262186e-05, + "loss": 3.4594, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316835837870808e-05, + "loss": 3.4605, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3159988810001293e-05, + "loss": 3.4587, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315160286249077e-05, + "loss": 3.4614, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314321691498025e-05, + "loss": 3.4639, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134830967469732e-05, + "loss": 3.4689, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126461398762945e-05, + "loss": 3.4483, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.311807545125242e-05, + "loss": 3.4677, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.31096895037419e-05, + "loss": 3.4637, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.310130355623138e-05, + "loss": 3.4459, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3092933987524594e-05, + "loss": 3.4665, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084548040014074e-05, + "loss": 3.4551, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076162092503554e-05, + "loss": 3.4693, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067776144993034e-05, + "loss": 3.461, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059406576286243e-05, + "loss": 3.448, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051020628775723e-05, + "loss": 3.4463, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3042634681265203e-05, + "loss": 3.4529, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034248733754686e-05, + "loss": 3.4681, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025879165047895e-05, + "loss": 3.4548, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017493217537375e-05, + "loss": 3.455, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009107270026855e-05, + "loss": 3.4572, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000721322516335e-05, + "loss": 3.4573, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992351753809548e-05, + "loss": 3.4512, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2983965806299028e-05, + "loss": 3.4352, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975579858788507e-05, + "loss": 3.455, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967193911277987e-05, + "loss": 3.4621, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958824342571197e-05, + "loss": 3.4615, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950438395060677e-05, + "loss": 3.4435, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942052447550156e-05, + "loss": 3.4526, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.293366650003964e-05, + "loss": 3.4544, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292529693133285e-05, + "loss": 3.4567, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291691098382233e-05, + "loss": 3.4619, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.290852503631181e-05, + "loss": 3.4532, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.290013908880129e-05, + "loss": 3.4568, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.28917695200945e-05, + "loss": 3.4612, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288338357258398e-05, + "loss": 3.4445, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287499762507346e-05, + "loss": 3.4552, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286661167756294e-05, + "loss": 3.4464, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285824210885615e-05, + "loss": 3.4611, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284985616134563e-05, + "loss": 3.4438, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.284147021383511e-05, + "loss": 3.4608, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833084266324593e-05, + "loss": 3.4516, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824714697617803e-05, + "loss": 3.456, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816328750107283e-05, + "loss": 3.4544, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2807942802596762e-05, + "loss": 3.4575, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799556855086242e-05, + "loss": 3.4543, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2791187286379455e-05, + "loss": 3.4676, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2782801338868935e-05, + "loss": 3.4593, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774415391358415e-05, + "loss": 3.4617, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766029443847895e-05, + "loss": 3.4529, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757659875141104e-05, + "loss": 3.4576, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749273927630584e-05, + "loss": 3.4423, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2740887980120064e-05, + "loss": 3.4523, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732502032609544e-05, + "loss": 3.4543, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724132463902756e-05, + "loss": 3.4579, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715746516392236e-05, + "loss": 3.4559, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707360568881716e-05, + "loss": 3.4535, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2698974621371193e-05, + "loss": 3.4535, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.269060505266441e-05, + "loss": 3.4547, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.268221910515389e-05, + "loss": 3.4534, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267383315764337e-05, + "loss": 3.4599, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665447210132845e-05, + "loss": 3.458, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657077641426058e-05, + "loss": 3.4519, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648691693915538e-05, + "loss": 3.4358, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640305746405017e-05, + "loss": 3.4617, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2631919798894497e-05, + "loss": 3.4593, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262355023018771e-05, + "loss": 3.4611, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261516428267719e-05, + "loss": 3.4544, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606778335166666e-05, + "loss": 3.4633, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598392387656146e-05, + "loss": 3.4564, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590022818949362e-05, + "loss": 3.4693, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581636871438842e-05, + "loss": 3.4518, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257325092392832e-05, + "loss": 3.4536, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.25648649764178e-05, + "loss": 3.4525, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255649540771101e-05, + "loss": 3.4539, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548109460200488e-05, + "loss": 3.4641, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.253972351268997e-05, + "loss": 3.4561, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.253133756517945e-05, + "loss": 3.4627, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2522967996472664e-05, + "loss": 3.4487, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251458204896214e-05, + "loss": 3.4583, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8708362579345703, + "eval_runtime": 302.3905, + "eval_samples_per_second": 1261.915, + "eval_steps_per_second": 39.436, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.250619610145162e-05, + "loss": 3.4577, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.24978101539411e-05, + "loss": 3.4561, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489440585234316e-05, + "loss": 3.455, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481054637723792e-05, + "loss": 3.4547, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472668690213272e-05, + "loss": 3.4666, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464282742702752e-05, + "loss": 3.4526, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.245591317399596e-05, + "loss": 3.4463, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.244752722648544e-05, + "loss": 3.4399, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2439141278974925e-05, + "loss": 3.4596, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430755331464405e-05, + "loss": 3.4568, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422385762757614e-05, + "loss": 3.4497, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2413999815247094e-05, + "loss": 3.4572, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405630246540306e-05, + "loss": 3.4558, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397244299029786e-05, + "loss": 3.4513, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2388858351519266e-05, + "loss": 3.4454, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2380472404008746e-05, + "loss": 3.4445, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2372086456498226e-05, + "loss": 3.4462, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2363700508987706e-05, + "loss": 3.4492, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355314561477186e-05, + "loss": 3.4552, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2346928613966666e-05, + "loss": 3.4646, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233855904525988e-05, + "loss": 3.4612, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.233017309774936e-05, + "loss": 3.4551, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.232178715023884e-05, + "loss": 3.4504, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231340120272832e-05, + "loss": 3.4543, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305031634021527e-05, + "loss": 3.4507, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296645686511007e-05, + "loss": 3.4527, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288259739000487e-05, + "loss": 3.4356, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.227987379148997e-05, + "loss": 3.4568, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.227150422278318e-05, + "loss": 3.4455, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.226311827527266e-05, + "loss": 3.4409, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.225473232776214e-05, + "loss": 3.4489, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246346380251616e-05, + "loss": 3.4571, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2237976811544832e-05, + "loss": 3.4543, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229590864034312e-05, + "loss": 3.4543, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221204916523792e-05, + "loss": 3.4451, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221281896901327e-05, + "loss": 3.4585, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220444940030648e-05, + "loss": 3.4558, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.219606345279596e-05, + "loss": 3.4431, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.218767750528544e-05, + "loss": 3.4418, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179307936578653e-05, + "loss": 3.4403, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2170921989068133e-05, + "loss": 3.4486, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162536041557613e-05, + "loss": 3.4562, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215415009404709e-05, + "loss": 3.4491, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2145780525340302e-05, + "loss": 3.4467, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2137394577829786e-05, + "loss": 3.4533, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2129008630319266e-05, + "loss": 3.4456, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2120622682808742e-05, + "loss": 3.4571, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112253114101955e-05, + "loss": 3.441, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2103867166591435e-05, + "loss": 3.4187, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209548121908091e-05, + "loss": 3.4634, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2087095271570395e-05, + "loss": 3.4551, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2078725702863607e-05, + "loss": 3.4537, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070339755353087e-05, + "loss": 3.4469, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2061953807842564e-05, + "loss": 3.4439, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053567860332044e-05, + "loss": 3.4378, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045198291625256e-05, + "loss": 3.4434, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203681234411474e-05, + "loss": 3.4472, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028426396604216e-05, + "loss": 3.4403, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2020040449093696e-05, + "loss": 3.4525, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.201167088038691e-05, + "loss": 3.4487, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003284932876385e-05, + "loss": 3.4366, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1994898985365865e-05, + "loss": 3.4554, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198651303785535e-05, + "loss": 3.437, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197814346914856e-05, + "loss": 3.4378, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1969757521638037e-05, + "loss": 3.453, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961371574127517e-05, + "loss": 3.4531, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1952985626616997e-05, + "loss": 3.4335, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.194461605791021e-05, + "loss": 3.4439, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193623011039969e-05, + "loss": 3.4332, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.192784416288917e-05, + "loss": 3.4508, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.191945821537865e-05, + "loss": 3.4521, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.191108864667186e-05, + "loss": 3.4481, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.190270269916134e-05, + "loss": 3.4477, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.189431675165082e-05, + "loss": 3.4499, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885930804140302e-05, + "loss": 3.4587, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.187756123543351e-05, + "loss": 3.4419, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.186917528792299e-05, + "loss": 3.4553, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.186078934041247e-05, + "loss": 3.4509, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.185240339290195e-05, + "loss": 3.4354, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844033824195163e-05, + "loss": 3.4514, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835647876684643e-05, + "loss": 3.4487, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827261929174123e-05, + "loss": 3.4544, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1818875981663603e-05, + "loss": 3.4528, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810506412956812e-05, + "loss": 3.4358, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1802120465446292e-05, + "loss": 3.4369, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1793734517935772e-05, + "loss": 3.4441, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1785348570425256e-05, + "loss": 3.4507, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1776979001718465e-05, + "loss": 3.444, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768593054207945e-05, + "loss": 3.445, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760207106697425e-05, + "loss": 3.4482, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1751821159186905e-05, + "loss": 3.4476, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1743451590480117e-05, + "loss": 3.4389, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1735065642969597e-05, + "loss": 3.4243, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1726679695459077e-05, + "loss": 3.4439, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1718293747948557e-05, + "loss": 3.4478, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1709924179241766e-05, + "loss": 3.452, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701538231731246e-05, + "loss": 3.433, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1693152284220726e-05, + "loss": 3.4432, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168476633671021e-05, + "loss": 3.4437, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167639676800342e-05, + "loss": 3.4433, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.16680108204929e-05, + "loss": 3.4512, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.165962487298238e-05, + "loss": 3.445, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651238925471858e-05, + "loss": 3.4451, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.164286935676507e-05, + "loss": 3.4476, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163448340925455e-05, + "loss": 3.4317, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162609746174403e-05, + "loss": 3.4454, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161771151423351e-05, + "loss": 3.4317, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160934194552672e-05, + "loss": 3.4545, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.16009559980162e-05, + "loss": 3.4315, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.159257005050568e-05, + "loss": 3.4467, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584184102995163e-05, + "loss": 3.4398, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1575814534288372e-05, + "loss": 3.4414, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567428586777852e-05, + "loss": 3.4443, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559042639267332e-05, + "loss": 3.4474, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.155065669175681e-05, + "loss": 3.4432, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542287123050024e-05, + "loss": 3.4556, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1533901175539504e-05, + "loss": 3.4434, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525515228028984e-05, + "loss": 3.4574, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151712928051846e-05, + "loss": 3.4423, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1508759711811673e-05, + "loss": 3.4439, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1500373764301153e-05, + "loss": 3.4372, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1491987816790633e-05, + "loss": 3.4395, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483601869280113e-05, + "loss": 3.4395, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475232300573326e-05, + "loss": 3.4499, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1466846353062806e-05, + "loss": 3.4421, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458460405552282e-05, + "loss": 3.4453, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1450074458041762e-05, + "loss": 3.4423, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1441704889334978e-05, + "loss": 3.4439, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1433318941824458e-05, + "loss": 3.4456, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1424932994313935e-05, + "loss": 3.4437, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416547046803415e-05, + "loss": 3.4438, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408177478096627e-05, + "loss": 3.4426, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1399791530586107e-05, + "loss": 3.4282, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391405583075587e-05, + "loss": 3.4507, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1383019635565067e-05, + "loss": 3.4476, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137465006685828e-05, + "loss": 3.4524, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1366264119347756e-05, + "loss": 3.4424, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1357878171837236e-05, + "loss": 3.4509, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349492224326716e-05, + "loss": 3.4458, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.134112265561993e-05, + "loss": 3.4558, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.133273670810941e-05, + "loss": 3.44, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.132435076059889e-05, + "loss": 3.4413, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1315964813088368e-05, + "loss": 3.4437, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.130759524438158e-05, + "loss": 3.4433, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1299209296871057e-05, + "loss": 3.4469, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.129082334936054e-05, + "loss": 3.4473, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.128243740185002e-05, + "loss": 3.4503, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127406783314323e-05, + "loss": 3.4371, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126568188563271e-05, + "loss": 3.451, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.871824026107788, + "eval_runtime": 302.2646, + "eval_samples_per_second": 1262.44, + "eval_steps_per_second": 39.452, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.125729593812219e-05, + "loss": 3.4498, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124890999061167e-05, + "loss": 3.4471, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.124052404310115e-05, + "loss": 3.4419, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232138095590633e-05, + "loss": 3.4433, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223768526883842e-05, + "loss": 3.4549, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215382579373322e-05, + "loss": 3.4455, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1206996631862802e-05, + "loss": 3.4374, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198610684352282e-05, + "loss": 3.4344, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190241115645494e-05, + "loss": 3.4421, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181855168134974e-05, + "loss": 3.4484, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173469220624454e-05, + "loss": 3.4359, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165083273113934e-05, + "loss": 3.4433, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156730083210876e-05, + "loss": 3.4503, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148344135700356e-05, + "loss": 3.4369, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139958188189836e-05, + "loss": 3.4362, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131572240679316e-05, + "loss": 3.4317, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123186293168796e-05, + "loss": 3.4365, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114800345658276e-05, + "loss": 3.4371, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106414398147756e-05, + "loss": 3.44, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098028450637236e-05, + "loss": 3.4575, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089658881930448e-05, + "loss": 3.4518, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081272934419928e-05, + "loss": 3.4447, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072886986909408e-05, + "loss": 3.4369, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064501039398884e-05, + "loss": 3.4413, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056131470692097e-05, + "loss": 3.4405, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047745523181577e-05, + "loss": 3.4422, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039359575671057e-05, + "loss": 3.4244, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1030973628160537e-05, + "loss": 3.4471, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102260405945375e-05, + "loss": 3.4349, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101421811194323e-05, + "loss": 3.4333, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100583216443271e-05, + "loss": 3.4327, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997446216922186e-05, + "loss": 3.4484, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.09890766482154e-05, + "loss": 3.4456, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.098069070070488e-05, + "loss": 3.4434, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972304753194358e-05, + "loss": 3.4321, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963918805683838e-05, + "loss": 3.4427, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095554923697705e-05, + "loss": 3.4488, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094716328946653e-05, + "loss": 3.4338, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093877734195601e-05, + "loss": 3.429, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930407773249223e-05, + "loss": 3.4295, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922021825738703e-05, + "loss": 3.4367, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913635878228183e-05, + "loss": 3.4433, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090524993071766e-05, + "loss": 3.4419, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896880362010872e-05, + "loss": 3.4345, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888494414500352e-05, + "loss": 3.4403, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880108466989832e-05, + "loss": 3.4364, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871722519479312e-05, + "loss": 3.4442, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863352950772524e-05, + "loss": 3.4328, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854967003262004e-05, + "loss": 3.4077, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084658105575148e-05, + "loss": 3.4469, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838195108240964e-05, + "loss": 3.4428, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829825539534177e-05, + "loss": 3.4451, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821439592023653e-05, + "loss": 3.436, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813053644513133e-05, + "loss": 3.4312, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804667697002613e-05, + "loss": 3.4307, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796298128295826e-05, + "loss": 3.4332, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787912180785306e-05, + "loss": 3.438, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779526233274786e-05, + "loss": 3.4259, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771140285764266e-05, + "loss": 3.4411, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762770717057478e-05, + "loss": 3.4392, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754384769546955e-05, + "loss": 3.4246, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0745998822036435e-05, + "loss": 3.4439, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737612874525918e-05, + "loss": 3.4284, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729243305819127e-05, + "loss": 3.4257, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720857358308607e-05, + "loss": 3.4387, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712471410798087e-05, + "loss": 3.444, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704085463287567e-05, + "loss": 3.4211, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.069571589458078e-05, + "loss": 3.4333, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.068732994707026e-05, + "loss": 3.4194, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.067894399955974e-05, + "loss": 3.4365, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.067055805204922e-05, + "loss": 3.4404, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662188483342428e-05, + "loss": 3.4367, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653802535831908e-05, + "loss": 3.4357, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645416588321388e-05, + "loss": 3.4383, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.063703064081087e-05, + "loss": 3.4511, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062866107210408e-05, + "loss": 3.4262, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.062027512459356e-05, + "loss": 3.4453, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.061188917708304e-05, + "loss": 3.4399, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060350322957252e-05, + "loss": 3.425, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595133660865733e-05, + "loss": 3.4422, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586747713355213e-05, + "loss": 3.4385, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578361765844693e-05, + "loss": 3.4405, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569975818334173e-05, + "loss": 3.4445, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561606249627382e-05, + "loss": 3.4216, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553220302116862e-05, + "loss": 3.4269, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544834354606342e-05, + "loss": 3.432, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536448407095825e-05, + "loss": 3.4423, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528078838389034e-05, + "loss": 3.4303, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519692890878514e-05, + "loss": 3.438, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511306943367994e-05, + "loss": 3.44, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502920995857474e-05, + "loss": 3.4317, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494551427150687e-05, + "loss": 3.431, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0486165479640167e-05, + "loss": 3.4157, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477779532129647e-05, + "loss": 3.4326, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469393584619127e-05, + "loss": 3.4354, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461024015912336e-05, + "loss": 3.4415, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452638068401816e-05, + "loss": 3.4209, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444252120891296e-05, + "loss": 3.4297, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0435866173380775e-05, + "loss": 3.4328, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427496604673988e-05, + "loss": 3.4345, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419110657163468e-05, + "loss": 3.4349, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410724709652948e-05, + "loss": 3.437, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402338762142428e-05, + "loss": 3.4352, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393969193435637e-05, + "loss": 3.4308, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038558324592512e-05, + "loss": 3.4263, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.03771972984146e-05, + "loss": 3.4305, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036881135090408e-05, + "loss": 3.423, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.036044178219729e-05, + "loss": 3.4433, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.035205583468677e-05, + "loss": 3.4215, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034366988717625e-05, + "loss": 3.4343, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033528393966573e-05, + "loss": 3.4279, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032691437095894e-05, + "loss": 3.4381, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031852842344842e-05, + "loss": 3.432, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.03101424759379e-05, + "loss": 3.4361, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030177290723111e-05, + "loss": 3.4306, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029338695972059e-05, + "loss": 3.4477, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285001012210074e-05, + "loss": 3.4322, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276615064699554e-05, + "loss": 3.4454, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026822911718903e-05, + "loss": 3.4294, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0259859548482243e-05, + "loss": 3.4327, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0251473600971723e-05, + "loss": 3.4273, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0243087653461203e-05, + "loss": 3.4324, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234718084754415e-05, + "loss": 3.4259, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226332137243895e-05, + "loss": 3.4387, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217946189733375e-05, + "loss": 3.4276, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209560242222852e-05, + "loss": 3.4353, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201190673516064e-05, + "loss": 3.4365, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192804726005544e-05, + "loss": 3.4293, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184418778495024e-05, + "loss": 3.4359, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176032830984504e-05, + "loss": 3.4354, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167663262277717e-05, + "loss": 3.4286, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159277314767197e-05, + "loss": 3.4347, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150891367256673e-05, + "loss": 3.4129, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142505419746157e-05, + "loss": 3.439, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013413585103937e-05, + "loss": 3.437, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.012574990352885e-05, + "loss": 3.4407, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117363956018326e-05, + "loss": 3.4306, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108978008507805e-05, + "loss": 3.439, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100608439801018e-05, + "loss": 3.4358, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092222492290498e-05, + "loss": 3.4451, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083836544779978e-05, + "loss": 3.4275, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075450597269458e-05, + "loss": 3.4336, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.006708102856267e-05, + "loss": 3.4322, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058695081052147e-05, + "loss": 3.4376, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050309133541627e-05, + "loss": 3.4351, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.004192318603111e-05, + "loss": 3.4353, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033553617324323e-05, + "loss": 3.4426, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.00251676698138e-05, + "loss": 3.4241, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.001678172230328e-05, + "loss": 3.4441, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.873692512512207, + "eval_runtime": 311.7476, + "eval_samples_per_second": 1224.038, + "eval_steps_per_second": 38.252, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.000839577479276e-05, + "loss": 3.4337, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 2.000000982728224e-05, + "loss": 3.4337, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.999162387977172e-05, + "loss": 3.4343, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.99832379322612e-05, + "loss": 3.4342, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997486836355441e-05, + "loss": 3.4449, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996648241604389e-05, + "loss": 3.4344, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995809646853337e-05, + "loss": 3.4247, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.994971052102285e-05, + "loss": 3.423, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.994134095231606e-05, + "loss": 3.4319, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932955004805544e-05, + "loss": 3.44, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924569057295024e-05, + "loss": 3.4281, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916183109784504e-05, + "loss": 3.4321, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907829919881442e-05, + "loss": 3.4381, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899443972370922e-05, + "loss": 3.4263, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9891058024860405e-05, + "loss": 3.426, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882672077349885e-05, + "loss": 3.4212, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874286129839365e-05, + "loss": 3.4283, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865900182328845e-05, + "loss": 3.4243, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857514234818325e-05, + "loss": 3.4329, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.98491282873078e-05, + "loss": 3.4441, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840758718601014e-05, + "loss": 3.4418, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832372771090497e-05, + "loss": 3.4328, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823986823579977e-05, + "loss": 3.4284, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815600876069454e-05, + "loss": 3.4312, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807231307362666e-05, + "loss": 3.4278, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798845359852146e-05, + "loss": 3.4301, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790459412341626e-05, + "loss": 3.4141, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9782073464831106e-05, + "loss": 3.4355, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.977370389612432e-05, + "loss": 3.4267, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.97653179486138e-05, + "loss": 3.4183, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756932001103275e-05, + "loss": 3.4224, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748546053592755e-05, + "loss": 3.4385, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9740176484885968e-05, + "loss": 3.435, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973179053737545e-05, + "loss": 3.4314, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9723404589864928e-05, + "loss": 3.4246, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9715018642354408e-05, + "loss": 3.426, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.970664907364762e-05, + "loss": 3.4407, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698263126137097e-05, + "loss": 3.4228, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.968987717862658e-05, + "loss": 3.4169, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.968149123111606e-05, + "loss": 3.4216, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673121662409273e-05, + "loss": 3.4246, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966473571489875e-05, + "loss": 3.4332, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965634976738823e-05, + "loss": 3.4263, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.964796381987771e-05, + "loss": 3.4293, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.963959425117092e-05, + "loss": 3.4263, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.96312083036604e-05, + "loss": 3.4252, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.962282235614988e-05, + "loss": 3.4394, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961443640863936e-05, + "loss": 3.4199, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960606683993257e-05, + "loss": 3.4017, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959768089242205e-05, + "loss": 3.4357, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589294944911534e-05, + "loss": 3.4293, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580925376204746e-05, + "loss": 3.4367, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572539428694223e-05, + "loss": 3.4268, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564153481183703e-05, + "loss": 3.4194, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555767533673183e-05, + "loss": 3.4178, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9547397964966395e-05, + "loss": 3.4199, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9539012017455875e-05, + "loss": 3.4303, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530626069945355e-05, + "loss": 3.4117, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522240122434835e-05, + "loss": 3.4342, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513870553728044e-05, + "loss": 3.4265, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505484606217524e-05, + "loss": 3.415, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9497098658707004e-05, + "loss": 3.4309, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488712711196484e-05, + "loss": 3.4168, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480343142489697e-05, + "loss": 3.4149, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471957194979176e-05, + "loss": 3.4254, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463571247468656e-05, + "loss": 3.4336, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455185299958136e-05, + "loss": 3.408, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446815731251345e-05, + "loss": 3.4275, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943842978374083e-05, + "loss": 3.4102, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.943004383623031e-05, + "loss": 3.4265, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.942165788871979e-05, + "loss": 3.4304, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413288320012998e-05, + "loss": 3.4209, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404902372502478e-05, + "loss": 3.4301, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396516424991958e-05, + "loss": 3.4231, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9388130477481438e-05, + "loss": 3.4424, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.937976090877465e-05, + "loss": 3.4151, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.937137496126413e-05, + "loss": 3.436, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.936298901375361e-05, + "loss": 3.4279, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.935460306624309e-05, + "loss": 3.4184, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.93462334975363e-05, + "loss": 3.4281, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337863928829515e-05, + "loss": 3.4264, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932947798131899e-05, + "loss": 3.4303, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.932109203380847e-05, + "loss": 3.433, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931270608629795e-05, + "loss": 3.4116, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930432013878743e-05, + "loss": 3.4163, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929593419127691e-05, + "loss": 3.4209, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.928754824376639e-05, + "loss": 3.4332, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279162296255875e-05, + "loss": 3.4186, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270792727549084e-05, + "loss": 3.4255, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262406780038564e-05, + "loss": 3.4307, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9254020832528044e-05, + "loss": 3.4199, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924563488501752e-05, + "loss": 3.4184, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9237265316310736e-05, + "loss": 3.4034, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228879368800216e-05, + "loss": 3.4199, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220493421289696e-05, + "loss": 3.4248, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9212123852582905e-05, + "loss": 3.4314, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9203737905072385e-05, + "loss": 3.4144, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9195351957561865e-05, + "loss": 3.4197, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186966010051345e-05, + "loss": 3.4206, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178580062540825e-05, + "loss": 3.4244, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9170210493834037e-05, + "loss": 3.4263, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161824546323517e-05, + "loss": 3.4258, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153438598812994e-05, + "loss": 3.4259, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9145069030106206e-05, + "loss": 3.4192, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913668308259569e-05, + "loss": 3.4182, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912829713508517e-05, + "loss": 3.4152, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119911187574646e-05, + "loss": 3.4137, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.911154161886786e-05, + "loss": 3.4338, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.910315567135734e-05, + "loss": 3.411, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909476972384682e-05, + "loss": 3.4222, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.90863837763363e-05, + "loss": 3.413, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.907799782882578e-05, + "loss": 3.4273, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.906962826011899e-05, + "loss": 3.4217, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061242312608468e-05, + "loss": 3.4233, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052856365097948e-05, + "loss": 3.4195, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.904448679639116e-05, + "loss": 3.4344, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036100848880643e-05, + "loss": 3.4235, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902771490137012e-05, + "loss": 3.4303, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.90193289538596e-05, + "loss": 3.4222, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010959385152812e-05, + "loss": 3.4224, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002573437642292e-05, + "loss": 3.417, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.899418749013177e-05, + "loss": 3.4215, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985801542621252e-05, + "loss": 3.4166, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977431973914465e-05, + "loss": 3.4259, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896904602640394e-05, + "loss": 3.4189, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896066007889342e-05, + "loss": 3.426, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.89522741313829e-05, + "loss": 3.423, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943904562676114e-05, + "loss": 3.4243, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935518615165594e-05, + "loss": 3.4229, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8927132667655074e-05, + "loss": 3.4293, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918746720144554e-05, + "loss": 3.4148, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910377151437763e-05, + "loss": 3.4274, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8901991203927243e-05, + "loss": 3.3996, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8893605256416723e-05, + "loss": 3.4291, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8885219308906206e-05, + "loss": 3.4279, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876849740199415e-05, + "loss": 3.4315, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868463792688895e-05, + "loss": 3.4158, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8860077845178375e-05, + "loss": 3.4311, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851691897667855e-05, + "loss": 3.4222, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8843322328961067e-05, + "loss": 3.4377, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8834936381450547e-05, + "loss": 3.4171, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826550433940027e-05, + "loss": 3.4196, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818164486429507e-05, + "loss": 3.4196, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809794917722716e-05, + "loss": 3.4315, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801408970212196e-05, + "loss": 3.4211, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8793023022701676e-05, + "loss": 3.4225, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.878463707519116e-05, + "loss": 3.4295, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.877626750648437e-05, + "loss": 3.4196, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.876788155897385e-05, + "loss": 3.429, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.875150203704834, + "eval_runtime": 366.5651, + "eval_samples_per_second": 1040.991, + "eval_steps_per_second": 32.532, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.875949561146333e-05, + "loss": 3.4158, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.875110966395281e-05, + "loss": 3.4261, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.874274009524602e-05, + "loss": 3.4208, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.87343541477355e-05, + "loss": 3.4241, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.872596820022498e-05, + "loss": 3.4359, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.871758225271446e-05, + "loss": 3.4199, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.870921268400767e-05, + "loss": 3.4149, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.870082673649715e-05, + "loss": 3.4125, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.869244078898663e-05, + "loss": 3.4222, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8684054841476113e-05, + "loss": 3.428, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675685272769322e-05, + "loss": 3.4179, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8667299325258802e-05, + "loss": 3.4208, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.865892975655201e-05, + "loss": 3.43, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.865054380904149e-05, + "loss": 3.415, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8642157861530975e-05, + "loss": 3.4158, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633771914020455e-05, + "loss": 3.4072, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625385966509935e-05, + "loss": 3.4193, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8617000018999415e-05, + "loss": 3.4168, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.860861407148889e-05, + "loss": 3.4139, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.860022812397837e-05, + "loss": 3.4331, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591858555271584e-05, + "loss": 3.4304, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583472607761067e-05, + "loss": 3.4237, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8575086660250544e-05, + "loss": 3.417, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566700712740024e-05, + "loss": 3.4186, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8558331144033236e-05, + "loss": 3.4214, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8549945196522716e-05, + "loss": 3.4178, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8541559249012193e-05, + "loss": 3.4029, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8533173301501676e-05, + "loss": 3.4242, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.852480373279489e-05, + "loss": 3.4173, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516417785284365e-05, + "loss": 3.4064, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8508031837773845e-05, + "loss": 3.4152, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499645890263325e-05, + "loss": 3.4197, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8491276321556537e-05, + "loss": 3.4245, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8482890374046017e-05, + "loss": 3.424, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8474504426535497e-05, + "loss": 3.417, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8466118479024977e-05, + "loss": 3.4133, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.845774891031819e-05, + "loss": 3.4329, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8449362962807666e-05, + "loss": 3.4111, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440977015297146e-05, + "loss": 3.4088, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.843259106778663e-05, + "loss": 3.4076, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.842422149907984e-05, + "loss": 3.4155, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.841583555156932e-05, + "loss": 3.4198, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.84074496040588e-05, + "loss": 3.4177, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.839906365654828e-05, + "loss": 3.4187, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.839069408784149e-05, + "loss": 3.4142, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.838230814033097e-05, + "loss": 3.4152, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837392219282045e-05, + "loss": 3.4238, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8365552624113663e-05, + "loss": 3.4148, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.835716667660314e-05, + "loss": 3.3935, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.834878072909262e-05, + "loss": 3.4207, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.83403947815821e-05, + "loss": 3.4216, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8332025212875312e-05, + "loss": 3.4264, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323655644168525e-05, + "loss": 3.4147, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8315269696658005e-05, + "loss": 3.4113, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8306883749147485e-05, + "loss": 3.4045, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.829849780163696e-05, + "loss": 3.4103, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8290111854126445e-05, + "loss": 3.4202, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281725906615925e-05, + "loss": 3.4048, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273339959105405e-05, + "loss": 3.4199, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264954011594885e-05, + "loss": 3.417, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256584442888094e-05, + "loss": 3.4083, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8248198495377574e-05, + "loss": 3.4181, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239812547867054e-05, + "loss": 3.4057, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8231426600356537e-05, + "loss": 3.408, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8223057031649746e-05, + "loss": 3.4103, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214671084139226e-05, + "loss": 3.4227, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206285136628706e-05, + "loss": 3.4035, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197915567921915e-05, + "loss": 3.4165, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.81895296204114e-05, + "loss": 3.3987, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.818114367290088e-05, + "loss": 3.4165, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8172757725390358e-05, + "loss": 3.4194, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164388156683567e-05, + "loss": 3.4154, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8156002209173047e-05, + "loss": 3.4138, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8147616261662527e-05, + "loss": 3.4177, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.8139230314152007e-05, + "loss": 3.4304, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.813086074544522e-05, + "loss": 3.4074, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.81224747979347e-05, + "loss": 3.4255, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.811408885042418e-05, + "loss": 3.4107, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.810570290291366e-05, + "loss": 3.4122, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.809733333420687e-05, + "loss": 3.4177, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088947386696352e-05, + "loss": 3.4135, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080561439185832e-05, + "loss": 3.4193, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8072175491675312e-05, + "loss": 3.4265, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806380592296852e-05, + "loss": 3.399, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8055419975458e-05, + "loss": 3.4074, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.804703402794748e-05, + "loss": 3.4109, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.803864808043696e-05, + "loss": 3.4212, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8030278511730173e-05, + "loss": 3.4069, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.8021892564219653e-05, + "loss": 3.4185, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8013506616709133e-05, + "loss": 3.4172, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8005120669198613e-05, + "loss": 3.4128, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7996751100491822e-05, + "loss": 3.407, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7988365152981306e-05, + "loss": 3.3964, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979979205470786e-05, + "loss": 3.4051, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971593257960262e-05, + "loss": 3.4161, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7963223689253475e-05, + "loss": 3.4229, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7954837741742955e-05, + "loss": 3.3993, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7946451794232435e-05, + "loss": 3.4092, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7938065846721915e-05, + "loss": 3.4111, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7929696278015127e-05, + "loss": 3.412, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7921310330504607e-05, + "loss": 3.4152, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912924382994087e-05, + "loss": 3.4146, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904538435483564e-05, + "loss": 3.4134, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7896168866776776e-05, + "loss": 3.4088, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.788778291926626e-05, + "loss": 3.4125, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7879396971755736e-05, + "loss": 3.4036, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7871011024245216e-05, + "loss": 3.4052, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.786264145553843e-05, + "loss": 3.4189, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.785425550802791e-05, + "loss": 3.406, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845869560517385e-05, + "loss": 3.4111, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837483613006868e-05, + "loss": 3.4016, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782911404430008e-05, + "loss": 3.4138, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.782072809678956e-05, + "loss": 3.4118, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7812342149279037e-05, + "loss": 3.4123, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803956201768517e-05, + "loss": 3.4122, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.779558663306173e-05, + "loss": 3.426, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.778720068555121e-05, + "loss": 3.4115, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777881473804069e-05, + "loss": 3.416, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.777042879053017e-05, + "loss": 3.4173, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7762059221823382e-05, + "loss": 3.4071, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.775367327431286e-05, + "loss": 3.4115, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.774528732680234e-05, + "loss": 3.4051, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736901379291822e-05, + "loss": 3.4065, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.7728531810585034e-05, + "loss": 3.4156, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.772014586307451e-05, + "loss": 3.4113, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.771175991556399e-05, + "loss": 3.4154, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7703390346857203e-05, + "loss": 3.411, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7695004399346683e-05, + "loss": 3.4168, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686618451836163e-05, + "loss": 3.4094, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7678232504325643e-05, + "loss": 3.4187, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7669846556815123e-05, + "loss": 3.4091, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7661460609304603e-05, + "loss": 3.4136, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7653074661794083e-05, + "loss": 3.3883, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7644688714283563e-05, + "loss": 3.4206, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7636319145576776e-05, + "loss": 3.4129, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627933198066256e-05, + "loss": 3.4221, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619547250555735e-05, + "loss": 3.4072, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7611177681848945e-05, + "loss": 3.4176, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602791734338425e-05, + "loss": 3.4113, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7594405786827904e-05, + "loss": 3.4308, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7586019839317384e-05, + "loss": 3.4061, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7577650270610597e-05, + "loss": 3.4109, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7569264323100077e-05, + "loss": 3.4087, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560878375589557e-05, + "loss": 3.4196, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552492428079037e-05, + "loss": 3.4114, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7544122859372246e-05, + "loss": 3.4096, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.753573691186173e-05, + "loss": 3.4179, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.752735096435121e-05, + "loss": 3.4132, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518965016840686e-05, + "loss": 3.4162, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8754217624664307, + "eval_runtime": 363.2197, + "eval_samples_per_second": 1050.579, + "eval_steps_per_second": 32.831, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510579069330166e-05, + "loss": 3.4033, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7502193121819646e-05, + "loss": 3.4143, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493807174309126e-05, + "loss": 3.4133, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485421226798606e-05, + "loss": 3.4138, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7477051658091818e-05, + "loss": 3.4257, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468665710581298e-05, + "loss": 3.409, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7460279763070778e-05, + "loss": 3.4091, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451893815560258e-05, + "loss": 3.4013, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7443524246853467e-05, + "loss": 3.4083, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7435138299342947e-05, + "loss": 3.4168, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.742675235183243e-05, + "loss": 3.4127, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741836640432191e-05, + "loss": 3.4098, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7410013214418852e-05, + "loss": 3.4193, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401627266908332e-05, + "loss": 3.4038, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.739324131939781e-05, + "loss": 3.4038, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384855371887292e-05, + "loss": 3.3981, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376469424376772e-05, + "loss": 3.409, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736808347686625e-05, + "loss": 3.4061, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.735969752935573e-05, + "loss": 3.406, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.735131158184521e-05, + "loss": 3.4179, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.734294201313842e-05, + "loss": 3.4213, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.73345560656279e-05, + "loss": 3.4125, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7326170118117384e-05, + "loss": 3.4043, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317784170606864e-05, + "loss": 3.4096, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7309414601900073e-05, + "loss": 3.4104, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7301028654389553e-05, + "loss": 3.4095, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7292642706879033e-05, + "loss": 3.3929, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7284256759368513e-05, + "loss": 3.4124, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275887190661725e-05, + "loss": 3.4087, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267501243151205e-05, + "loss": 3.3963, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7259115295640685e-05, + "loss": 3.4055, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7250729348130165e-05, + "loss": 3.4121, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7242359779423374e-05, + "loss": 3.4083, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233973831912854e-05, + "loss": 3.4161, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7225587884402338e-05, + "loss": 3.4049, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7217201936891814e-05, + "loss": 3.4016, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208832368185027e-05, + "loss": 3.4267, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200446420674507e-05, + "loss": 3.3972, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7192060473163987e-05, + "loss": 3.3997, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7183674525653463e-05, + "loss": 3.4024, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717530495694668e-05, + "loss": 3.4041, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.716691900943616e-05, + "loss": 3.4065, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.715853306192564e-05, + "loss": 3.4112, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7150147114415116e-05, + "loss": 3.4097, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141777545708328e-05, + "loss": 3.4046, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133391598197808e-05, + "loss": 3.4016, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7125005650687288e-05, + "loss": 3.4113, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116619703176768e-05, + "loss": 3.4018, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.710825013446998e-05, + "loss": 3.3875, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709986418695946e-05, + "loss": 3.4115, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7091478239448937e-05, + "loss": 3.4111, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7083108670742153e-05, + "loss": 3.4135, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074739102035362e-05, + "loss": 3.4041, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7066353154524842e-05, + "loss": 3.404, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057967207014322e-05, + "loss": 3.3936, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7049581259503802e-05, + "loss": 3.3963, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.704119531199328e-05, + "loss": 3.4107, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.703280936448276e-05, + "loss": 3.3942, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.702442341697224e-05, + "loss": 3.4084, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701603746946172e-05, + "loss": 3.405, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7007667900754934e-05, + "loss": 3.4004, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699928195324441e-05, + "loss": 3.4089, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.699089600573389e-05, + "loss": 3.3948, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.698251005822337e-05, + "loss": 3.3993, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6974140489516583e-05, + "loss": 3.3982, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965754542006063e-05, + "loss": 3.4116, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6957368594495543e-05, + "loss": 3.394, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6948982646985023e-05, + "loss": 3.4066, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6940613078278232e-05, + "loss": 3.3879, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6932227130767715e-05, + "loss": 3.405, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923841183257195e-05, + "loss": 3.4055, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6915471614550408e-05, + "loss": 3.4088, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6907085667039884e-05, + "loss": 3.4027, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898699719529364e-05, + "loss": 3.4055, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6890313772018844e-05, + "loss": 3.4195, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881944203312057e-05, + "loss": 3.3978, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873558255801537e-05, + "loss": 3.4188, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6865172308291017e-05, + "loss": 3.4001, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856786360780497e-05, + "loss": 3.3999, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848416792073706e-05, + "loss": 3.4063, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6840030844563186e-05, + "loss": 3.4017, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.683164489705267e-05, + "loss": 3.4103, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.682325894954215e-05, + "loss": 3.4143, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6814889380835358e-05, + "loss": 3.3949, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806503433324838e-05, + "loss": 3.394, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6798117485814318e-05, + "loss": 3.3981, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789731538303798e-05, + "loss": 3.4091, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.678136196959701e-05, + "loss": 3.3982, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.677297602208649e-05, + "loss": 3.4084, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.676459007457597e-05, + "loss": 3.4093, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.675620412706545e-05, + "loss": 3.4047, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.674783455835866e-05, + "loss": 3.3932, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.673944861084814e-05, + "loss": 3.3906, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6731062663337623e-05, + "loss": 3.3935, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6722676715827103e-05, + "loss": 3.4051, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6714307147120312e-05, + "loss": 3.4113, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.670592119960979e-05, + "loss": 3.3901, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.669753525209927e-05, + "loss": 3.399, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.668914930458875e-05, + "loss": 3.4016, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680779735881964e-05, + "loss": 3.4047, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6672393788371444e-05, + "loss": 3.4064, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6664007840860924e-05, + "loss": 3.4031, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6655621893350404e-05, + "loss": 3.4027, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6647252324643613e-05, + "loss": 3.3999, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638866377133093e-05, + "loss": 3.3982, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6630480429622576e-05, + "loss": 3.3948, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6622094482112056e-05, + "loss": 3.399, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613724913405265e-05, + "loss": 3.4046, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6605338965894745e-05, + "loss": 3.3979, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596953018384225e-05, + "loss": 3.3986, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6588567070873705e-05, + "loss": 3.395, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6580197502166918e-05, + "loss": 3.4009, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6571811554656398e-05, + "loss": 3.4043, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6563425607145878e-05, + "loss": 3.4003, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6555039659635358e-05, + "loss": 3.4, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6546670090928567e-05, + "loss": 3.4177, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6538284143418047e-05, + "loss": 3.4039, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652989819590753e-05, + "loss": 3.4042, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.652151224839701e-05, + "loss": 3.4049, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.651314267969022e-05, + "loss": 3.3974, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.65047567321797e-05, + "loss": 3.4027, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.649637078466918e-05, + "loss": 3.3929, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487984837158656e-05, + "loss": 3.3969, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.647961526845187e-05, + "loss": 3.4046, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.647124569974508e-05, + "loss": 3.4039, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.646285975223456e-05, + "loss": 3.3994, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.645447380472404e-05, + "loss": 3.4019, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.644608785721352e-05, + "loss": 3.4024, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437701909703e-05, + "loss": 3.4001, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.642931596219248e-05, + "loss": 3.4046, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.642093001468196e-05, + "loss": 3.4045, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.641254406717144e-05, + "loss": 3.4019, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6404174498464653e-05, + "loss": 3.3802, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.639578855095413e-05, + "loss": 3.4111, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.638740260344361e-05, + "loss": 3.4011, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6379016655933093e-05, + "loss": 3.4138, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370647087226305e-05, + "loss": 3.3965, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.636226113971578e-05, + "loss": 3.4058, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.635387519220526e-05, + "loss": 3.4017, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.634548924469474e-05, + "loss": 3.4218, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6337119675987954e-05, + "loss": 3.3949, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6328733728477434e-05, + "loss": 3.403, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6320347780966914e-05, + "loss": 3.3997, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6311961833456394e-05, + "loss": 3.4071, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6303592264749603e-05, + "loss": 3.4023, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6295206317239083e-05, + "loss": 3.3995, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6286820369728563e-05, + "loss": 3.404, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6278434422218046e-05, + "loss": 3.4056, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6270064853511255e-05, + "loss": 3.4051, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.8769922256469727, + "eval_runtime": 307.8628, + "eval_samples_per_second": 1239.484, + "eval_steps_per_second": 38.735, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261678906000735e-05, + "loss": 3.4031, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253292958490215e-05, + "loss": 3.401, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244907010979695e-05, + "loss": 3.4026, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236521063469175e-05, + "loss": 3.4046, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228151494762388e-05, + "loss": 3.4099, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219765547251868e-05, + "loss": 3.3992, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211379599741348e-05, + "loss": 3.4024, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6202993652230827e-05, + "loss": 3.3905, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194624083524037e-05, + "loss": 3.396, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186238136013517e-05, + "loss": 3.4066, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6177852188503e-05, + "loss": 3.4009, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616946624099248e-05, + "loss": 3.3995, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.616111305108942e-05, + "loss": 3.4145, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152727103578898e-05, + "loss": 3.3891, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144341156068378e-05, + "loss": 3.3952, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613595520855786e-05, + "loss": 3.3869, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612756926104734e-05, + "loss": 3.401, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.611918331353682e-05, + "loss": 3.3948, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.61107973660263e-05, + "loss": 3.3973, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.610241141851578e-05, + "loss": 3.4065, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609404184980899e-05, + "loss": 3.4077, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608565590229847e-05, + "loss": 3.4048, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077269954787954e-05, + "loss": 3.3938, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068884007277433e-05, + "loss": 3.4009, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060514438570643e-05, + "loss": 3.4009, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052128491060123e-05, + "loss": 3.3969, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6043742543549602e-05, + "loss": 3.3842, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603535659603908e-05, + "loss": 3.3997, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6026987027332295e-05, + "loss": 3.3956, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018601079821775e-05, + "loss": 3.3852, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010215132311255e-05, + "loss": 3.3948, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.600182918480073e-05, + "loss": 3.4017, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993459616093944e-05, + "loss": 3.3994, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5985073668583424e-05, + "loss": 3.4057, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5976687721072904e-05, + "loss": 3.3955, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968301773562384e-05, + "loss": 3.3949, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959932204855596e-05, + "loss": 3.4165, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951546257345076e-05, + "loss": 3.3838, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5943160309834553e-05, + "loss": 3.3887, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5934774362324033e-05, + "loss": 3.3915, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592640479361725e-05, + "loss": 3.393, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591801884610673e-05, + "loss": 3.3931, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909632898596205e-05, + "loss": 3.4046, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901246951085685e-05, + "loss": 3.3962, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892877382378898e-05, + "loss": 3.3981, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884491434868378e-05, + "loss": 3.3921, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876105487357857e-05, + "loss": 3.3986, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5867719539847337e-05, + "loss": 3.3956, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585934997114055e-05, + "loss": 3.3775, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850964023630026e-05, + "loss": 3.401, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842578076119506e-05, + "loss": 3.3996, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834192128608986e-05, + "loss": 3.4015, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825822559902202e-05, + "loss": 3.3961, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581743661239168e-05, + "loss": 3.3912, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580905066488116e-05, + "loss": 3.3885, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.580066471737064e-05, + "loss": 3.3857, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.579229514866385e-05, + "loss": 3.4005, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.578390920115333e-05, + "loss": 3.3853, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577552325364281e-05, + "loss": 3.3985, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767153684936024e-05, + "loss": 3.3922, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.57587677374255e-05, + "loss": 3.3925, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575038178991498e-05, + "loss": 3.3937, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.574199584240446e-05, + "loss": 3.3887, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733626273697673e-05, + "loss": 3.3902, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725256704990885e-05, + "loss": 3.3813, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716870757480365e-05, + "loss": 3.4058, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708484809969845e-05, + "loss": 3.3868, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700098862459325e-05, + "loss": 3.3876, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.56917129149488e-05, + "loss": 3.3829, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5683326967438285e-05, + "loss": 3.3925, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5674941019927765e-05, + "loss": 3.3963, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666555072417245e-05, + "loss": 3.3977, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5658185503710454e-05, + "loss": 3.3965, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5649799556199934e-05, + "loss": 3.3943, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641413608689414e-05, + "loss": 3.4077, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5633044039982626e-05, + "loss": 3.3901, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5624658092472106e-05, + "loss": 3.4096, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616272144961586e-05, + "loss": 3.3913, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5607886197451066e-05, + "loss": 3.3892, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599516628744275e-05, + "loss": 3.3952, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591130681233755e-05, + "loss": 3.3925, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.558274473372324e-05, + "loss": 3.4009, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.557435878621272e-05, + "loss": 3.4056, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5565989217505928e-05, + "loss": 3.3882, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557603269995408e-05, + "loss": 3.38, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549217322484887e-05, + "loss": 3.3895, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5540831374974367e-05, + "loss": 3.3958, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.553246180626758e-05, + "loss": 3.3891, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.552407585875706e-05, + "loss": 3.3952, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.551568991124654e-05, + "loss": 3.3986, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550730396373602e-05, + "loss": 3.3944, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.549893439502923e-05, + "loss": 3.3823, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.549054844751871e-05, + "loss": 3.3783, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548216250000819e-05, + "loss": 3.3855, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473776552497672e-05, + "loss": 3.3925, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.546540698379088e-05, + "loss": 3.4062, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545702103628036e-05, + "loss": 3.3768, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544863508876984e-05, + "loss": 3.3886, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.544024914125932e-05, + "loss": 3.394, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431879572552534e-05, + "loss": 3.3904, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423493625042014e-05, + "loss": 3.3978, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5415107677531493e-05, + "loss": 3.392, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406721730020973e-05, + "loss": 3.3949, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398352161314183e-05, + "loss": 3.3862, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389966213803663e-05, + "loss": 3.3908, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381580266293142e-05, + "loss": 3.3871, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373194318782626e-05, + "loss": 3.3911, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364824750075835e-05, + "loss": 3.3946, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356438802565315e-05, + "loss": 3.3892, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5348052855054795e-05, + "loss": 3.387, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5339666907544275e-05, + "loss": 3.3805, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5331297338837487e-05, + "loss": 3.3906, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322911391326967e-05, + "loss": 3.3962, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314525443816447e-05, + "loss": 3.393, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306139496305924e-05, + "loss": 3.3896, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297769927599136e-05, + "loss": 3.3971, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289383980088616e-05, + "loss": 3.3979, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5280998032578096e-05, + "loss": 3.3976, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5272612085067576e-05, + "loss": 3.3957, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.526424251636079e-05, + "loss": 3.3911, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255856568850269e-05, + "loss": 3.3908, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247470621339748e-05, + "loss": 3.3828, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239084673829227e-05, + "loss": 3.3873, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.523071510512244e-05, + "loss": 3.3954, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.522232915761192e-05, + "loss": 3.3944, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213943210101397e-05, + "loss": 3.391, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.520557364139461e-05, + "loss": 3.3898, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.519718769388409e-05, + "loss": 3.3912, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188801746373572e-05, + "loss": 3.3906, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180415798863048e-05, + "loss": 3.3943, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172029851352528e-05, + "loss": 3.393, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.516364390384201e-05, + "loss": 3.3962, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.515525795633149e-05, + "loss": 3.3692, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.514687200882097e-05, + "loss": 3.4005, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.513850244011418e-05, + "loss": 3.3888, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.513011649260366e-05, + "loss": 3.4041, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.512173054509314e-05, + "loss": 3.3891, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.511334459758262e-05, + "loss": 3.3927, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104975028875831e-05, + "loss": 3.3956, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096589081365311e-05, + "loss": 3.4071, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088203133854793e-05, + "loss": 3.3852, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079833565148002e-05, + "loss": 3.3951, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071447617637482e-05, + "loss": 3.3891, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063061670126963e-05, + "loss": 3.3943, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054675722616443e-05, + "loss": 3.3951, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046306153909654e-05, + "loss": 3.3901, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037920206399134e-05, + "loss": 3.3921, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029534258888614e-05, + "loss": 3.3999, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021148311378094e-05, + "loss": 3.3914, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.876962423324585, + "eval_runtime": 302.9008, + "eval_samples_per_second": 1259.789, + "eval_steps_per_second": 39.369, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012762363867574e-05, + "loss": 3.3929, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5004376416357052e-05, + "loss": 3.3931, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995990468846532e-05, + "loss": 3.3879, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4987604521336012e-05, + "loss": 3.3972, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4979234952629226e-05, + "loss": 3.3967, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970849005118703e-05, + "loss": 3.3948, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962463057608185e-05, + "loss": 3.3913, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4954077110097664e-05, + "loss": 3.3782, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945707541390874e-05, + "loss": 3.3854, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4937321593880355e-05, + "loss": 3.4024, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928935646369835e-05, + "loss": 3.389, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920549698859315e-05, + "loss": 3.3866, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4912196508956258e-05, + "loss": 3.4064, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903810561445738e-05, + "loss": 3.379, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4895424613935218e-05, + "loss": 3.384, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4887038666424698e-05, + "loss": 3.3787, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4878652718914177e-05, + "loss": 3.3903, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4870266771403657e-05, + "loss": 3.3841, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4861880823893136e-05, + "loss": 3.3884, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4853494876382618e-05, + "loss": 3.3973, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4845125307675827e-05, + "loss": 3.3956, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4836739360165309e-05, + "loss": 3.3976, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4828353412654789e-05, + "loss": 3.3816, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819967465144269e-05, + "loss": 3.3918, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.481159789643748e-05, + "loss": 3.3944, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.480321194892696e-05, + "loss": 3.3861, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.479482600141644e-05, + "loss": 3.3786, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.478645643270965e-05, + "loss": 3.3849, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.477807048519913e-05, + "loss": 3.3879, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.476968453768861e-05, + "loss": 3.3764, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.476129859017809e-05, + "loss": 3.3865, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4752912642667572e-05, + "loss": 3.3867, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4744526695157052e-05, + "loss": 3.3927, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4736140747646528e-05, + "loss": 3.3908, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.472775480013601e-05, + "loss": 3.3835, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4719385231429222e-05, + "loss": 3.3895, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4710999283918702e-05, + "loss": 3.4026, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.470261333640818e-05, + "loss": 3.374, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4694243767701393e-05, + "loss": 3.381, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4685857820190873e-05, + "loss": 3.3869, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4677471872680355e-05, + "loss": 3.378, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4669085925169831e-05, + "loss": 3.3874, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660716356463044e-05, + "loss": 3.39, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4652330408952525e-05, + "loss": 3.3864, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4643944461442002e-05, + "loss": 3.3851, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635558513931482e-05, + "loss": 3.3845, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4627188945224696e-05, + "loss": 3.3854, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618819376517905e-05, + "loss": 3.3924, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4610433429007387e-05, + "loss": 3.3612, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4602047481496867e-05, + "loss": 3.3865, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593661533986347e-05, + "loss": 3.3938, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4585275586475827e-05, + "loss": 3.3922, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576906017769038e-05, + "loss": 3.3879, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568520070258518e-05, + "loss": 3.3785, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4560134122747997e-05, + "loss": 3.3814, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551748175237476e-05, + "loss": 3.374, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4543362227726956e-05, + "loss": 3.3915, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534976280216436e-05, + "loss": 3.3769, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4526590332705917e-05, + "loss": 3.3891, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4518220763999126e-05, + "loss": 3.3808, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4509834816488608e-05, + "loss": 3.3836, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4501448868978088e-05, + "loss": 3.3787, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4493062921467568e-05, + "loss": 3.3814, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4484676973957048e-05, + "loss": 3.3782, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4476291026446528e-05, + "loss": 3.3737, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.446790507893601e-05, + "loss": 3.3899, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4459519131425486e-05, + "loss": 3.3837, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4451149562718699e-05, + "loss": 3.377, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.444276361520818e-05, + "loss": 3.3725, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4434377667697657e-05, + "loss": 3.3869, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4425991720187137e-05, + "loss": 3.3803, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4417622151480351e-05, + "loss": 3.3912, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4409236203969831e-05, + "loss": 3.3817, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400850256459309e-05, + "loss": 3.387, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4392464308948789e-05, + "loss": 3.3948, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4384094740242002e-05, + "loss": 3.3812, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.437570879273148e-05, + "loss": 3.3943, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.436732284522096e-05, + "loss": 3.3826, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.435893689771044e-05, + "loss": 3.3793, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4350567329003652e-05, + "loss": 3.3864, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4342197760296863e-05, + "loss": 3.3855, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333811812786343e-05, + "loss": 3.383, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4325425865275825e-05, + "loss": 3.3986, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4317039917765305e-05, + "loss": 3.3821, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308653970254781e-05, + "loss": 3.3702, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4300268022744263e-05, + "loss": 3.3796, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291882075233743e-05, + "loss": 3.3837, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283496127723223e-05, + "loss": 3.3849, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4275126559016434e-05, + "loss": 3.3829, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4266740611505913e-05, + "loss": 3.3897, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4258354663995393e-05, + "loss": 3.3849, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249968716484873e-05, + "loss": 3.3735, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4241599147778084e-05, + "loss": 3.3674, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4233213200267564e-05, + "loss": 3.3759, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4224827252757044e-05, + "loss": 3.3796, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4216441305246526e-05, + "loss": 3.3982, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4208071736539735e-05, + "loss": 3.3667, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199685789029216e-05, + "loss": 3.3795, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4191299841518696e-05, + "loss": 3.3849, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182913894008176e-05, + "loss": 3.3824, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4174544325301387e-05, + "loss": 3.3886, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4166158377790867e-05, + "loss": 3.3832, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4157772430280347e-05, + "loss": 3.3797, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4149386482769827e-05, + "loss": 3.3819, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4141016914063038e-05, + "loss": 3.377, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4132630966552518e-05, + "loss": 3.3751, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4124245019041998e-05, + "loss": 3.3826, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.411585907153148e-05, + "loss": 3.3854, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4107489502824688e-05, + "loss": 3.3805, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4099103555314168e-05, + "loss": 3.3742, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.409071760780365e-05, + "loss": 3.3747, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.408233166029313e-05, + "loss": 3.3802, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4073978470390073e-05, + "loss": 3.3841, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.406559252287955e-05, + "loss": 3.3828, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.405720657536903e-05, + "loss": 3.377, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4048820627858512e-05, + "loss": 3.3845, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4040434680347992e-05, + "loss": 3.3931, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4032048732837471e-05, + "loss": 3.3852, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4023662785326951e-05, + "loss": 3.3869, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4015276837816433e-05, + "loss": 3.384, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006907269109642e-05, + "loss": 3.3774, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3998521321599122e-05, + "loss": 3.3738, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3990135374088604e-05, + "loss": 3.38, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.398174942657808e-05, + "loss": 3.383, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3973379857871295e-05, + "loss": 3.3831, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964993910360774e-05, + "loss": 3.3833, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956624341653984e-05, + "loss": 3.3807, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3948238394143465e-05, + "loss": 3.38, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939852446632945e-05, + "loss": 3.3775, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3931466499122425e-05, + "loss": 3.3885, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3923080551611905e-05, + "loss": 3.3811, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914694604101383e-05, + "loss": 3.3855, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3906308656590863e-05, + "loss": 3.3602, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897922709080343e-05, + "loss": 3.3858, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3889553140373554e-05, + "loss": 3.3824, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3881167192863034e-05, + "loss": 3.3925, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3872781245352514e-05, + "loss": 3.3807, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3864395297841996e-05, + "loss": 3.3767, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3856025729135205e-05, + "loss": 3.387, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3847639781624686e-05, + "loss": 3.4004, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3839253834114166e-05, + "loss": 3.3737, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830867886603646e-05, + "loss": 3.3861, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3822498317896857e-05, + "loss": 3.3813, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3814112370386337e-05, + "loss": 3.3853, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3805726422875817e-05, + "loss": 3.3838, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3797356854169028e-05, + "loss": 3.378, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788970906658508e-05, + "loss": 3.3834, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3780584959147988e-05, + "loss": 3.3884, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3772199011637468e-05, + "loss": 3.3854, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.8787667751312256, + "eval_runtime": 306.3783, + "eval_samples_per_second": 1245.49, + "eval_steps_per_second": 38.922, + "step": 2213280 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.4784014057748849e+18, + "trial_name": null, + "trial_params": null +}