diff --git "a/checkpoint-2442240/trainer_state.json" "b/checkpoint-2442240/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2442240/trainer_state.json" @@ -0,0 +1,28901 @@ +{ + "best_metric": 3.842909812927246, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/transformer/3/checkpoints/checkpoint-992160", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2442240, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9828, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.815, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1821, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9729, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8165, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7082, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6061, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5386, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4514, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4102, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3599, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3198, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2546, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2159, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.183, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1335, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1172, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0848, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0452, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.023, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0069, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9763, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9588, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.926, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9188, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8964, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8732, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8532, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.828, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8199, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8034, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.7967, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7807, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7672, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7584, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7461, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7364, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7037, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7038, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6797, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6841, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6644, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6666, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6455, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6428, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6342, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6276, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6153, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5907, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5971, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5978, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5916, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5719, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5592, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5614, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5481, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.563, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5249, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5405, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5303, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5116, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5213, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5053, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4964, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4904, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5027, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4811, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4772, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4696, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4621, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4697, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.4767, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4497, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4607, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4656, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4472, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4359, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4374, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4348, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.421, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4193, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4273, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931261436499706e-05, + "loss": 4.4282, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930422841748654e-05, + "loss": 4.4108, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3884, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4021, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.406, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3941, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3996, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3806, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3806, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3754, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3734, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3795, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3668, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3828, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3664, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3492, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3528, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3598, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3504, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3481, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3471, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3356, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3382, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3182, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.324, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3292, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3239, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3165, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3255, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3005, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3115, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3071, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3115, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3189, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3064, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2984, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2937, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2998, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2947, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2915, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2846, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.2819, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2823, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2714, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.277, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2747, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.271, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2606, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.279, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2791, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2664, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2571, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2637, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2635, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2636, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.2589, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.2573, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2537, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2512, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2461, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2477, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.239, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2339, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2479, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2322, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2427, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2285, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.2223, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.196377277374268, + "eval_runtime": 306.8923, + "eval_samples_per_second": 1243.404, + "eval_steps_per_second": 38.857, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.2163, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.2165, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2265, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2193, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2205, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.21, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2079, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.1989, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2145, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.2058, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.2166, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.1978, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.1944, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.1892, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.1842, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.1853, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.1941, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.1816, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.1797, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.1999, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1844, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1862, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1753, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1852, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.1707, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.172, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.1704, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.1637, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1582, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1592, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1676, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1664, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.158, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.166, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1614, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1609, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1469, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1482, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.1377, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1503, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1356, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.1489, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.1375, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838210176740395e-05, + "loss": 4.1372, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1404, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1359, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.1338, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348574356165606e-05, + "loss": 4.1203, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1251, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1366, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.1329, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315046944927255e-05, + "loss": 4.124, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306660997416735e-05, + "loss": 4.1146, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1228, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.1109, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.1329, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273133586178384e-05, + "loss": 4.1051, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826474763866787e-05, + "loss": 4.1251, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825637806996108e-05, + "loss": 4.1189, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.1047, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823960617494004e-05, + "loss": 4.1166, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823122022742952e-05, + "loss": 4.11, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222834279919e-05, + "loss": 4.1003, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821446471121221e-05, + "loss": 4.101, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.1148, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.1036, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.1005, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.0983, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.0941, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.1028, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.1173, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.0947, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139023941224994e-05, + "loss": 4.1104, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.1093, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.0994, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113866098693434e-05, + "loss": 4.0894, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810549652998664e-05, + "loss": 4.1022, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.0984, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.0893, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808033868745508e-05, + "loss": 4.0905, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807196911874829e-05, + "loss": 4.0945, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.1003, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0885, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.0734, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803844170750995e-05, + "loss": 4.0813, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803005575999943e-05, + "loss": 4.0892, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802166981248891e-05, + "loss": 4.0851, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.0895, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0757, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996528348761076e-05, + "loss": 4.0717, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988142401250556e-05, + "loss": 4.0725, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979756453740036e-05, + "loss": 4.0767, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971386885033245e-05, + "loss": 4.0792, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963000937522725e-05, + "loss": 4.0746, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.0931, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794624542130542e-05, + "loss": 4.0785, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.79378594737949e-05, + "loss": 4.0617, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792947352628438e-05, + "loss": 4.0713, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792108757877386e-05, + "loss": 4.0731, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791270163126334e-05, + "loss": 4.0726, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.0717, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.0686, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788756016753551e-05, + "loss": 4.0607, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787917422002499e-05, + "loss": 4.0708, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787078827251447e-05, + "loss": 4.0472, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.0587, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.0586, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845646808786646e-05, + "loss": 4.0626, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.0525, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.0614, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.0475, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.0531, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.0525, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.0539, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.0702, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.0595, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.0532, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.0492, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0514, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774504819626786e-05, + "loss": 4.0508, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.0468, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0447, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.043, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.0457, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0343, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0423, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0405, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767799337379116e-05, + "loss": 4.0413, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.0288, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.0497, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0547, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0394, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763606363623857e-05, + "loss": 4.0319, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762767768872805e-05, + "loss": 4.0387, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761929174121753e-05, + "loss": 4.0416, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.0439, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760253622500022e-05, + "loss": 4.0386, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941502774897e-05, + "loss": 4.0385, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758576432997918e-05, + "loss": 4.0334, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577394761272386e-05, + "loss": 4.0388, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569008813761866e-05, + "loss": 4.0283, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560622866251346e-05, + "loss": 4.0369, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552236918740826e-05, + "loss": 4.0321, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0208, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753549778132725e-05, + "loss": 4.0379, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752711183381673e-05, + "loss": 4.0271, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751872588630621e-05, + "loss": 4.0329, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751033993879569e-05, + "loss": 4.0203, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750195399128517e-05, + "loss": 4.0204, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.026838779449463, + "eval_runtime": 307.1642, + "eval_samples_per_second": 1242.303, + "eval_steps_per_second": 38.823, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 4.0165, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0099, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.0288, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.0187, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0269, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 4.0116, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.0151, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 4.0018, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0178, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741809451617997e-05, + "loss": 4.0175, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.0197, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.01, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739296943125587e-05, + "loss": 4.003, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738458348374535e-05, + "loss": 4.0031, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737619753623483e-05, + "loss": 3.9992, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736781158872431e-05, + "loss": 4.0005, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735942564121379e-05, + "loss": 4.0053, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735103969370327e-05, + "loss": 3.9983, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734265374619275e-05, + "loss": 3.9995, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733428417748596e-05, + "loss": 4.021, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325898229975444e-05, + "loss": 4.0019, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 4.008, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 3.9973, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730075676624761e-05, + "loss": 4.0105, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729237081873709e-05, + "loss": 3.9884, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 3.9993, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 3.9966, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726722935500926e-05, + "loss": 3.9928, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.982, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9886, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724208789128143e-05, + "loss": 3.9988, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723370194377091e-05, + "loss": 3.9982, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 3.9927, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9943, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9918, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720015815372884e-05, + "loss": 3.9957, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719177220621832e-05, + "loss": 3.9817, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833862587078e-05, + "loss": 3.9831, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9728, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166630742490486e-05, + "loss": 3.9895, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158244794979966e-05, + "loss": 3.9768, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149858847469446e-05, + "loss": 3.9855, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 3.9797, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133103331252135e-05, + "loss": 3.9737, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124717383741615e-05, + "loss": 3.9882, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116331436231095e-05, + "loss": 3.9738, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9772, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709957592001379e-05, + "loss": 3.9606, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709118997250327e-05, + "loss": 3.9738, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082804024992744e-05, + "loss": 3.9805, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9768, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706604850877544e-05, + "loss": 3.9728, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705766256126492e-05, + "loss": 3.9589, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704927661375439e-05, + "loss": 3.972, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9606, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703252109753709e-05, + "loss": 3.9809, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702413515002657e-05, + "loss": 3.9563, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701574920251605e-05, + "loss": 3.9739, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007379633809265e-05, + "loss": 3.974, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998993686298745e-05, + "loss": 3.9543, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699060773878822e-05, + "loss": 3.964, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.69822217912777e-05, + "loss": 3.9672, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9539, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.9577, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9674, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9638, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9523, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693193886382204e-05, + "loss": 3.9593, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692355291631152e-05, + "loss": 3.9493, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.9591, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.9747, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689841145258369e-05, + "loss": 3.9552, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689002550507317e-05, + "loss": 3.9704, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688163955756265e-05, + "loss": 3.9672, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687325361005213e-05, + "loss": 3.9626, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686488404134534e-05, + "loss": 3.9487, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685649809383482e-05, + "loss": 3.9676, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.958, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9575, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.9531, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822970682596476e-05, + "loss": 3.9593, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814584735085956e-05, + "loss": 3.9692, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806198787575436e-05, + "loss": 3.9519, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797829218868645e-05, + "loss": 3.938, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789443271358125e-05, + "loss": 3.9448, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781057323847605e-05, + "loss": 3.9566, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772671376337085e-05, + "loss": 3.9553, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9582, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755915860119774e-05, + "loss": 3.9422, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747529912609254e-05, + "loss": 3.9436, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739143965098734e-05, + "loss": 3.939, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.9453, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9507, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9475, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.967, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9471, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9389, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9426, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9438, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666370319511152e-05, + "loss": 3.9509, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655317247601e-05, + "loss": 3.9451, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664693130009048e-05, + "loss": 3.94, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663854535257996e-05, + "loss": 3.9385, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9475, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9251, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9397, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6605017941341614e-05, + "loss": 3.9345, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9395, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588246046320574e-05, + "loss": 3.9318, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579860098810054e-05, + "loss": 3.9393, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.9259, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656310458259274e-05, + "loss": 3.931, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655471863508222e-05, + "loss": 3.9378, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.9311, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.9517, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.942, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652119122384387e-05, + "loss": 3.938, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651280527633335e-05, + "loss": 3.9281, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650441932882283e-05, + "loss": 3.9324, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649603338131231e-05, + "loss": 3.9334, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648764743380179e-05, + "loss": 3.9317, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647926148629127e-05, + "loss": 3.931, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647087553878075e-05, + "loss": 3.9226, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646248959127023e-05, + "loss": 3.9323, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645412002256344e-05, + "loss": 3.9183, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644573407505292e-05, + "loss": 3.9267, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.64373481275424e-05, + "loss": 3.9253, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642897855883561e-05, + "loss": 3.9268, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642059261132509e-05, + "loss": 3.9145, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641220666381457e-05, + "loss": 3.9395, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640382071630405e-05, + "loss": 3.9399, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395434768793536e-05, + "loss": 3.9297, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387048821283016e-05, + "loss": 3.9154, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378679252576226e-05, + "loss": 3.9295, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370293305065705e-05, + "loss": 3.9276, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361907357555185e-05, + "loss": 3.9337, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353521410044665e-05, + "loss": 3.9272, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345135462534145e-05, + "loss": 3.9247, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336749515023625e-05, + "loss": 3.9241, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328379946316834e-05, + "loss": 3.9309, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319993998806314e-05, + "loss": 3.9219, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311608051295794e-05, + "loss": 3.9262, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303222103785274e-05, + "loss": 3.9228, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629485253507848e-05, + "loss": 3.9155, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628646658756797e-05, + "loss": 3.9279, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627808064005745e-05, + "loss": 3.9239, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626969469254693e-05, + "loss": 3.9206, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626130874503641e-05, + "loss": 3.9132, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625292279752589e-05, + "loss": 3.912, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9523091316223145, + "eval_runtime": 303.3686, + "eval_samples_per_second": 1257.846, + "eval_steps_per_second": 39.309, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624453685001536e-05, + "loss": 3.9155, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623615090250484e-05, + "loss": 3.9062, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622778133379806e-05, + "loss": 3.9212, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621939538628753e-05, + "loss": 3.9144, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621102581758075e-05, + "loss": 3.9242, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620263987007023e-05, + "loss": 3.9076, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619425392255971e-05, + "loss": 3.9098, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618586797504919e-05, + "loss": 3.8978, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617748202753867e-05, + "loss": 3.9155, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616909608002815e-05, + "loss": 3.9145, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160726511321364e-05, + "loss": 3.915, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615234056381084e-05, + "loss": 3.9078, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614397099510405e-05, + "loss": 3.9022, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613558504759353e-05, + "loss": 3.9028, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127199100083006e-05, + "loss": 3.8973, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118813152572486e-05, + "loss": 3.9007, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110427205061966e-05, + "loss": 3.9042, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102041257551446e-05, + "loss": 3.8972, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093655310040926e-05, + "loss": 3.8988, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085269362530406e-05, + "loss": 3.9237, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607689979382362e-05, + "loss": 3.9038, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.60685138463131e-05, + "loss": 3.9044, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606012789880258e-05, + "loss": 3.9011, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605174195129206e-05, + "loss": 3.9078, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604335600378154e-05, + "loss": 3.8908, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603498643507475e-05, + "loss": 3.907, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602660048756423e-05, + "loss": 3.8973, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601821454005371e-05, + "loss": 3.894, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600982859254319e-05, + "loss": 3.8853, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60014590238364e-05, + "loss": 3.8938, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599307307632588e-05, + "loss": 3.8986, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984703507619095e-05, + "loss": 3.9032, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976317560108575e-05, + "loss": 3.9011, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967931612598055e-05, + "loss": 3.9012, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959545665087535e-05, + "loss": 3.892, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951159717577015e-05, + "loss": 3.9039, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942773770066495e-05, + "loss": 3.8853, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934387822555975e-05, + "loss": 3.8927, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926001875045455e-05, + "loss": 3.8776, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917632306338664e-05, + "loss": 3.8933, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909246358828144e-05, + "loss": 3.8844, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900860411317624e-05, + "loss": 3.8934, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892474463807104e-05, + "loss": 3.8898, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884088516296584e-05, + "loss": 3.8802, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.58757189475898e-05, + "loss": 3.8942, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586733300007928e-05, + "loss": 3.8863, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585894705256876e-05, + "loss": 3.8845, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585056110505824e-05, + "loss": 3.8714, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584217515754772e-05, + "loss": 3.8815, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.58337892100372e-05, + "loss": 3.8885, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582540326252667e-05, + "loss": 3.8863, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581703369381989e-05, + "loss": 3.8811, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580864774630937e-05, + "loss": 3.8716, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580026179879884e-05, + "loss": 3.8815, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579187585128832e-05, + "loss": 3.8681, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578350628258154e-05, + "loss": 3.8878, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577512033507102e-05, + "loss": 3.8746, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.57667343875605e-05, + "loss": 3.8798, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575834844004998e-05, + "loss": 3.8845, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574996249253946e-05, + "loss": 3.8678, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741592923832666e-05, + "loss": 3.8717, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733206976322146e-05, + "loss": 3.8802, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724821028811626e-05, + "loss": 3.8659, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716435081301106e-05, + "loss": 3.8741, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708065512594315e-05, + "loss": 3.877, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699679565083795e-05, + "loss": 3.8804, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691293617573275e-05, + "loss": 3.8654, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682907670062755e-05, + "loss": 3.8729, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674521722552235e-05, + "loss": 3.8635, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666135775041715e-05, + "loss": 3.8706, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565776620633493e-05, + "loss": 3.8838, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564938025882441e-05, + "loss": 3.8726, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564099431131389e-05, + "loss": 3.8857, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563260836380337e-05, + "loss": 3.8829, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562422241629285e-05, + "loss": 3.8807, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561583646878233e-05, + "loss": 3.8587, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560746690007554e-05, + "loss": 3.8802, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559908095256502e-05, + "loss": 3.88, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.55906950050545e-05, + "loss": 3.8682, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558230905754398e-05, + "loss": 3.8723, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557393948883719e-05, + "loss": 3.8757, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556555354132667e-05, + "loss": 3.8862, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557167593816156e-05, + "loss": 3.8682, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548781646305635e-05, + "loss": 3.8554, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540395698795115e-05, + "loss": 3.8659, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.5532009751284595e-05, + "loss": 3.8692, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523623803774075e-05, + "loss": 3.8733, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515237856263555e-05, + "loss": 3.8716, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506884666360494e-05, + "loss": 3.8633, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498498718849973e-05, + "loss": 3.8651, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5490112771339453e-05, + "loss": 3.8566, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481726823828933e-05, + "loss": 3.8619, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547335725512214e-05, + "loss": 3.8643, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546497130761162e-05, + "loss": 3.874, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545658536010111e-05, + "loss": 3.8876, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544819941259059e-05, + "loss": 3.8652, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543981346508007e-05, + "loss": 3.8551, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543142751756955e-05, + "loss": 3.8634, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542305794886276e-05, + "loss": 3.8626, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541467200135224e-05, + "loss": 3.8715, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540628605384172e-05, + "loss": 3.8632, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.53979001063312e-05, + "loss": 3.8628, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538953053762441e-05, + "loss": 3.86, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538114459011389e-05, + "loss": 3.8693, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537275864260337e-05, + "loss": 3.8437, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536437269509285e-05, + "loss": 3.8578, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535598674758233e-05, + "loss": 3.8515, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534761717887554e-05, + "loss": 3.8658, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533923123136502e-05, + "loss": 3.8533, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.53308452838545e-05, + "loss": 3.8601, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322459336343976e-05, + "loss": 3.8496, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314073388833456e-05, + "loss": 3.854, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530570382012667e-05, + "loss": 3.8578, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529731787261615e-05, + "loss": 3.8584, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288931925105625e-05, + "loss": 3.8711, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280545977595105e-05, + "loss": 3.8683, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527219278769205e-05, + "loss": 3.8599, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526380684018153e-05, + "loss": 3.8523, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255420892671017e-05, + "loss": 3.854, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247034945160496e-05, + "loss": 3.8594, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238648997649976e-05, + "loss": 3.8487, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523026305013945e-05, + "loss": 3.8553, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522187710262893e-05, + "loss": 3.8524, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521349115511841e-05, + "loss": 3.8505, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205121586411625e-05, + "loss": 3.8498, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.51967356389011e-05, + "loss": 3.8493, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518834969139058e-05, + "loss": 3.8482, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517996374388006e-05, + "loss": 3.8548, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517157779636954e-05, + "loss": 3.8399, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163208227662754e-05, + "loss": 3.8655, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.5154822280152234e-05, + "loss": 3.8614, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146436332641714e-05, + "loss": 3.8604, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5138050385131194e-05, + "loss": 3.837, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.51296808164244e-05, + "loss": 3.8552, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512129486891388e-05, + "loss": 3.8589, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511290892140336e-05, + "loss": 3.8573, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510452297389284e-05, + "loss": 3.853, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509615340518605e-05, + "loss": 3.8505, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508776745767553e-05, + "loss": 3.8499, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507938151016501e-05, + "loss": 3.8566, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507099556265449e-05, + "loss": 3.8489, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506260961514397e-05, + "loss": 3.8523, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505424004643719e-05, + "loss": 3.851, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504585409892667e-05, + "loss": 3.841, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503746815141615e-05, + "loss": 3.8564, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502908220390563e-05, + "loss": 3.852, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502071263519884e-05, + "loss": 3.8479, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501232668768832e-05, + "loss": 3.84, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.50039407401778e-05, + "loss": 3.8408, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.911149501800537, + "eval_runtime": 304.4711, + "eval_samples_per_second": 1253.291, + "eval_steps_per_second": 39.166, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499555479266728e-05, + "loss": 3.8417, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498716884515676e-05, + "loss": 3.8358, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497878289764624e-05, + "loss": 3.847, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497039695013572e-05, + "loss": 3.8454, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962011002625197e-05, + "loss": 3.8584, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953625055114677e-05, + "loss": 3.8345, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945239107604156e-05, + "loss": 3.8389, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936853160093636e-05, + "loss": 3.8249, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492848359138685e-05, + "loss": 3.8479, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492009764387633e-05, + "loss": 3.8451, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491171169636581e-05, + "loss": 3.8422, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903325748855285e-05, + "loss": 3.8407, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.48949561801485e-05, + "loss": 3.8305, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488657023263798e-05, + "loss": 3.8387, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487818428512746e-05, + "loss": 3.8254, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869798337616934e-05, + "loss": 3.8346, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486142876891015e-05, + "loss": 3.8314, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485304282139963e-05, + "loss": 3.8305, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484465687388911e-05, + "loss": 3.8355, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483627092637859e-05, + "loss": 3.8528, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827901357671806e-05, + "loss": 3.8316, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819515410161286e-05, + "loss": 3.8376, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481112946265076e-05, + "loss": 3.8319, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480274351514024e-05, + "loss": 3.8397, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479435756762972e-05, + "loss": 3.8269, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.4785987998922935e-05, + "loss": 3.8384, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477760205141241e-05, + "loss": 3.8295, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476921610390189e-05, + "loss": 3.8259, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476083015639137e-05, + "loss": 3.8194, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475246058768458e-05, + "loss": 3.8265, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744074640174064e-05, + "loss": 3.8325, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473570507146728e-05, + "loss": 3.8362, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472731912395676e-05, + "loss": 3.8364, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471893317644623e-05, + "loss": 3.8328, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471054722893571e-05, + "loss": 3.8264, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470216128142519e-05, + "loss": 3.838, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469377533391467e-05, + "loss": 3.824, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468538938640415e-05, + "loss": 3.8242, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467700343889363e-05, + "loss": 3.8115, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466863387018684e-05, + "loss": 3.8263, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466024792267632e-05, + "loss": 3.8215, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46518619751658e-05, + "loss": 3.8317, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464347602765528e-05, + "loss": 3.8259, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.46351064589485e-05, + "loss": 3.8145, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462672051143798e-05, + "loss": 3.8299, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461833456392746e-05, + "loss": 3.8243, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460994861641694e-05, + "loss": 3.818, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601579047710146e-05, + "loss": 3.811, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593193100199626e-05, + "loss": 3.8121, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584807152689106e-05, + "loss": 3.8244, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576421205178586e-05, + "loss": 3.8209, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568051636471795e-05, + "loss": 3.8171, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559665688961275e-05, + "loss": 3.8098, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551279741450755e-05, + "loss": 3.82, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542893793940235e-05, + "loss": 3.8063, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453452422523345e-05, + "loss": 3.8224, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452613827772293e-05, + "loss": 3.8092, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451775233021241e-05, + "loss": 3.8197, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450936638270189e-05, + "loss": 3.8181, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.45009968139951e-05, + "loss": 3.8123, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449261086648458e-05, + "loss": 3.8067, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448422491897406e-05, + "loss": 3.8184, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447583897146354e-05, + "loss": 3.8032, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446746940275675e-05, + "loss": 3.8108, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445908345524623e-05, + "loss": 3.8181, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445069750773571e-05, + "loss": 3.8167, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444231156022519e-05, + "loss": 3.805, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433941991518405e-05, + "loss": 3.8079, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425556044007885e-05, + "loss": 3.8052, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417170096497365e-05, + "loss": 3.8049, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408784148986845e-05, + "loss": 3.8204, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400414580280054e-05, + "loss": 3.8134, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392028632769534e-05, + "loss": 3.825, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383642685259014e-05, + "loss": 3.8221, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375256737748494e-05, + "loss": 3.8214, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43668871690417e-05, + "loss": 3.8011, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435850122153118e-05, + "loss": 3.8134, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435011527402066e-05, + "loss": 3.8216, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434172932651014e-05, + "loss": 3.8083, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433335975780336e-05, + "loss": 3.8094, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432497381029284e-05, + "loss": 3.8129, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431658786278232e-05, + "loss": 3.8281, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.43082019152718e-05, + "loss": 3.8089, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429983234656501e-05, + "loss": 3.795, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429144639905449e-05, + "loss": 3.8057, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428306045154397e-05, + "loss": 3.8111, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427467450403345e-05, + "loss": 3.8137, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426628855652293e-05, + "loss": 3.8146, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257918987816136e-05, + "loss": 3.8016, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249533040305616e-05, + "loss": 3.8054, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241147092795096e-05, + "loss": 3.8025, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232761145284576e-05, + "loss": 3.7991, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422439157657779e-05, + "loss": 3.8068, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421600562906727e-05, + "loss": 3.813, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420761968155675e-05, + "loss": 3.8276, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419923373404623e-05, + "loss": 3.8104, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419086416533944e-05, + "loss": 3.794, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418247821782892e-05, + "loss": 3.8053, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.41740922703184e-05, + "loss": 3.8016, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416570632280788e-05, + "loss": 3.814, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415733675410109e-05, + "loss": 3.8096, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414895080659057e-05, + "loss": 3.8048, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414056485908005e-05, + "loss": 3.7996, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413217891156953e-05, + "loss": 3.8103, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123809342862746e-05, + "loss": 3.7881, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115423395352226e-05, + "loss": 3.8032, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107037447841706e-05, + "loss": 3.7911, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098651500331186e-05, + "loss": 3.8096, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090281931624395e-05, + "loss": 3.7975, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081895984113875e-05, + "loss": 3.8, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073510036603355e-05, + "loss": 3.7932, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065124089092835e-05, + "loss": 3.7995, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056754520386044e-05, + "loss": 3.8015, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048368572875524e-05, + "loss": 3.8002, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039982625365004e-05, + "loss": 3.8142, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031596677854484e-05, + "loss": 3.8119, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402324348795143e-05, + "loss": 3.8039, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401485754044091e-05, + "loss": 3.7973, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400647159293039e-05, + "loss": 3.7993, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399808564541987e-05, + "loss": 3.8063, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398969969790935e-05, + "loss": 3.7871, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398131375039883e-05, + "loss": 3.8015, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397292780288831e-05, + "loss": 3.7911, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396454185537778e-05, + "loss": 3.7985, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956172286671e-05, + "loss": 3.7961, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394778633916048e-05, + "loss": 3.7957, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393940039164996e-05, + "loss": 3.7875, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393101444413944e-05, + "loss": 3.7998, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392264487543265e-05, + "loss": 3.787, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391425892792213e-05, + "loss": 3.8083, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905872980411606e-05, + "loss": 3.8018, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897487032901086e-05, + "loss": 3.811, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889101085390566e-05, + "loss": 3.7797, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388073151668378e-05, + "loss": 3.8007, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872345569173255e-05, + "loss": 3.8022, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863959621662735e-05, + "loss": 3.8001, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855573674152215e-05, + "loss": 3.7986, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847204105445424e-05, + "loss": 3.7983, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383881815793491e-05, + "loss": 3.7936, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383043221042439e-05, + "loss": 3.8048, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382204626291387e-05, + "loss": 3.7887, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381367669420708e-05, + "loss": 3.8003, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380529074669656e-05, + "loss": 3.7963, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379690479918604e-05, + "loss": 3.7886, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378851885167552e-05, + "loss": 3.7971, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378014928296873e-05, + "loss": 3.8021, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377176333545821e-05, + "loss": 3.7943, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376337738794769e-05, + "loss": 3.782, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375499144043717e-05, + "loss": 3.7917, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8861355781555176, + "eval_runtime": 312.6961, + "eval_samples_per_second": 1220.325, + "eval_steps_per_second": 38.136, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374662187173038e-05, + "loss": 3.7948, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738235924219865e-05, + "loss": 3.7808, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729849976709345e-05, + "loss": 3.7903, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721464029198824e-05, + "loss": 3.7985, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3713094460492034e-05, + "loss": 3.7996, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704708512981514e-05, + "loss": 3.7869, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.3696322565470993e-05, + "loss": 3.7832, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.3687936617960473e-05, + "loss": 3.7748, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367956704925368e-05, + "loss": 3.7935, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367118110174316e-05, + "loss": 3.7956, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366279515423264e-05, + "loss": 3.7857, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365440920672212e-05, + "loss": 3.7893, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364603963801533e-05, + "loss": 3.7781, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363765369050482e-05, + "loss": 3.7867, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.36292677429943e-05, + "loss": 3.7763, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362088179548378e-05, + "loss": 3.782, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361251222677699e-05, + "loss": 3.7758, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360412627926647e-05, + "loss": 3.782, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359574033175595e-05, + "loss": 3.7777, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358735438424543e-05, + "loss": 3.7977, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3578984815538636e-05, + "loss": 3.7832, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570598868028116e-05, + "loss": 3.7923, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562212920517596e-05, + "loss": 3.778, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553826973007076e-05, + "loss": 3.7883, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545457404300285e-05, + "loss": 3.7725, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353707145678977e-05, + "loss": 3.7863, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352868550927925e-05, + "loss": 3.7817, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352029956176873e-05, + "loss": 3.7705, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351192999306194e-05, + "loss": 3.7677, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350354404555142e-05, + "loss": 3.7745, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.34951580980409e-05, + "loss": 3.7841, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348678852933411e-05, + "loss": 3.7839, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347840258182359e-05, + "loss": 3.7856, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347001663431307e-05, + "loss": 3.7864, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346163068680255e-05, + "loss": 3.7769, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345324473929203e-05, + "loss": 3.7851, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344485879178151e-05, + "loss": 3.7764, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343647284427099e-05, + "loss": 3.7748, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342808689676047e-05, + "loss": 3.761, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419717328053685e-05, + "loss": 3.7778, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411331380543165e-05, + "loss": 3.7709, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402945433032645e-05, + "loss": 3.7823, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394559485522125e-05, + "loss": 3.776, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3386189916815334e-05, + "loss": 3.7666, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377803969304814e-05, + "loss": 3.7812, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369418021794294e-05, + "loss": 3.7703, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3361032074283774e-05, + "loss": 3.771, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352662505576983e-05, + "loss": 3.7632, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334427655806646e-05, + "loss": 3.7616, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333589061055594e-05, + "loss": 3.7734, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332750466304542e-05, + "loss": 3.7727, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331913509433864e-05, + "loss": 3.7668, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331074914682812e-05, + "loss": 3.7635, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7719, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329397725180708e-05, + "loss": 3.7532, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328560768310029e-05, + "loss": 3.7753, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327722173558977e-05, + "loss": 3.7627, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.77, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.7689, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325208027186194e-05, + "loss": 3.7657, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324369432435142e-05, + "loss": 3.7577, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.32353083768409e-05, + "loss": 3.7683, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322692242933038e-05, + "loss": 3.7603, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321855286062359e-05, + "loss": 3.7599, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321016691311307e-05, + "loss": 3.77, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320178096560255e-05, + "loss": 3.7672, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319339501809203e-05, + "loss": 3.7547, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318502544938524e-05, + "loss": 3.7652, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317663950187472e-05, + "loss": 3.7549, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.31682535543642e-05, + "loss": 3.7574, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.7741, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315149803814689e-05, + "loss": 3.7676, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314311209063637e-05, + "loss": 3.7736, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313472614312585e-05, + "loss": 3.7706, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.7784, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117970626908546e-05, + "loss": 3.758, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109584679398026e-05, + "loss": 3.763, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.7736, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7586, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084443215670195e-05, + "loss": 3.767, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3076057268159675e-05, + "loss": 3.7684, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067671320649155e-05, + "loss": 3.7712, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305928537313863e-05, + "loss": 3.7629, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050915804431844e-05, + "loss": 3.751, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042529856921324e-05, + "loss": 3.7577, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034143909410804e-05, + "loss": 3.7627, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025757961900284e-05, + "loss": 3.7668, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.30173883931935e-05, + "loss": 3.765, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300900244568298e-05, + "loss": 3.7584, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300061649817245e-05, + "loss": 3.7604, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299223055066193e-05, + "loss": 3.7539, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298386098195515e-05, + "loss": 3.753, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297547503444463e-05, + "loss": 3.7581, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.29670890869341e-05, + "loss": 3.7689, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295870313942358e-05, + "loss": 3.7829, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.29503335707168e-05, + "loss": 3.7669, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294194762320628e-05, + "loss": 3.7458, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293356167569576e-05, + "loss": 3.7632, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292517572818524e-05, + "loss": 3.7575, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916806159478454e-05, + "loss": 3.7675, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290842021196793e-05, + "loss": 3.7612, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290003426445741e-05, + "loss": 3.7595, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289164831694689e-05, + "loss": 3.7568, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.28832787482401e-05, + "loss": 3.7605, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874892800729576e-05, + "loss": 3.7473, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866506853219056e-05, + "loss": 3.7582, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858120905708536e-05, + "loss": 3.7445, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284975133700175e-05, + "loss": 3.767, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841365389491225e-05, + "loss": 3.7512, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283297944198071e-05, + "loss": 3.7535, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282459349447019e-05, + "loss": 3.7451, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.28162239257634e-05, + "loss": 3.7586, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807854357056617e-05, + "loss": 3.7558, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799468409546097e-05, + "loss": 3.7561, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791082462035576e-05, + "loss": 3.7681, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278269651452505e-05, + "loss": 3.768, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774326945818266e-05, + "loss": 3.7595, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765940998307746e-05, + "loss": 3.7543, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757555050797225e-05, + "loss": 3.7512, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.27491691032867e-05, + "loss": 3.763, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274078315577618e-05, + "loss": 3.7453, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2732397208265665e-05, + "loss": 3.7556, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2724011260755145e-05, + "loss": 3.7444, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715625313244625e-05, + "loss": 3.7556, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707255744537834e-05, + "loss": 3.7448, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698869797027314e-05, + "loss": 3.7519, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690483849516794e-05, + "loss": 3.7497, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2682097902006274e-05, + "loss": 3.7507, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267372833329948e-05, + "loss": 3.7474, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266534238578896e-05, + "loss": 3.7612, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265695643827844e-05, + "loss": 3.7609, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264857049076792e-05, + "loss": 3.7643, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264020092206113e-05, + "loss": 3.737, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263181497455062e-05, + "loss": 3.7586, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.26234290270401e-05, + "loss": 3.7593, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261504307952958e-05, + "loss": 3.7608, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260667351082279e-05, + "loss": 3.7521, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259828756331227e-05, + "loss": 3.7576, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258990161580175e-05, + "loss": 3.752, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258151566829123e-05, + "loss": 3.7643, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257314609958444e-05, + "loss": 3.7415, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256476015207392e-05, + "loss": 3.7599, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.25563742045634e-05, + "loss": 3.7492, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254798825705288e-05, + "loss": 3.75, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539618688346086e-05, + "loss": 3.7538, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253123274083557e-05, + "loss": 3.7514, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252284679332505e-05, + "loss": 3.7579, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251446084581453e-05, + "loss": 3.7368, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250609127710774e-05, + "loss": 3.7492, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.870025873184204, + "eval_runtime": 311.8832, + "eval_samples_per_second": 1223.506, + "eval_steps_per_second": 38.235, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249770532959722e-05, + "loss": 3.7486, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.24893193820867e-05, + "loss": 3.7375, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248093343457618e-05, + "loss": 3.7494, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247254748706566e-05, + "loss": 3.7556, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246416153955514e-05, + "loss": 3.7598, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245577559204462e-05, + "loss": 3.7433, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.24473896445341e-05, + "loss": 3.7378, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243900369702358e-05, + "loss": 3.7373, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243063412831679e-05, + "loss": 3.7457, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242224818080627e-05, + "loss": 3.754, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241386223329575e-05, + "loss": 3.7441, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240547628578524e-05, + "loss": 3.7487, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397123095882175e-05, + "loss": 3.7395, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388737148371655e-05, + "loss": 3.7413, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7373, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371965253350615e-05, + "loss": 3.7386, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7358, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355193358329575e-05, + "loss": 3.7379, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346807410819055e-05, + "loss": 3.7398, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233842146330853e-05, + "loss": 3.7557, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330051894601744e-05, + "loss": 3.7425, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321665947091224e-05, + "loss": 3.7498, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313279999580704e-05, + "loss": 3.7353, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304894052070184e-05, + "loss": 3.747, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.22965244833634e-05, + "loss": 3.732, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228813853585288e-05, + "loss": 3.7473, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227975258834236e-05, + "loss": 3.738, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227136664083183e-05, + "loss": 3.73, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226299707212505e-05, + "loss": 3.7331, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225461112461453e-05, + "loss": 3.7356, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246225177104e-05, + "loss": 3.7409, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223785560839722e-05, + "loss": 3.7437, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.22294696608867e-05, + "loss": 3.7454, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222108371337618e-05, + "loss": 3.7489, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221269776586566e-05, + "loss": 3.7298, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220431181835514e-05, + "loss": 3.7472, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219592587084462e-05, + "loss": 3.7395, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.21875399233341e-05, + "loss": 3.7275, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217915397582358e-05, + "loss": 3.7235, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170784407116787e-05, + "loss": 3.7309, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162398459606267e-05, + "loss": 3.7346, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154012512095746e-05, + "loss": 3.7406, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145626564585226e-05, + "loss": 3.7342, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137256995878436e-05, + "loss": 3.7285, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128871048367915e-05, + "loss": 3.744, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120485100857395e-05, + "loss": 3.7312, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211209915334688e-05, + "loss": 3.7314, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210372958464009e-05, + "loss": 3.7234, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209534363712957e-05, + "loss": 3.7209, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208695768961905e-05, + "loss": 3.7354, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207858812091226e-05, + "loss": 3.7341, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207020217340174e-05, + "loss": 3.7296, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206181622589122e-05, + "loss": 3.7236, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.20534302783807e-05, + "loss": 3.7344, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204506070967391e-05, + "loss": 3.7114, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203667476216339e-05, + "loss": 3.7351, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202828881465287e-05, + "loss": 3.7224, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201990286714235e-05, + "loss": 3.7243, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011533298435565e-05, + "loss": 3.7333, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003147350925045e-05, + "loss": 3.7236, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994761403414525e-05, + "loss": 3.7212, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986375455904005e-05, + "loss": 3.7366, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1978005887197214e-05, + "loss": 3.7179, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969619939686694e-05, + "loss": 3.7221, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961233992176174e-05, + "loss": 3.731, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952848044665654e-05, + "loss": 3.7287, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194447847595886e-05, + "loss": 3.7156, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193609252844834e-05, + "loss": 3.7266, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192770658093782e-05, + "loss": 3.7142, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.19193206334273e-05, + "loss": 3.7181, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191095106472052e-05, + "loss": 3.7317, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190256511721e-05, + "loss": 3.7287, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189417916969948e-05, + "loss": 3.7368, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188579322218896e-05, + "loss": 3.7295, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187742365348217e-05, + "loss": 3.7421, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186903770597165e-05, + "loss": 3.7186, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186065175846113e-05, + "loss": 3.7279, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185226581095061e-05, + "loss": 3.735, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843896242243817e-05, + "loss": 3.7173, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835510294733297e-05, + "loss": 3.7279, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827124347222776e-05, + "loss": 3.7319, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818738399712256e-05, + "loss": 3.7352, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181036883100547e-05, + "loss": 3.7244, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180198288349495e-05, + "loss": 3.7159, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179359693598443e-05, + "loss": 3.7177, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178521098847391e-05, + "loss": 3.724, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177684141976712e-05, + "loss": 3.7313, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.17684554722566e-05, + "loss": 3.727, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176006952474608e-05, + "loss": 3.7257, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175168357723556e-05, + "loss": 3.7141, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174331400852877e-05, + "loss": 3.7191, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173492806101825e-05, + "loss": 3.7169, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172654211350773e-05, + "loss": 3.7203, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171815616599721e-05, + "loss": 3.732, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709786597290426e-05, + "loss": 3.7411, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7295, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693014702269386e-05, + "loss": 3.7137, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684628754758866e-05, + "loss": 3.7216, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676259186052075e-05, + "loss": 3.7206, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667873238541555e-05, + "loss": 3.7293, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659487291031035e-05, + "loss": 3.7235, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651101343520515e-05, + "loss": 3.7283, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642731774813724e-05, + "loss": 3.721, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634345827303204e-05, + "loss": 3.7178, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625959879792684e-05, + "loss": 3.7159, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617573932282164e-05, + "loss": 3.7181, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160920436357538e-05, + "loss": 3.7083, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160081841606486e-05, + "loss": 3.7296, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159243246855434e-05, + "loss": 3.7144, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158404652104382e-05, + "loss": 3.7167, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157567695233703e-05, + "loss": 3.7119, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156729100482651e-05, + "loss": 3.7168, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155892143611972e-05, + "loss": 3.723, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.15505354886092e-05, + "loss": 3.7177, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154214954109868e-05, + "loss": 3.7331, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153376359358816e-05, + "loss": 3.7268, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152539402488137e-05, + "loss": 3.7236, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151700807737085e-05, + "loss": 3.7203, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150862212986033e-05, + "loss": 3.708, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150023618234981e-05, + "loss": 3.7306, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149185023483929e-05, + "loss": 3.7148, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148346428732877e-05, + "loss": 3.7174, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147507833981825e-05, + "loss": 3.7092, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146669239230773e-05, + "loss": 3.7166, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145832282360094e-05, + "loss": 3.7101, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144993687609042e-05, + "loss": 3.7163, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.14415509285799e-05, + "loss": 3.7112, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143316498106938e-05, + "loss": 3.72, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142479541236259e-05, + "loss": 3.7095, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141640946485207e-05, + "loss": 3.7268, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140802351734155e-05, + "loss": 3.7215, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.7287, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139126800112425e-05, + "loss": 3.7026, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138288205361373e-05, + "loss": 3.7242, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137449610610321e-05, + "loss": 3.722, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136611015859268e-05, + "loss": 3.7215, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357740589885896e-05, + "loss": 3.7198, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349354642375376e-05, + "loss": 3.7194, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340968694864856e-05, + "loss": 3.7122, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.7343, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324213178647545e-05, + "loss": 3.7032, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315827231137025e-05, + "loss": 3.7234, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.7141, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299055336115985e-05, + "loss": 3.7143, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12906857674092e-05, + "loss": 3.7175, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128229981989868e-05, + "loss": 3.7137, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7243, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265527924877634e-05, + "loss": 3.6976, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125715835617085e-05, + "loss": 3.7159, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.86078143119812, + "eval_runtime": 306.4804, + "eval_samples_per_second": 1245.075, + "eval_steps_per_second": 38.91, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124877240866032e-05, + "loss": 3.7148, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.12403864611498e-05, + "loss": 3.7035, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123200051363928e-05, + "loss": 3.7123, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12236309449325e-05, + "loss": 3.7168, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121524499742198e-05, + "loss": 3.7243, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120685904991146e-05, + "loss": 3.7105, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119847310240094e-05, + "loss": 3.7044, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1190103533694154e-05, + "loss": 3.7024, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118171758618363e-05, + "loss": 3.7122, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117333163867311e-05, + "loss": 3.7169, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116494569116259e-05, + "loss": 3.7101, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156576122455796e-05, + "loss": 3.7129, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114820655374901e-05, + "loss": 3.7087, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113982060623849e-05, + "loss": 3.706, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113143465872797e-05, + "loss": 3.6996, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112304871121745e-05, + "loss": 3.7014, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111466276370693e-05, + "loss": 3.7049, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110627681619641e-05, + "loss": 3.7022, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109789086868589e-05, + "loss": 3.707, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108950492117537e-05, + "loss": 3.7162, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108113535246858e-05, + "loss": 3.7117, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107274940495806e-05, + "loss": 3.7145, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106436345744754e-05, + "loss": 3.7025, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105597750993702e-05, + "loss": 3.711, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104760794123023e-05, + "loss": 3.699, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103922199371971e-05, + "loss": 3.7161, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103083604620919e-05, + "loss": 3.6991, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102245009869867e-05, + "loss": 3.6975, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1014080529991886e-05, + "loss": 3.6992, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005694582481366e-05, + "loss": 3.7006, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997308634970846e-05, + "loss": 3.7038, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988939066264055e-05, + "loss": 3.7108, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980553118753535e-05, + "loss": 3.7119, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972167171243015e-05, + "loss": 3.7074, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963781223732495e-05, + "loss": 3.7017, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955395276221975e-05, + "loss": 3.7123, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0947009328711455e-05, + "loss": 3.7085, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938623381200935e-05, + "loss": 3.6903, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930237433690414e-05, + "loss": 3.6925, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921867864983624e-05, + "loss": 3.6972, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913481917473104e-05, + "loss": 3.7005, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905095969962583e-05, + "loss": 3.7064, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089671002245207e-05, + "loss": 3.7013, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088834045374528e-05, + "loss": 3.6955, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087995450623476e-05, + "loss": 3.7068, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087156855872424e-05, + "loss": 3.7003, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086319899001745e-05, + "loss": 3.7022, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085481304250693e-05, + "loss": 3.6876, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084642709499641e-05, + "loss": 3.6845, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083804114748589e-05, + "loss": 3.7073, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.08296715787791e-05, + "loss": 3.6961, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082128563126858e-05, + "loss": 3.7004, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081289968375806e-05, + "loss": 3.6926, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080453011505127e-05, + "loss": 3.6947, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079614416754075e-05, + "loss": 3.6815, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078775822003023e-05, + "loss": 3.6985, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077937227251971e-05, + "loss": 3.6933, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077098632500919e-05, + "loss": 3.6922, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076260037749867e-05, + "loss": 3.7058, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075421442998815e-05, + "loss": 3.6897, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074582848247763e-05, + "loss": 3.6866, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073745891377084e-05, + "loss": 3.7037, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072907296626032e-05, + "loss": 3.6874, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.07206870187498e-05, + "loss": 3.684, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071230107123928e-05, + "loss": 3.7002, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070393150253249e-05, + "loss": 3.6963, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069554555502198e-05, + "loss": 3.6823, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068715960751146e-05, + "loss": 3.6971, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067877366000094e-05, + "loss": 3.6826, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6845, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.7016, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653632196273106e-05, + "loss": 3.6976, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064524624876258e-05, + "loss": 3.6996, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636876680055796e-05, + "loss": 3.6974, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628490732545275e-05, + "loss": 3.712, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620104785034755e-05, + "loss": 3.6886, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061171883752423e-05, + "loss": 3.6973, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603349268817444e-05, + "loss": 3.7027, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059496332130693e-05, + "loss": 3.6868, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586577373796404e-05, + "loss": 3.6949, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578191426285884e-05, + "loss": 3.7014, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569805478775364e-05, + "loss": 3.7022, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561419531264844e-05, + "loss": 3.6951, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553033583754324e-05, + "loss": 3.6839, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544647636243804e-05, + "loss": 3.6812, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053627806753701e-05, + "loss": 3.694, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052789212002649e-05, + "loss": 3.7022, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051950617251597e-05, + "loss": 3.6966, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051112022500545e-05, + "loss": 3.6949, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050275065629867e-05, + "loss": 3.6785, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049436470878815e-05, + "loss": 3.6896, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048597876127763e-05, + "loss": 3.6875, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047760919257084e-05, + "loss": 3.6931, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046922324506032e-05, + "loss": 3.6961, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.04608372975498e-05, + "loss": 3.71, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045245135003928e-05, + "loss": 3.6967, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044408178133249e-05, + "loss": 3.6833, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043569583382197e-05, + "loss": 3.6874, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042730988631145e-05, + "loss": 3.6903, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041892393880093e-05, + "loss": 3.6982, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410554370094136e-05, + "loss": 3.6927, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040216842258362e-05, + "loss": 3.6983, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.03937824750731e-05, + "loss": 3.6884, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038539652756258e-05, + "loss": 3.679, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037702695885579e-05, + "loss": 3.6903, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036864101134527e-05, + "loss": 3.6842, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036025506383475e-05, + "loss": 3.6804, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035186911632423e-05, + "loss": 3.6942, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034349954761744e-05, + "loss": 3.6865, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033511360010692e-05, + "loss": 3.6832, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032674403140013e-05, + "loss": 3.6837, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031835808388961e-05, + "loss": 3.6812, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030997213637909e-05, + "loss": 3.6932, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301586188868576e-05, + "loss": 3.6852, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293200241358056e-05, + "loss": 3.7032, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.6979, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276428346337016e-05, + "loss": 3.6945, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268058777630225e-05, + "loss": 3.6873, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259672830119705e-05, + "loss": 3.6773, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.692, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242900935098665e-05, + "loss": 3.6877, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234514987588145e-05, + "loss": 3.6847, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226129040077625e-05, + "loss": 3.6785, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217743092567105e-05, + "loss": 3.6875, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209373523860314e-05, + "loss": 3.679, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200987576349794e-05, + "loss": 3.6874, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192601628839274e-05, + "loss": 3.6797, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184215681328754e-05, + "loss": 3.6921, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017584611262197e-05, + "loss": 3.6763, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016746016511145e-05, + "loss": 3.6976, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015907421760093e-05, + "loss": 3.6896, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015068827009041e-05, + "loss": 3.6982, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014231870138362e-05, + "loss": 3.6741, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.01339327538731e-05, + "loss": 3.6936, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012554680636258e-05, + "loss": 3.6907, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011716085885206e-05, + "loss": 3.6937, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010879129014527e-05, + "loss": 3.6887, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010040534263475e-05, + "loss": 3.6848, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009201939512423e-05, + "loss": 3.6861, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008363344761371e-05, + "loss": 3.7015, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.0075263878906924e-05, + "loss": 3.6739, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.0066877931396404e-05, + "loss": 3.6915, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005850836268961e-05, + "loss": 3.6876, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005012241517909e-05, + "loss": 3.6827, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004173646766857e-05, + "loss": 3.688, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003335052015805e-05, + "loss": 3.6816, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002496457264753e-05, + "loss": 3.6942, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016578625137006e-05, + "loss": 3.6676, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000820905643022e-05, + "loss": 3.6895, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.852648973464966, + "eval_runtime": 304.8314, + "eval_samples_per_second": 1251.81, + "eval_steps_per_second": 39.12, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.99998231089197e-05, + "loss": 3.679, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999143716140918e-05, + "loss": 3.6764, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998305121389866e-05, + "loss": 3.6814, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997466526638814e-05, + "loss": 3.6864, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996627931887762e-05, + "loss": 3.6968, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.99578933713671e-05, + "loss": 3.6777, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994950742385658e-05, + "loss": 3.679, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994112147634606e-05, + "loss": 3.6751, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993275190763927e-05, + "loss": 3.6782, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992436596012875e-05, + "loss": 3.6901, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991598001261823e-05, + "loss": 3.6769, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990759406510771e-05, + "loss": 3.6859, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899240875204655e-05, + "loss": 3.6761, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890854927694135e-05, + "loss": 3.6745, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882468980183615e-05, + "loss": 3.6738, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874083032673095e-05, + "loss": 3.6706, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865697085162575e-05, + "loss": 3.6736, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857311137652055e-05, + "loss": 3.673, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848925190141535e-05, + "loss": 3.6769, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840539242631015e-05, + "loss": 3.6839, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832169673924224e-05, + "loss": 3.6827, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823783726413704e-05, + "loss": 3.6876, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815397778903184e-05, + "loss": 3.6734, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9807011831392664e-05, + "loss": 3.6794, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979864226268587e-05, + "loss": 3.6717, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979025631517535e-05, + "loss": 3.6855, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978187036766484e-05, + "loss": 3.673, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977348442015432e-05, + "loss": 3.6712, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976511485144753e-05, + "loss": 3.6698, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975672890393701e-05, + "loss": 3.6696, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974834295642649e-05, + "loss": 3.671, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.97399733877197e-05, + "loss": 3.6843, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973158744020918e-05, + "loss": 3.6793, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972320149269866e-05, + "loss": 3.6799, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971481554518814e-05, + "loss": 3.6713, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970642959767762e-05, + "loss": 3.6848, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9698060028970827e-05, + "loss": 3.6779, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689674081460306e-05, + "loss": 3.6626, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968128813394979e-05, + "loss": 3.6656, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967290218643927e-05, + "loss": 3.6673, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966451623892875e-05, + "loss": 3.6706, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965613029141823e-05, + "loss": 3.6777, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964776072271144e-05, + "loss": 3.6745, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963937477520092e-05, + "loss": 3.6669, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.96309888276904e-05, + "loss": 3.6792, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962260288017988e-05, + "loss": 3.6688, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961421693266936e-05, + "loss": 3.6761, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960583098515884e-05, + "loss": 3.6596, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597445037648315e-05, + "loss": 3.6504, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958907546894153e-05, + "loss": 3.6809, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958068952143101e-05, + "loss": 3.6676, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957230357392049e-05, + "loss": 3.6744, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956391762640997e-05, + "loss": 3.6665, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955554805770319e-05, + "loss": 3.6621, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954716211019267e-05, + "loss": 3.6573, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538792541485876e-05, + "loss": 3.6705, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530406593975356e-05, + "loss": 3.6624, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9522020646464836e-05, + "loss": 3.6672, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513634698954316e-05, + "loss": 3.6782, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950524875144379e-05, + "loss": 3.6583, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949686280393327e-05, + "loss": 3.6589, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948847685642275e-05, + "loss": 3.6767, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948009090891223e-05, + "loss": 3.6577, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471721340205445e-05, + "loss": 3.6584, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463335392694925e-05, + "loss": 3.6747, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454949445184404e-05, + "loss": 3.6651, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446563497673884e-05, + "loss": 3.6549, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438193928967094e-05, + "loss": 3.6678, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429807981456573e-05, + "loss": 3.6568, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421422033946053e-05, + "loss": 3.6547, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413036086435533e-05, + "loss": 3.6722, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940466651772874e-05, + "loss": 3.6687, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939628057021822e-05, + "loss": 3.6699, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938791100151144e-05, + "loss": 3.6703, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937952505400092e-05, + "loss": 3.6853, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.93711391064904e-05, + "loss": 3.6607, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936275315897988e-05, + "loss": 3.6702, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935438359027309e-05, + "loss": 3.6704, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934599764276257e-05, + "loss": 3.6612, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933761169525205e-05, + "loss": 3.6635, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932922574774153e-05, + "loss": 3.6777, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932083980023101e-05, + "loss": 3.6714, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931245385272049e-05, + "loss": 3.6723, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304084284013696e-05, + "loss": 3.6547, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295698336503176e-05, + "loss": 3.6505, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287312388992656e-05, + "loss": 3.6692, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9278926441482136e-05, + "loss": 3.6738, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270540493971616e-05, + "loss": 3.6682, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621545464611e-05, + "loss": 3.6671, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925376859895058e-05, + "loss": 3.6509, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924539903024379e-05, + "loss": 3.6627, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923701308273327e-05, + "loss": 3.6599, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922862713522275e-05, + "loss": 3.6609, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922024118771223e-05, + "loss": 3.6728, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921187161900544e-05, + "loss": 3.6787, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920348567149492e-05, + "loss": 3.6731, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.91950997239844e-05, + "loss": 3.6589, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918671377647388e-05, + "loss": 3.6566, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917832782896336e-05, + "loss": 3.6643, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916994188145284e-05, + "loss": 3.6717, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161572312746056e-05, + "loss": 3.6642, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153186365235536e-05, + "loss": 3.6721, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144800417725016e-05, + "loss": 3.6644, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136414470214496e-05, + "loss": 3.6549, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128028522703976e-05, + "loss": 3.6621, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911964257519345e-05, + "loss": 3.6562, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111273006486665e-05, + "loss": 3.6547, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102887058976145e-05, + "loss": 3.6659, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094501111465625e-05, + "loss": 3.6626, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.90861151639551e-05, + "loss": 3.6565, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077745595248314e-05, + "loss": 3.6532, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069359647737794e-05, + "loss": 3.6525, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060973700227274e-05, + "loss": 3.6655, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052587752716754e-05, + "loss": 3.6569, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044201805206234e-05, + "loss": 3.6775, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035815857695714e-05, + "loss": 3.6738, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027429910185194e-05, + "loss": 3.6653, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.90190603414784e-05, + "loss": 3.6597, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901067439396788e-05, + "loss": 3.6547, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900228844645736e-05, + "loss": 3.666, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899390249894684e-05, + "loss": 3.6583, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898553293024005e-05, + "loss": 3.6587, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897714698272953e-05, + "loss": 3.6537, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896876103521901e-05, + "loss": 3.663, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896037508770849e-05, + "loss": 3.6552, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895198914019798e-05, + "loss": 3.6584, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894360319268746e-05, + "loss": 3.6503, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893521724517694e-05, + "loss": 3.6657, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892683129766642e-05, + "loss": 3.6508, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891846172895963e-05, + "loss": 3.6669, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891007578144911e-05, + "loss": 3.6641, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890168983393859e-05, + "loss": 3.671, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889330388642807e-05, + "loss": 3.6497, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888491793891755e-05, + "loss": 3.668, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887653199140703e-05, + "loss": 3.6582, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886814604389651e-05, + "loss": 3.6667, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859776475189716e-05, + "loss": 3.6675, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851390527679196e-05, + "loss": 3.6556, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843004580168676e-05, + "loss": 3.6604, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8834618632658156e-05, + "loss": 3.6736, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882624906395137e-05, + "loss": 3.6489, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881786311644085e-05, + "loss": 3.6629, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880949354773406e-05, + "loss": 3.6651, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880110760022354e-05, + "loss": 3.6599, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879272165271302e-05, + "loss": 3.6561, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.87843357052025e-05, + "loss": 3.6558, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877594975769198e-05, + "loss": 3.6673, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876756381018146e-05, + "loss": 3.6453, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875919424147467e-05, + "loss": 3.6619, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8480799198150635, + "eval_runtime": 305.5345, + "eval_samples_per_second": 1248.929, + "eval_steps_per_second": 39.03, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875080829396415e-05, + "loss": 3.6553, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874242234645363e-05, + "loss": 3.6492, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873403639894311e-05, + "loss": 3.652, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872565045143259e-05, + "loss": 3.6612, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871726450392207e-05, + "loss": 3.6727, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6521, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870050898770476e-05, + "loss": 3.651, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869212304019424e-05, + "loss": 3.6542, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868373709268372e-05, + "loss": 3.6464, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.86753511451732e-05, + "loss": 3.6665, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866696519766268e-05, + "loss": 3.6496, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865857925015216e-05, + "loss": 3.6546, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6611, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.6437, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.6451, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625051838913814e-05, + "loss": 3.6449, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616665891403294e-05, + "loss": 3.6483, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608279943892774e-05, + "loss": 3.6517, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599893996382254e-05, + "loss": 3.647, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591508048871734e-05, + "loss": 3.6558, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858313848016494e-05, + "loss": 3.6602, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857475253265442e-05, + "loss": 3.6631, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.85663665851439e-05, + "loss": 3.6533, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855798063763338e-05, + "loss": 3.6463, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854962744773032e-05, + "loss": 3.6483, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.85412415002198e-05, + "loss": 3.6594, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853285555270929e-05, + "loss": 3.651, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852446960519877e-05, + "loss": 3.6474, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851608365768825e-05, + "loss": 3.6426, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850769771017773e-05, + "loss": 3.6444, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849931176266721e-05, + "loss": 3.6422, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849094219396042e-05, + "loss": 3.662, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84825562464499e-05, + "loss": 3.6573, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847417029893938e-05, + "loss": 3.6535, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846578435142886e-05, + "loss": 3.6459, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845739840391834e-05, + "loss": 3.6499, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449028835211546e-05, + "loss": 3.6588, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440642887701026e-05, + "loss": 3.6398, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432256940190506e-05, + "loss": 3.6432, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423870992679986e-05, + "loss": 3.6389, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.84155014239732e-05, + "loss": 3.644, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840711547646268e-05, + "loss": 3.6528, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839872952895216e-05, + "loss": 3.6479, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839034358144164e-05, + "loss": 3.6438, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838195763393112e-05, + "loss": 3.6525, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837358806522433e-05, + "loss": 3.6463, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836520211771381e-05, + "loss": 3.6465, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835681617020329e-05, + "loss": 3.6396, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834843022269277e-05, + "loss": 3.6196, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340044275182244e-05, + "loss": 3.66, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331658327671724e-05, + "loss": 3.6403, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832328875896494e-05, + "loss": 3.6546, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831490281145442e-05, + "loss": 3.637, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.83065168639439e-05, + "loss": 3.6405, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829813091643338e-05, + "loss": 3.6324, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289761347726595e-05, + "loss": 3.6414, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828137540021607e-05, + "loss": 3.6376, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827298945270555e-05, + "loss": 3.6423, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826460350519503e-05, + "loss": 3.6543, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825621755768451e-05, + "loss": 3.6342, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824784798897772e-05, + "loss": 3.6339, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.82394620414672e-05, + "loss": 3.6527, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823107609395668e-05, + "loss": 3.6355, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822269014644616e-05, + "loss": 3.6304, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8214304198935644e-05, + "loss": 3.6462, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205918251425124e-05, + "loss": 3.642, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197532303914604e-05, + "loss": 3.6311, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189146356404084e-05, + "loss": 3.6434, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818077678769729e-05, + "loss": 3.632, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817239084018677e-05, + "loss": 3.6341, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816400489267625e-05, + "loss": 3.6472, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815563532396946e-05, + "loss": 3.6441, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814724937645894e-05, + "loss": 3.6478, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813886342894842e-05, + "loss": 3.645, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81304774814379e-05, + "loss": 3.66, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812209153392738e-05, + "loss": 3.6339, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.81137219652206e-05, + "loss": 3.6511, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810533601771008e-05, + "loss": 3.6416, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809695007019956e-05, + "loss": 3.6401, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808856412268904e-05, + "loss": 3.6393, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808017817517852e-05, + "loss": 3.6535, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071808606471727e-05, + "loss": 3.6452, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063422658961207e-05, + "loss": 3.6487, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055036711450686e-05, + "loss": 3.6281, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046650763940166e-05, + "loss": 3.6303, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038264816429646e-05, + "loss": 3.6438, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029895247722855e-05, + "loss": 3.6487, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021509300212335e-05, + "loss": 3.6385, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013123352701815e-05, + "loss": 3.6482, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004737405191295e-05, + "loss": 3.6293, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799635145768078e-05, + "loss": 3.6378, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987965510170255e-05, + "loss": 3.6375, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979579562659735e-05, + "loss": 3.6356, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971193615149215e-05, + "loss": 3.6478, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796282404644243e-05, + "loss": 3.6543, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954438098931904e-05, + "loss": 3.6487, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946052151421384e-05, + "loss": 3.6334, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937666203910864e-05, + "loss": 3.6336, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929280256400344e-05, + "loss": 3.642, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920894308889824e-05, + "loss": 3.6447, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791252474018303e-05, + "loss": 3.641, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790413879267252e-05, + "loss": 3.6469, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895752845162e-05, + "loss": 3.6426, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788736689765148e-05, + "loss": 3.6326, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787898095014096e-05, + "loss": 3.6363, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787061138143417e-05, + "loss": 3.632, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786222543392365e-05, + "loss": 3.6323, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785383948641313e-05, + "loss": 3.6448, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784545353890261e-05, + "loss": 3.6392, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783706759139209e-05, + "loss": 3.6315, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.78286980226853e-05, + "loss": 3.6316, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782031207517478e-05, + "loss": 3.6243, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781192612766426e-05, + "loss": 3.643, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780354018015374e-05, + "loss": 3.6321, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779515423264322e-05, + "loss": 3.6528, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786768285132704e-05, + "loss": 3.6466, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778382337622184e-05, + "loss": 3.6484, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777001276891539e-05, + "loss": 3.6361, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776162682140487e-05, + "loss": 3.6316, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775324087389435e-05, + "loss": 3.643, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774485492638383e-05, + "loss": 3.6386, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773648535767704e-05, + "loss": 3.6316, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772809941016652e-05, + "loss": 3.6272, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719713462656e-05, + "loss": 3.6393, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771132751514548e-05, + "loss": 3.6328, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770294156763496e-05, + "loss": 3.6332, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769457199892817e-05, + "loss": 3.632, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768618605141765e-05, + "loss": 3.6378, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767780010390714e-05, + "loss": 3.6296, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766941415639662e-05, + "loss": 3.6435, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766104458768983e-05, + "loss": 3.6363, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765265864017931e-05, + "loss": 3.6522, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764427269266879e-05, + "loss": 3.6236, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763588674515827e-05, + "loss": 3.6435, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627517176451476e-05, + "loss": 3.634, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619131228940956e-05, + "loss": 3.6454, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610745281430436e-05, + "loss": 3.6387, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760235933391991e-05, + "loss": 3.6324, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759397338640939e-05, + "loss": 3.637, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585587438898876e-05, + "loss": 3.656, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757721787019209e-05, + "loss": 3.6242, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568831922681565e-05, + "loss": 3.6436, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7560445975171045e-05, + "loss": 3.6398, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7552060027660525e-05, + "loss": 3.6352, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543690458953734e-05, + "loss": 3.6313, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535304511443214e-05, + "loss": 3.6337, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526918563932694e-05, + "loss": 3.6391, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518532616422174e-05, + "loss": 3.6303, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751016304771538e-05, + "loss": 3.6343, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8460195064544678, + "eval_runtime": 303.7551, + "eval_samples_per_second": 1256.246, + "eval_steps_per_second": 39.259, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750177710020486e-05, + "loss": 3.6265, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749339115269434e-05, + "loss": 3.6267, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748500520518383e-05, + "loss": 3.6292, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747661925767331e-05, + "loss": 3.6421, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746823331016279e-05, + "loss": 3.6467, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459863741456e-05, + "loss": 3.6299, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745147779394548e-05, + "loss": 3.6303, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744309184643496e-05, + "loss": 3.6294, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743470589892444e-05, + "loss": 3.6261, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742633633021765e-05, + "loss": 3.6404, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741795038270713e-05, + "loss": 3.6274, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740956443519661e-05, + "loss": 3.6344, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740117848768609e-05, + "loss": 3.6375, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739279254017557e-05, + "loss": 3.6215, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738440659266505e-05, + "loss": 3.6224, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737603702395826e-05, + "loss": 3.62, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736765107644774e-05, + "loss": 3.6259, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735926512893722e-05, + "loss": 3.625, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.73508791814267e-05, + "loss": 3.6252, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734249323391618e-05, + "loss": 3.6348, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733410728640566e-05, + "loss": 3.6353, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732573771769887e-05, + "loss": 3.6385, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731735177018835e-05, + "loss": 3.6319, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730896582267783e-05, + "loss": 3.6242, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730057987516731e-05, + "loss": 3.6292, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729219392765679e-05, + "loss": 3.6347, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728382435895e-05, + "loss": 3.6259, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727543841143948e-05, + "loss": 3.6285, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726705246392897e-05, + "loss": 3.6208, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725866651641845e-05, + "loss": 3.6185, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250296947711657e-05, + "loss": 3.6232, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7241911000201137e-05, + "loss": 3.6341, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233525052690616e-05, + "loss": 3.6368, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7225139105180096e-05, + "loss": 3.63, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721675315766957e-05, + "loss": 3.6287, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720836721015905e-05, + "loss": 3.6239, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199997641452265e-05, + "loss": 3.6394, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191611693941745e-05, + "loss": 3.6194, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718322574643122e-05, + "loss": 3.618, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174839798920705e-05, + "loss": 3.6174, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716647023021392e-05, + "loss": 3.6234, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.71580842827034e-05, + "loss": 3.6255, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149698335192874e-05, + "loss": 3.6271, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141312387682354e-05, + "loss": 3.6265, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132926440171834e-05, + "loss": 3.6266, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124540492661314e-05, + "loss": 3.6238, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711617092395452e-05, + "loss": 3.6223, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107784976444e-05, + "loss": 3.6199, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709939902893348e-05, + "loss": 3.5989, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709101308142296e-05, + "loss": 3.6352, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708262713391244e-05, + "loss": 3.6175, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707425756520566e-05, + "loss": 3.6312, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706587161769514e-05, + "loss": 3.6208, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705748567018462e-05, + "loss": 3.6159, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.70490997226741e-05, + "loss": 3.6071, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704073015396731e-05, + "loss": 3.6198, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703234420645679e-05, + "loss": 3.6176, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702395825894627e-05, + "loss": 3.6132, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701557231143575e-05, + "loss": 3.6343, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700718636392523e-05, + "loss": 3.6183, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699881679521844e-05, + "loss": 3.6048, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699043084770792e-05, + "loss": 3.6297, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.69820449001974e-05, + "loss": 3.6155, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697365895268688e-05, + "loss": 3.6125, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696528938398009e-05, + "loss": 3.6247, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695690343646957e-05, + "loss": 3.6173, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694851748895905e-05, + "loss": 3.6087, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694013154144853e-05, + "loss": 3.6216, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693174559393801e-05, + "loss": 3.6092, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692335964642749e-05, + "loss": 3.6115, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691497369891697e-05, + "loss": 3.6239, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690660413021018e-05, + "loss": 3.6226, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689821818269966e-05, + "loss": 3.6245, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688983223518914e-05, + "loss": 3.6194, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688144628767862e-05, + "loss": 3.6419, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.68730603401681e-05, + "loss": 3.613, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686469077146131e-05, + "loss": 3.6258, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685630482395079e-05, + "loss": 3.6194, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684791887644028e-05, + "loss": 3.6169, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683953292892976e-05, + "loss": 3.615, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683114698141923e-05, + "loss": 3.6313, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822777412712446e-05, + "loss": 3.6219, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814391465201926e-05, + "loss": 3.6317, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806005517691406e-05, + "loss": 3.6063, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679761957018088e-05, + "loss": 3.6074, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678923362267036e-05, + "loss": 3.6218, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780864053963575e-05, + "loss": 3.6308, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772478106453055e-05, + "loss": 3.6165, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676409215894253e-05, + "loss": 3.6239, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755706211432015e-05, + "loss": 3.6132, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747320263921495e-05, + "loss": 3.6128, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738950695214704e-05, + "loss": 3.6169, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730564747704184e-05, + "loss": 3.6128, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722178800193664e-05, + "loss": 3.6243, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713792852683144e-05, + "loss": 3.6344, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670542328397635e-05, + "loss": 3.6294, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669703733646583e-05, + "loss": 3.6106, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668865138895531e-05, + "loss": 3.6087, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668026544144479e-05, + "loss": 3.6178, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667187949393427e-05, + "loss": 3.6228, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666350992522748e-05, + "loss": 3.6218, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665512397771697e-05, + "loss": 3.6216, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664673803020645e-05, + "loss": 3.6222, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663835208269593e-05, + "loss": 3.6107, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662998251398914e-05, + "loss": 3.616, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662159656647862e-05, + "loss": 3.6122, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.66132106189681e-05, + "loss": 3.6102, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660482467145758e-05, + "loss": 3.6216, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659643872394706e-05, + "loss": 3.6181, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658805277643654e-05, + "loss": 3.6079, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579683207729746e-05, + "loss": 3.6124, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571297260219226e-05, + "loss": 3.6017, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562911312708706e-05, + "loss": 3.6213, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6554525365198186e-05, + "loss": 3.6164, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.65461557964914e-05, + "loss": 3.6256, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653776984898088e-05, + "loss": 3.627, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652938390147036e-05, + "loss": 3.6281, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652101433276357e-05, + "loss": 3.6144, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651262838525305e-05, + "loss": 3.6125, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650424243774253e-05, + "loss": 3.618, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649585649023201e-05, + "loss": 3.6187, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648747054272149e-05, + "loss": 3.6109, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647908459521097e-05, + "loss": 3.6043, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647069864770045e-05, + "loss": 3.6184, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646231270018993e-05, + "loss": 3.6118, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645394313148314e-05, + "loss": 3.614, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644555718397262e-05, + "loss": 3.6078, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.64371712364621e-05, + "loss": 3.6201, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428785288951587e-05, + "loss": 3.6045, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420415720244796e-05, + "loss": 3.6252, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412029772734276e-05, + "loss": 3.6177, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403643825223756e-05, + "loss": 3.6292, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395257877713236e-05, + "loss": 3.6019, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386888309006445e-05, + "loss": 3.6213, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6378502361495925e-05, + "loss": 3.6213, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6370116413985405e-05, + "loss": 3.6199, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6361730466474884e-05, + "loss": 3.62, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635334451896436e-05, + "loss": 3.6113, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344974950257574e-05, + "loss": 3.6154, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336589002747053e-05, + "loss": 3.6316, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632820305523654e-05, + "loss": 3.6069, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319817107726013e-05, + "loss": 3.6182, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631144753901923e-05, + "loss": 3.6197, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630306159150871e-05, + "loss": 3.6127, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629467564399819e-05, + "loss": 3.6128, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628628969648766e-05, + "loss": 3.6144, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627792012778088e-05, + "loss": 3.6159, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626953418027036e-05, + "loss": 3.6159, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626114823275983e-05, + "loss": 3.61, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8442649841308594, + "eval_runtime": 302.6112, + "eval_samples_per_second": 1260.994, + "eval_steps_per_second": 39.407, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625276228524931e-05, + "loss": 3.6093, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624439271654253e-05, + "loss": 3.6032, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623600676903201e-05, + "loss": 3.6083, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622762082152149e-05, + "loss": 3.6183, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621923487401097e-05, + "loss": 3.6244, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621086530530418e-05, + "loss": 3.6119, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620247935779366e-05, + "loss": 3.6099, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194093410283136e-05, + "loss": 3.611, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185707462772616e-05, + "loss": 3.6033, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177321515262096e-05, + "loss": 3.6188, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6168951946555305e-05, + "loss": 3.6069, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160565999044785e-05, + "loss": 3.6154, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152180051534265e-05, + "loss": 3.6141, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6143794104023745e-05, + "loss": 3.5989, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613542453531696e-05, + "loss": 3.6042, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612703858780644e-05, + "loss": 3.5948, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611865264029592e-05, + "loss": 3.6111, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.61102666927854e-05, + "loss": 3.6074, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610188074527488e-05, + "loss": 3.6023, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609349479776436e-05, + "loss": 3.6123, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608510885025384e-05, + "loss": 3.6165, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607673928154705e-05, + "loss": 3.6186, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606835333403653e-05, + "loss": 3.6115, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605996738652601e-05, + "loss": 3.6064, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605158143901549e-05, + "loss": 3.6079, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.60432118703087e-05, + "loss": 3.6117, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034825922798185e-05, + "loss": 3.6024, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026439975287665e-05, + "loss": 3.6078, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6018054027777145e-05, + "loss": 3.6038, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009668080266625e-05, + "loss": 3.5995, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001298511559834e-05, + "loss": 3.6049, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992912564049314e-05, + "loss": 3.6122, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5984526616538794e-05, + "loss": 3.6071, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5976140669028274e-05, + "loss": 3.6191, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596777110032148e-05, + "loss": 3.6021, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595938515281096e-05, + "loss": 3.6068, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595099920530044e-05, + "loss": 3.6186, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594261325778992e-05, + "loss": 3.5958, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593424368908314e-05, + "loss": 3.5998, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592585774157262e-05, + "loss": 3.5977, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.59174717940621e-05, + "loss": 3.6046, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590908584655158e-05, + "loss": 3.6023, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590069989904106e-05, + "loss": 3.6067, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589233033033427e-05, + "loss": 3.6078, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588394438282375e-05, + "loss": 3.6042, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587555843531323e-05, + "loss": 3.6087, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586718886660644e-05, + "loss": 3.5983, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585880291909592e-05, + "loss": 3.6005, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.58504169715854e-05, + "loss": 3.577, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584203102407488e-05, + "loss": 3.6148, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583364507656436e-05, + "loss": 3.5973, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582527550785757e-05, + "loss": 3.6081, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581688956034705e-05, + "loss": 3.6019, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580850361283653e-05, + "loss": 3.5949, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580011766532601e-05, + "loss": 3.5888, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579174809661922e-05, + "loss": 3.5984, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.57833621491087e-05, + "loss": 3.6032, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577497620159818e-05, + "loss": 3.5915, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576659025408766e-05, + "loss": 3.613, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575822068538087e-05, + "loss": 3.6016, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574983473787035e-05, + "loss": 3.5826, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574144879035983e-05, + "loss": 3.6086, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573306284284931e-05, + "loss": 3.5994, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572467689533879e-05, + "loss": 3.5931, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716307326632006e-05, + "loss": 3.6014, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707921379121486e-05, + "loss": 3.5998, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5699535431610966e-05, + "loss": 3.5884, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569114948410044e-05, + "loss": 3.6029, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5682779915393655e-05, + "loss": 3.5893, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.5674393967883135e-05, + "loss": 3.5879, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5666008020372615e-05, + "loss": 3.6075, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565762207286209e-05, + "loss": 3.6, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649252504155304e-05, + "loss": 3.6053, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640866556644784e-05, + "loss": 3.6029, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632480609134264e-05, + "loss": 3.6143, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624094661623744e-05, + "loss": 3.5968, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561572509291696e-05, + "loss": 3.6079, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560733914540644e-05, + "loss": 3.5969, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559895319789591e-05, + "loss": 3.5992, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559056725038539e-05, + "loss": 3.5958, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558219768167861e-05, + "loss": 3.6097, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557381173416809e-05, + "loss": 3.6023, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556542578665756e-05, + "loss": 3.6131, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555703983914704e-05, + "loss": 3.5857, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554865389163652e-05, + "loss": 3.5871, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554028432292974e-05, + "loss": 3.603, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553189837541922e-05, + "loss": 3.6074, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.55235124279087e-05, + "loss": 3.5967, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551512648039818e-05, + "loss": 3.6067, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550675691169139e-05, + "loss": 3.5954, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549837096418087e-05, + "loss": 3.5899, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548998501667035e-05, + "loss": 3.5972, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548159906915983e-05, + "loss": 3.5952, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473229500453036e-05, + "loss": 3.6069, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464843552942516e-05, + "loss": 3.6108, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456457605431996e-05, + "loss": 3.6151, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448071657921476e-05, + "loss": 3.5876, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439685710410956e-05, + "loss": 3.5949, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543131614170417e-05, + "loss": 3.5988, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542293019419365e-05, + "loss": 3.6038, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541454424668313e-05, + "loss": 3.5992, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540615829917261e-05, + "loss": 3.6049, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539778873046582e-05, + "loss": 3.5989, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.53894027829553e-05, + "loss": 3.5931, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538101683544478e-05, + "loss": 3.597, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537263088793426e-05, + "loss": 3.587, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536426131922747e-05, + "loss": 3.5938, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535587537171695e-05, + "loss": 3.5981, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534748942420643e-05, + "loss": 3.6014, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533910347669591e-05, + "loss": 3.5865, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330733907989125e-05, + "loss": 3.596, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322347960478605e-05, + "loss": 3.5794, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313962012968085e-05, + "loss": 3.6079, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305576065457565e-05, + "loss": 3.5925, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5297206496750774e-05, + "loss": 3.6075, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5288820549240254e-05, + "loss": 3.6048, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280434601729734e-05, + "loss": 3.6062, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527206503302294e-05, + "loss": 3.5959, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526367908551242e-05, + "loss": 3.5923, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52552931380019e-05, + "loss": 3.6041, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524690719049138e-05, + "loss": 3.5976, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523852124298086e-05, + "loss": 3.594, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523013529547034e-05, + "loss": 3.5868, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522174934795982e-05, + "loss": 3.596, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521336340044931e-05, + "loss": 3.5919, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520499383174252e-05, + "loss": 3.5954, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196607884232e-05, + "loss": 3.5883, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518822193672148e-05, + "loss": 3.6006, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517983598921096e-05, + "loss": 3.5852, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517146642050417e-05, + "loss": 3.6057, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516308047299365e-05, + "loss": 3.5962, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515469452548313e-05, + "loss": 3.6119, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514630857797261e-05, + "loss": 3.5851, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137939009265817e-05, + "loss": 3.6022, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129553061755297e-05, + "loss": 3.5992, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121167114244776e-05, + "loss": 3.5989, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511278116673426e-05, + "loss": 3.6007, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510439521922374e-05, + "loss": 3.593, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509602565051695e-05, + "loss": 3.5975, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508763970300643e-05, + "loss": 3.6105, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507925375549591e-05, + "loss": 3.5904, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507086780798539e-05, + "loss": 3.6003, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.50624982392786e-05, + "loss": 3.5986, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505411229176808e-05, + "loss": 3.5966, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504572634425756e-05, + "loss": 3.5966, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503734039674704e-05, + "loss": 3.5915, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502897082804025e-05, + "loss": 3.5973, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502058488052973e-05, + "loss": 3.5959, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501219893301922e-05, + "loss": 3.5902, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.843705654144287, + "eval_runtime": 302.5756, + "eval_samples_per_second": 1261.143, + "eval_steps_per_second": 39.412, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.50038129855087e-05, + "loss": 3.6002, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499542703799817e-05, + "loss": 3.5802, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498704109048765e-05, + "loss": 3.5899, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497865514297713e-05, + "loss": 3.6012, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970285574270346e-05, + "loss": 3.6019, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496189962675982e-05, + "loss": 3.5941, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.49535136792493e-05, + "loss": 3.5968, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494512773173878e-05, + "loss": 3.5895, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493675816303199e-05, + "loss": 3.5836, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492837221552147e-05, + "loss": 3.5946, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4919986268010955e-05, + "loss": 3.5944, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911600320500435e-05, + "loss": 3.594, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903230751793644e-05, + "loss": 3.5955, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894844804283124e-05, + "loss": 3.579, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886458856772604e-05, + "loss": 3.587, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878072909262084e-05, + "loss": 3.5771, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869686961751564e-05, + "loss": 3.5919, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486131739304477e-05, + "loss": 3.5894, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485293144553425e-05, + "loss": 3.5833, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484454549802373e-05, + "loss": 3.5932, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483615955051321e-05, + "loss": 3.5962, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482778998180642e-05, + "loss": 3.5991, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.48194040342959e-05, + "loss": 3.5934, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481101808678539e-05, + "loss": 3.5869, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480263213927487e-05, + "loss": 3.5933, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479426257056808e-05, + "loss": 3.5922, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478587662305756e-05, + "loss": 3.5859, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477749067554704e-05, + "loss": 3.5884, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476910472803652e-05, + "loss": 3.5818, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760735159329726e-05, + "loss": 3.5787, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752349211819206e-05, + "loss": 3.5872, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743963264308686e-05, + "loss": 3.5923, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735577316798166e-05, + "loss": 3.5895, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727207748091375e-05, + "loss": 3.5983, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718821800580855e-05, + "loss": 3.5858, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471043585307034e-05, + "loss": 3.5904, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470204990555982e-05, + "loss": 3.5975, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469368033685303e-05, + "loss": 3.5777, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468529438934251e-05, + "loss": 3.5788, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467690844183199e-05, + "loss": 3.585, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466852249432147e-05, + "loss": 3.5816, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466013654681095e-05, + "loss": 3.5823, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465176697810416e-05, + "loss": 3.5897, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464338103059364e-05, + "loss": 3.5884, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463499508308312e-05, + "loss": 3.5832, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.46266091355726e-05, + "loss": 3.5925, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461823956686581e-05, + "loss": 3.5825, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609853619355296e-05, + "loss": 3.5829, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601467671844776e-05, + "loss": 3.5604, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593081724334256e-05, + "loss": 3.596, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584695776823735e-05, + "loss": 3.5787, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576326208116945e-05, + "loss": 3.589, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4567940260606425e-05, + "loss": 3.5817, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559554313095904e-05, + "loss": 3.5768, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551168365585384e-05, + "loss": 3.5702, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4542798796878594e-05, + "loss": 3.5801, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534412849368073e-05, + "loss": 3.5889, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526026901857553e-05, + "loss": 3.5713, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517640954347033e-05, + "loss": 3.5954, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450927138564025e-05, + "loss": 3.5845, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450088543812973e-05, + "loss": 3.564, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449249949061921e-05, + "loss": 3.5918, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448411354310869e-05, + "loss": 3.5762, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.44757439744019e-05, + "loss": 3.577, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446735802689138e-05, + "loss": 3.5784, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445897207938086e-05, + "loss": 3.5833, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445058613187034e-05, + "loss": 3.5737, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444220018435982e-05, + "loss": 3.5868, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443383061565303e-05, + "loss": 3.5698, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442544466814251e-05, + "loss": 3.5726, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441705872063199e-05, + "loss": 3.5851, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440867277312147e-05, + "loss": 3.582, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440030320441468e-05, + "loss": 3.5879, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439191725690416e-05, + "loss": 3.5812, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438353130939364e-05, + "loss": 3.6002, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437514536188312e-05, + "loss": 3.5788, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436677579317633e-05, + "loss": 3.5913, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435838984566581e-05, + "loss": 3.5775, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435000389815529e-05, + "loss": 3.5818, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434161795064477e-05, + "loss": 3.5757, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4333232003134245e-05, + "loss": 3.5891, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432486243442746e-05, + "loss": 3.5864, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431647648691694e-05, + "loss": 3.5949, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430809053940642e-05, + "loss": 3.5746, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.42997045918959e-05, + "loss": 3.5704, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291335023189117e-05, + "loss": 3.5813, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282949075678596e-05, + "loss": 3.5893, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427456312816807e-05, + "loss": 3.5788, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426617718065755e-05, + "loss": 3.589, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4257807611950765e-05, + "loss": 3.5781, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249421664440245e-05, + "loss": 3.5737, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424103571692972e-05, + "loss": 3.5798, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.42326497694192e-05, + "loss": 3.5747, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224280200712414e-05, + "loss": 3.5878, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4215894253201894e-05, + "loss": 3.5964, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207508305691374e-05, + "loss": 3.594, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199122358180854e-05, + "loss": 3.5717, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419075278947407e-05, + "loss": 3.5762, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418236684196354e-05, + "loss": 3.5815, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417398089445302e-05, + "loss": 3.585, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.41655949469425e-05, + "loss": 3.5855, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415722537823572e-05, + "loss": 3.5853, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414883943072519e-05, + "loss": 3.5809, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414045348321467e-05, + "loss": 3.5758, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413206753570415e-05, + "loss": 3.5847, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412369796699737e-05, + "loss": 3.5667, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411531201948685e-05, + "loss": 3.5741, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410692607197633e-05, + "loss": 3.5791, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409854012446581e-05, + "loss": 3.5814, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409015417695529e-05, + "loss": 3.5705, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.40817846082485e-05, + "loss": 3.581, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407339866073798e-05, + "loss": 3.5586, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406501271322746e-05, + "loss": 3.584, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405662676571694e-05, + "loss": 3.5806, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048257197010146e-05, + "loss": 3.5829, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4039871249499626e-05, + "loss": 3.5892, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031485301989106e-05, + "loss": 3.5916, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4023115733282315e-05, + "loss": 3.5776, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.40147297857718e-05, + "loss": 3.5759, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400634383826128e-05, + "loss": 3.5825, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399795789075076e-05, + "loss": 3.5781, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398957194324024e-05, + "loss": 3.5744, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398118599572972e-05, + "loss": 3.5734, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.39728000482192e-05, + "loss": 3.5764, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396441410070868e-05, + "loss": 3.5759, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395604453200189e-05, + "loss": 3.5746, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394765858449137e-05, + "loss": 3.5737, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393927263698085e-05, + "loss": 3.5803, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393088668947033e-05, + "loss": 3.5663, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392251712076354e-05, + "loss": 3.5889, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391413117325302e-05, + "loss": 3.5793, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.39057452257425e-05, + "loss": 3.5946, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389735927823198e-05, + "loss": 3.5632, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888989709525195e-05, + "loss": 3.5873, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880603762014675e-05, + "loss": 3.583, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872217814504155e-05, + "loss": 3.5782, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3863831866993635e-05, + "loss": 3.5818, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855462298286844e-05, + "loss": 3.5759, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3847076350776324e-05, + "loss": 3.5858, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838690403265804e-05, + "loss": 3.5877, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830304455755284e-05, + "loss": 3.572, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3821918508244764e-05, + "loss": 3.583, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381354893953797e-05, + "loss": 3.5817, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380516299202745e-05, + "loss": 3.5765, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379677704451693e-05, + "loss": 3.5759, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378839109700642e-05, + "loss": 3.5815, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378002152829963e-05, + "loss": 3.5746, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377163558078911e-05, + "loss": 3.581, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376324963327859e-05, + "loss": 3.571, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.842909812927246, + "eval_runtime": 315.0277, + "eval_samples_per_second": 1211.294, + "eval_steps_per_second": 37.854, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375486368576807e-05, + "loss": 3.5793, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374649411706128e-05, + "loss": 3.5654, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373810816955076e-05, + "loss": 3.5705, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372972222204024e-05, + "loss": 3.5882, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372133627452972e-05, + "loss": 3.5815, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371296670582293e-05, + "loss": 3.5792, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370458075831241e-05, + "loss": 3.5772, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369619481080189e-05, + "loss": 3.57, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3687808863291373e-05, + "loss": 3.5649, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367943929458458e-05, + "loss": 3.5838, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367105334707406e-05, + "loss": 3.5746, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366266739956354e-05, + "loss": 3.5763, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365428145205302e-05, + "loss": 3.5815, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364591188334623e-05, + "loss": 3.5622, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363752593583571e-05, + "loss": 3.5666, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362913998832519e-05, + "loss": 3.5612, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362075404081467e-05, + "loss": 3.575, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361238447210788e-05, + "loss": 3.568, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360399852459736e-05, + "loss": 3.5666, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359561257708684e-05, + "loss": 3.5709, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358722662957633e-05, + "loss": 3.5813, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3578857060869536e-05, + "loss": 3.5781, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3570471113359016e-05, + "loss": 3.5777, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3562085165848496e-05, + "loss": 3.5714, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3553699218337976e-05, + "loss": 3.5751, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3545329649631185e-05, + "loss": 3.5708, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3536943702120665e-05, + "loss": 3.571, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528557754610145e-05, + "loss": 3.5739, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352017180709962e-05, + "loss": 3.5636, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3511802238392834e-05, + "loss": 3.5618, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3503416290882314e-05, + "loss": 3.5694, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3495030343371794e-05, + "loss": 3.5721, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486644395861274e-05, + "loss": 3.5788, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347827482715449e-05, + "loss": 3.5782, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346988887964397e-05, + "loss": 3.5678, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346150293213345e-05, + "loss": 3.5759, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345311698462292e-05, + "loss": 3.5829, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344474741591614e-05, + "loss": 3.554, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343636146840562e-05, + "loss": 3.5652, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342797552089509e-05, + "loss": 3.567, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341958957338457e-05, + "loss": 3.5654, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341122000467779e-05, + "loss": 3.566, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340283405716727e-05, + "loss": 3.5734, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339444810965675e-05, + "loss": 3.5754, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338606216214623e-05, + "loss": 3.5635, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3377692593439444e-05, + "loss": 3.5711, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3369306645928924e-05, + "loss": 3.5663, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.33609206984184e-05, + "loss": 3.5628, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335253475090788e-05, + "loss": 3.5476, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334416518220109e-05, + "loss": 3.576, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3335779234690566e-05, + "loss": 3.5621, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3327393287180046e-05, + "loss": 3.5726, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3319007339669526e-05, + "loss": 3.5642, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331063777096274e-05, + "loss": 3.5579, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330225182345222e-05, + "loss": 3.5538, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.32938658759417e-05, + "loss": 3.5623, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328547992843118e-05, + "loss": 3.5728, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.32771103597244e-05, + "loss": 3.5507, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326872441221387e-05, + "loss": 3.5801, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326033846470335e-05, + "loss": 3.5673, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325195251719283e-05, + "loss": 3.5477, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324358294848604e-05, + "loss": 3.574, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323519700097552e-05, + "loss": 3.559, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3226811053465e-05, + "loss": 3.5639, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321842510595448e-05, + "loss": 3.5561, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3210055537247695e-05, + "loss": 3.5699, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3201669589737175e-05, + "loss": 3.554, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193283642226655e-05, + "loss": 3.5706, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3184897694716135e-05, + "loss": 3.5501, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176528126009344e-05, + "loss": 3.5593, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3168142178498824e-05, + "loss": 3.5651, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3159756230988304e-05, + "loss": 3.572, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3151370283477784e-05, + "loss": 3.5673, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314300071477099e-05, + "loss": 3.5671, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313461476726047e-05, + "loss": 3.5826, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312622881974995e-05, + "loss": 3.5603, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311784287223943e-05, + "loss": 3.5727, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310947330353264e-05, + "loss": 3.5645, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310108735602213e-05, + "loss": 3.5652, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309270140851161e-05, + "loss": 3.5636, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308431546100109e-05, + "loss": 3.5682, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.30759458922943e-05, + "loss": 3.5699, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306755994478378e-05, + "loss": 3.5754, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305917399727326e-05, + "loss": 3.5623, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305078804976274e-05, + "loss": 3.5516, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304241848105595e-05, + "loss": 3.5628, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303403253354543e-05, + "loss": 3.5701, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302564658603491e-05, + "loss": 3.5641, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301726063852439e-05, + "loss": 3.5713, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3008891069817596e-05, + "loss": 3.5614, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300050512230708e-05, + "loss": 3.5555, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299211917479656e-05, + "loss": 3.5636, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298373322728604e-05, + "loss": 3.5597, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297536365857925e-05, + "loss": 3.5747, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296697771106873e-05, + "loss": 3.5715, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295859176355821e-05, + "loss": 3.5786, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295020581604769e-05, + "loss": 3.5559, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294181986853717e-05, + "loss": 3.5609, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293345029983038e-05, + "loss": 3.5641, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292506435231986e-05, + "loss": 3.5665, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291667840480934e-05, + "loss": 3.5738, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290829245729882e-05, + "loss": 3.5648, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2899922888592036e-05, + "loss": 3.5648, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891536941081516e-05, + "loss": 3.5591, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2883150993570996e-05, + "loss": 3.5715, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2874765046060476e-05, + "loss": 3.5488, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866395477353685e-05, + "loss": 3.5569, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.2858009529843165e-05, + "loss": 3.5654, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2849623582332645e-05, + "loss": 3.5665, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2841237634822125e-05, + "loss": 3.5552, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2832868066115334e-05, + "loss": 3.5633, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824482118604814e-05, + "loss": 3.5443, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2816096171094294e-05, + "loss": 3.5704, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2807710223583774e-05, + "loss": 3.5594, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279934065487699e-05, + "loss": 3.5649, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279095470736647e-05, + "loss": 3.5752, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278256875985595e-05, + "loss": 3.5729, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277419919114916e-05, + "loss": 3.5602, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276581324363864e-05, + "loss": 3.5635, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275742729612812e-05, + "loss": 3.567, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.27490413486176e-05, + "loss": 3.5583, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274065540110708e-05, + "loss": 3.5619, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273226945359656e-05, + "loss": 3.5528, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272388350608604e-05, + "loss": 3.5626, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271549755857552e-05, + "loss": 3.5564, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270712798986873e-05, + "loss": 3.5571, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269874204235821e-05, + "loss": 3.5601, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269035609484769e-05, + "loss": 3.5624, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2681970147337174e-05, + "loss": 3.5517, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267360057863038e-05, + "loss": 3.5734, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266521463111986e-05, + "loss": 3.5632, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265682868360934e-05, + "loss": 3.5757, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264844273609882e-05, + "loss": 3.5552, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264007316739203e-05, + "loss": 3.5661, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263168721988151e-05, + "loss": 3.567, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262330127237099e-05, + "loss": 3.5649, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261491532486047e-05, + "loss": 3.561, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260654575615368e-05, + "loss": 3.5617, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259815980864316e-05, + "loss": 3.567, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258977386113264e-05, + "loss": 3.5727, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258138791362212e-05, + "loss": 3.5608, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257301834491534e-05, + "loss": 3.5611, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256463239740482e-05, + "loss": 3.5675, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.25562464498943e-05, + "loss": 3.5618, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254786050238377e-05, + "loss": 3.5575, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539490933676986e-05, + "loss": 3.5668, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531104986166466e-05, + "loss": 3.5596, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252271903865594e-05, + "loss": 3.5656, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251433309114542e-05, + "loss": 3.5525, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8434338569641113, + "eval_runtime": 313.7173, + "eval_samples_per_second": 1216.353, + "eval_steps_per_second": 38.012, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2505963522438635e-05, + "loss": 3.5705, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497577574928115e-05, + "loss": 3.5512, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489191627417595e-05, + "loss": 3.5545, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480805679907075e-05, + "loss": 3.5689, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247243611120029e-05, + "loss": 3.5676, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246405016368977e-05, + "loss": 3.5613, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2455664216179244e-05, + "loss": 3.5572, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2447278268668724e-05, + "loss": 3.5539, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243890869996194e-05, + "loss": 3.5503, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243052275245141e-05, + "loss": 3.5684, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242213680494089e-05, + "loss": 3.5574, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241375085743037e-05, + "loss": 3.5616, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240538128872359e-05, + "loss": 3.5609, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239699534121307e-05, + "loss": 3.5498, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238860939370255e-05, + "loss": 3.5512, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238022344619203e-05, + "loss": 3.5439, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237183749868151e-05, + "loss": 3.5583, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236346792997472e-05, + "loss": 3.5493, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.23550819824642e-05, + "loss": 3.5538, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234669603495368e-05, + "loss": 3.5534, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233831008744316e-05, + "loss": 3.5647, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2329940518736366e-05, + "loss": 3.5638, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321554571225846e-05, + "loss": 3.5625, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313168623715326e-05, + "loss": 3.5549, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304782676204806e-05, + "loss": 3.5643, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229641310749802e-05, + "loss": 3.5527, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.22880271599875e-05, + "loss": 3.5515, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227964121247698e-05, + "loss": 3.5633, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227125526496646e-05, + "loss": 3.5435, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226288569625967e-05, + "loss": 3.5457, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225449974874915e-05, + "loss": 3.553, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224611380123863e-05, + "loss": 3.5535, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223772785372811e-05, + "loss": 3.5633, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222935828502132e-05, + "loss": 3.5641, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.22209723375108e-05, + "loss": 3.547, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221258639000028e-05, + "loss": 3.5637, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220420044248976e-05, + "loss": 3.5627, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2195830873782976e-05, + "loss": 3.5434, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187444926272456e-05, + "loss": 3.5483, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2179058978761936e-05, + "loss": 3.5504, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170673031251416e-05, + "loss": 3.546, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162303462544625e-05, + "loss": 3.5531, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2153917515034105e-05, + "loss": 3.5618, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145531567523585e-05, + "loss": 3.5532, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2137145620013065e-05, + "loss": 3.5479, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2128776051306274e-05, + "loss": 3.5592, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120390103795754e-05, + "loss": 3.5492, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2112004156285234e-05, + "loss": 3.5474, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103618208774714e-05, + "loss": 3.5295, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209524864006793e-05, + "loss": 3.5595, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208686269255741e-05, + "loss": 3.5489, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207847674504689e-05, + "loss": 3.5592, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207009079753637e-05, + "loss": 3.5465, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206172122882958e-05, + "loss": 3.5406, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205333528131906e-05, + "loss": 3.5401, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204494933380854e-05, + "loss": 3.5447, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203656338629802e-05, + "loss": 3.5555, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.20281774387875e-05, + "loss": 3.5364, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201980787008071e-05, + "loss": 3.5634, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201142192257019e-05, + "loss": 3.5502, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200303597505967e-05, + "loss": 3.5378, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199465002754915e-05, + "loss": 3.5575, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198628045884236e-05, + "loss": 3.5423, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197789451133184e-05, + "loss": 3.5468, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196950856382132e-05, + "loss": 3.5388, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.19611226163108e-05, + "loss": 3.5547, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195275304760401e-05, + "loss": 3.5423, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194436710009349e-05, + "loss": 3.5464, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193598115258297e-05, + "loss": 3.5425, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192759520507245e-05, + "loss": 3.5417, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191922563636566e-05, + "loss": 3.5484, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191083968885514e-05, + "loss": 3.5624, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190245374134462e-05, + "loss": 3.5475, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.18940677938341e-05, + "loss": 3.5484, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188569822512732e-05, + "loss": 3.5659, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.18773122776168e-05, + "loss": 3.5448, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186892633010628e-05, + "loss": 3.5526, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186054038259576e-05, + "loss": 3.5516, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852170813888966e-05, + "loss": 3.5521, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1843784866378446e-05, + "loss": 3.5453, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835398918867926e-05, + "loss": 3.5506, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1827012971357406e-05, + "loss": 3.5543, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818643402650615e-05, + "loss": 3.562, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810257455140095e-05, + "loss": 3.5482, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801871507629575e-05, + "loss": 3.5338, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793485560119055e-05, + "loss": 3.5471, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178511599141227e-05, + "loss": 3.5571, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177673004390175e-05, + "loss": 3.5514, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176834409639123e-05, + "loss": 3.5535, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175995814888071e-05, + "loss": 3.5438, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175158858017392e-05, + "loss": 3.5414, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.17432026326634e-05, + "loss": 3.5448, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173481668515288e-05, + "loss": 3.5451, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172643073764236e-05, + "loss": 3.555, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171806116893557e-05, + "loss": 3.5553, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170967522142505e-05, + "loss": 3.5682, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170128927391453e-05, + "loss": 3.5395, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169290332640401e-05, + "loss": 3.5453, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684533757697224e-05, + "loss": 3.55, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676147810186704e-05, + "loss": 3.5514, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1667761862676184e-05, + "loss": 3.5541, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1659375915165664e-05, + "loss": 3.5518, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165100634645887e-05, + "loss": 3.5495, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164262039894835e-05, + "loss": 3.5399, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163423445143783e-05, + "loss": 3.5547, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162584850392731e-05, + "loss": 3.5299, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161747893522052e-05, + "loss": 3.5416, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160909298771e-05, + "loss": 3.55, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160070704019948e-05, + "loss": 3.5521, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159232109268896e-05, + "loss": 3.5412, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158395152398218e-05, + "loss": 3.5431, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157556557647166e-05, + "loss": 3.5376, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156717962896114e-05, + "loss": 3.5471, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155879368145062e-05, + "loss": 3.5449, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155042411274383e-05, + "loss": 3.5535, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154203816523331e-05, + "loss": 3.5607, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153365221772279e-05, + "loss": 3.5567, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525282649015996e-05, + "loss": 3.5424, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516896701505476e-05, + "loss": 3.5467, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508510753994956e-05, + "loss": 3.5534, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500124806484436e-05, + "loss": 3.5468, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491738858973916e-05, + "loss": 3.5429, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483352911463396e-05, + "loss": 3.5426, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1474966963952876e-05, + "loss": 3.5424, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466581016442355e-05, + "loss": 3.5432, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458211447735565e-05, + "loss": 3.5387, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1449825500225045e-05, + "loss": 3.5451, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441439552714524e-05, + "loss": 3.5469, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1433053605204004e-05, + "loss": 3.5362, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424684036497214e-05, + "loss": 3.5519, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416298088986694e-05, + "loss": 3.5522, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1407912141476173e-05, + "loss": 3.5575, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399526193965653e-05, + "loss": 3.5457, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139115662525887e-05, + "loss": 3.5464, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138277067774835e-05, + "loss": 3.5547, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137438473023783e-05, + "loss": 3.5441, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136599878272731e-05, + "loss": 3.5491, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135762921402052e-05, + "loss": 3.5454, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134924326651e-05, + "loss": 3.5527, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134085731899948e-05, + "loss": 3.5533, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133247137148896e-05, + "loss": 3.5465, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132410180278217e-05, + "loss": 3.5466, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131571585527165e-05, + "loss": 3.5513, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130732990776113e-05, + "loss": 3.5443, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129894396025061e-05, + "loss": 3.5445, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129057439154382e-05, + "loss": 3.5518, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.12821884440333e-05, + "loss": 3.541, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127380249652278e-05, + "loss": 3.5579, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126541654901226e-05, + "loss": 3.5337, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8454809188842773, + "eval_runtime": 311.2004, + "eval_samples_per_second": 1226.191, + "eval_steps_per_second": 38.319, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125704698030547e-05, + "loss": 3.5413, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124866103279495e-05, + "loss": 3.5407, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124027508528443e-05, + "loss": 3.5383, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123188913777391e-05, + "loss": 3.5525, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122351956906712e-05, + "loss": 3.5525, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.12151336215566e-05, + "loss": 3.5496, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120674767404608e-05, + "loss": 3.5384, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119836172653556e-05, + "loss": 3.5388, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118999215782878e-05, + "loss": 3.5383, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1181606210318257e-05, + "loss": 3.5501, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1173220262807737e-05, + "loss": 3.541, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1164834315297216e-05, + "loss": 3.546, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156464746590426e-05, + "loss": 3.5459, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1148078799079906e-05, + "loss": 3.5326, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1139692851569385e-05, + "loss": 3.5357, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1131306904058865e-05, + "loss": 3.5287, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1122937335352075e-05, + "loss": 3.5432, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114551387841555e-05, + "loss": 3.536, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106165440331034e-05, + "loss": 3.5385, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1097779492820514e-05, + "loss": 3.539, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1089393545309994e-05, + "loss": 3.5505, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108102397660321e-05, + "loss": 3.5471, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107263802909269e-05, + "loss": 3.5433, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106425208158217e-05, + "loss": 3.5434, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105586613407165e-05, + "loss": 3.5477, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104749656536486e-05, + "loss": 3.5418, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103911061785434e-05, + "loss": 3.535, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103072467034382e-05, + "loss": 3.5452, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.10223387228333e-05, + "loss": 3.5282, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101396915412651e-05, + "loss": 3.5288, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100558320661599e-05, + "loss": 3.5369, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099719725910547e-05, + "loss": 3.5413, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098881131159495e-05, + "loss": 3.5452, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980441742888164e-05, + "loss": 3.5452, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972055795377644e-05, + "loss": 3.5378, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963669847867124e-05, + "loss": 3.545, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955283900356604e-05, + "loss": 3.5486, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094691433164981e-05, + "loss": 3.5273, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093852838413929e-05, + "loss": 3.5386, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093014243662877e-05, + "loss": 3.5274, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092175648911825e-05, + "loss": 3.5343, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091338692041146e-05, + "loss": 3.5371, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090500097290094e-05, + "loss": 3.5453, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089661502539042e-05, + "loss": 3.5378, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.08882290778799e-05, + "loss": 3.533, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087985950917312e-05, + "loss": 3.5452, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.08714735616626e-05, + "loss": 3.5358, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086308761415208e-05, + "loss": 3.5312, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085470166664156e-05, + "loss": 3.5155, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0846332097934767e-05, + "loss": 3.5441, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0837946150424246e-05, + "loss": 3.5368, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829560202913726e-05, + "loss": 3.5416, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0821174255403206e-05, + "loss": 3.5329, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0812804686696416e-05, + "loss": 3.5285, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804418739185895e-05, + "loss": 3.5234, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0796032791675375e-05, + "loss": 3.5249, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787646844164855e-05, + "loss": 3.5433, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077927727545807e-05, + "loss": 3.5257, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077089132794755e-05, + "loss": 3.5415, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076250538043703e-05, + "loss": 3.5343, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075411943292651e-05, + "loss": 3.5258, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074574986421972e-05, + "loss": 3.5408, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.07373639167092e-05, + "loss": 3.5297, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072897796919868e-05, + "loss": 3.5306, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072059202168816e-05, + "loss": 3.5252, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071222245298137e-05, + "loss": 3.5402, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070383650547085e-05, + "loss": 3.5286, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069545055796033e-05, + "loss": 3.5321, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068706461044981e-05, + "loss": 3.5247, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0678695041743025e-05, + "loss": 3.5304, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670309094232505e-05, + "loss": 3.5313, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0661923146721985e-05, + "loss": 3.5445, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653537199211465e-05, + "loss": 3.5314, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645167630504674e-05, + "loss": 3.5372, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636781682994154e-05, + "loss": 3.547, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628395735483634e-05, + "loss": 3.5369, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620009787973114e-05, + "loss": 3.5337, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061164021926632e-05, + "loss": 3.54, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.06032542717558e-05, + "loss": 3.5381, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059486832424528e-05, + "loss": 3.5339, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058648237673476e-05, + "loss": 3.5346, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057811280802798e-05, + "loss": 3.5431, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056972686051746e-05, + "loss": 3.5454, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056134091300694e-05, + "loss": 3.5337, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055295496549641e-05, + "loss": 3.5161, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054458539678963e-05, + "loss": 3.5301, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053619944927911e-05, + "loss": 3.5418, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052781350176859e-05, + "loss": 3.5373, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051942755425806e-05, + "loss": 3.54, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511057985551277e-05, + "loss": 3.5334, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050267203804076e-05, + "loss": 3.5274, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494286090530233e-05, + "loss": 3.5268, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485900143019713e-05, + "loss": 3.5294, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.047753057431293e-05, + "loss": 3.5409, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046914462680241e-05, + "loss": 3.5375, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460758679291885e-05, + "loss": 3.552, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452372731781365e-05, + "loss": 3.5305, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044400316307458e-05, + "loss": 3.5301, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043561721556406e-05, + "loss": 3.5348, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427231268053534e-05, + "loss": 3.5361, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418845320543014e-05, + "loss": 3.5407, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.041047575183623e-05, + "loss": 3.5356, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402089804325707e-05, + "loss": 3.5339, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393703856815187e-05, + "loss": 3.5265, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385317909304667e-05, + "loss": 3.5416, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376948340597883e-05, + "loss": 3.5183, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036856239308736e-05, + "loss": 3.5282, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036017644557684e-05, + "loss": 3.5348, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035179049806632e-05, + "loss": 3.5336, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343420929359535e-05, + "loss": 3.5243, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335034981849008e-05, + "loss": 3.5348, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326649034338488e-05, + "loss": 3.5184, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318263086827968e-05, + "loss": 3.5354, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030989351812118e-05, + "loss": 3.5302, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030150757061066e-05, + "loss": 3.5375, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029312162310014e-05, + "loss": 3.5424, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028473567558962e-05, + "loss": 3.5421, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027636610688283e-05, + "loss": 3.5311, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267980159372313e-05, + "loss": 3.5352, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259594211861793e-05, + "loss": 3.5363, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251208264351273e-05, + "loss": 3.5281, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242822316840753e-05, + "loss": 3.5308, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234436369330233e-05, + "loss": 3.5272, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226050421819713e-05, + "loss": 3.531, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217664474309192e-05, + "loss": 3.5267, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.02092949056024e-05, + "loss": 3.5268, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200908958091885e-05, + "loss": 3.5284, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192523010581365e-05, + "loss": 3.532, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184137063070845e-05, + "loss": 3.5254, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175767494364054e-05, + "loss": 3.5319, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167381546853534e-05, + "loss": 3.5361, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0158995599343014e-05, + "loss": 3.5455, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150609651832494e-05, + "loss": 3.5249, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142240083125706e-05, + "loss": 3.5292, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133854135615186e-05, + "loss": 3.54, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125468188104666e-05, + "loss": 3.5333, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117082240594146e-05, + "loss": 3.537, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108712671887355e-05, + "loss": 3.5327, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010032672437684e-05, + "loss": 3.5388, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009194077686632e-05, + "loss": 3.5326, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.00835548293558e-05, + "loss": 3.537, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075185260649008e-05, + "loss": 3.5317, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066799313138488e-05, + "loss": 3.5308, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058413365627968e-05, + "loss": 3.5322, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050027418117447e-05, + "loss": 3.5283, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004165784941066e-05, + "loss": 3.5364, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003327190190014e-05, + "loss": 3.5275, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002488595438962e-05, + "loss": 3.5411, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.00165000068791e-05, + "loss": 3.5184, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000813043817231e-05, + "loss": 3.5324, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.845076560974121, + "eval_runtime": 306.6085, + "eval_samples_per_second": 1244.554, + "eval_steps_per_second": 38.893, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999744490661792e-05, + "loss": 3.5234, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991358543151272e-05, + "loss": 3.5238, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982972595640752e-05, + "loss": 3.537, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997460302693396e-05, + "loss": 3.5388, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996621707942344e-05, + "loss": 3.5376, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995783113191292e-05, + "loss": 3.525, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.99494451844024e-05, + "loss": 3.5258, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941075615695614e-05, + "loss": 3.5178, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932689668185094e-05, + "loss": 3.5382, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924303720674574e-05, + "loss": 3.525, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915917773164053e-05, + "loss": 3.5382, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907548204457263e-05, + "loss": 3.5306, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899162256946746e-05, + "loss": 3.5205, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890776309436226e-05, + "loss": 3.5195, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882390361925706e-05, + "loss": 3.5159, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874004414415186e-05, + "loss": 3.5245, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865634845708395e-05, + "loss": 3.5242, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857248898197875e-05, + "loss": 3.5225, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848862950687355e-05, + "loss": 3.5228, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840477003176838e-05, + "loss": 3.5385, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832107434470047e-05, + "loss": 3.5306, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823721486959527e-05, + "loss": 3.5341, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815335539449007e-05, + "loss": 3.5253, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806949591938487e-05, + "loss": 3.5348, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.97985800232317e-05, + "loss": 3.5257, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.979019407572118e-05, + "loss": 3.524, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978180812821066e-05, + "loss": 3.5307, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977342218070014e-05, + "loss": 3.5148, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976505261199335e-05, + "loss": 3.5181, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975666666448283e-05, + "loss": 3.5188, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974828071697231e-05, + "loss": 3.5314, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739894769461785e-05, + "loss": 3.5271, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731525200755e-05, + "loss": 3.5314, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972313925324448e-05, + "loss": 3.5262, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971475330573396e-05, + "loss": 3.5277, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706367358223437e-05, + "loss": 3.5349, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697997789516653e-05, + "loss": 3.514, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689611842006133e-05, + "loss": 3.5239, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681225894495613e-05, + "loss": 3.5124, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672839946985086e-05, + "loss": 3.5254, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664470378278302e-05, + "loss": 3.5191, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656084430767782e-05, + "loss": 3.5331, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964769848325726e-05, + "loss": 3.5241, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963931253574674e-05, + "loss": 3.5206, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630942967039955e-05, + "loss": 3.5286, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622557019529435e-05, + "loss": 3.5226, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614171072018908e-05, + "loss": 3.5175, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960578512450839e-05, + "loss": 3.5012, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597415555801607e-05, + "loss": 3.5244, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589029608291087e-05, + "loss": 3.5273, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958064366078056e-05, + "loss": 3.5283, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957225771327004e-05, + "loss": 3.517, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563888144563256e-05, + "loss": 3.5151, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555502197052732e-05, + "loss": 3.511, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547116249542212e-05, + "loss": 3.5072, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538730302031692e-05, + "loss": 3.5357, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530360733324908e-05, + "loss": 3.5094, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952197478581438e-05, + "loss": 3.5285, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951358883830386e-05, + "loss": 3.5251, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505202890793345e-05, + "loss": 3.5067, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949683332208656e-05, + "loss": 3.5272, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488447374576034e-05, + "loss": 3.5161, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480061427065514e-05, + "loss": 3.5162, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471675479554994e-05, + "loss": 3.5125, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463305910848206e-05, + "loss": 3.5246, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454919963337686e-05, + "loss": 3.518, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446534015827166e-05, + "loss": 3.5135, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438148068316646e-05, + "loss": 3.5144, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429778499609855e-05, + "loss": 3.5143, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421392552099335e-05, + "loss": 3.5174, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413006604588815e-05, + "loss": 3.5305, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.94046206570783e-05, + "loss": 3.5145, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396251088371507e-05, + "loss": 3.5269, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387865140860987e-05, + "loss": 3.532, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379479193350467e-05, + "loss": 3.5252, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371093245839947e-05, + "loss": 3.5195, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936272367713316e-05, + "loss": 3.5253, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935433772962264e-05, + "loss": 3.5263, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934595178211212e-05, + "loss": 3.5188, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.93375658346016e-05, + "loss": 3.5174, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932919626589481e-05, + "loss": 3.5307, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932081031838429e-05, + "loss": 3.5326, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931242437087377e-05, + "loss": 3.5187, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930403842336325e-05, + "loss": 3.5017, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929566885465646e-05, + "loss": 3.5167, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928728290714594e-05, + "loss": 3.5279, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927889695963542e-05, + "loss": 3.5218, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.92705110121249e-05, + "loss": 3.528, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926214144341811e-05, + "loss": 3.5158, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253755495907593e-05, + "loss": 3.5179, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245369548397073e-05, + "loss": 3.5126, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236983600886553e-05, + "loss": 3.5135, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228614032179762e-05, + "loss": 3.5266, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220228084669242e-05, + "loss": 3.5226, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211842137158722e-05, + "loss": 3.5375, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203456189648202e-05, + "loss": 3.5229, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195086620941415e-05, + "loss": 3.5133, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186700673430895e-05, + "loss": 3.5214, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178314725920375e-05, + "loss": 3.5255, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169928778409855e-05, + "loss": 3.5212, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161559209703064e-05, + "loss": 3.5246, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153173262192547e-05, + "loss": 3.5183, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144787314682027e-05, + "loss": 3.5156, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136401367171507e-05, + "loss": 3.524, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128031798464716e-05, + "loss": 3.5078, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119645850954196e-05, + "loss": 3.5136, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111259903443676e-05, + "loss": 3.5202, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102873955933156e-05, + "loss": 3.5169, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909450438722637e-05, + "loss": 3.5097, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908611843971585e-05, + "loss": 3.5259, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907773249220533e-05, + "loss": 3.505, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906934654469481e-05, + "loss": 3.5182, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.906096059718429e-05, + "loss": 3.5147, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.90525910284775e-05, + "loss": 3.5226, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904420508096698e-05, + "loss": 3.5319, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903581913345646e-05, + "loss": 3.5275, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902744956474967e-05, + "loss": 3.5161, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901906361723915e-05, + "loss": 3.5168, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901067766972863e-05, + "loss": 3.5253, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900229172221811e-05, + "loss": 3.5139, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993905774707593e-05, + "loss": 3.5147, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985519827197073e-05, + "loss": 3.5114, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977133879686553e-05, + "loss": 3.5135, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968747932176033e-05, + "loss": 3.5202, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960378363469242e-05, + "loss": 3.5108, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951992415958722e-05, + "loss": 3.5155, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943606468448202e-05, + "loss": 3.5169, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935220520937685e-05, + "loss": 3.5107, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926850952230894e-05, + "loss": 3.5142, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918465004720374e-05, + "loss": 3.5268, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910079057209854e-05, + "loss": 3.5307, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901693109699334e-05, + "loss": 3.5198, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893323540992547e-05, + "loss": 3.5091, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8884937593482027e-05, + "loss": 3.5219, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876551645971507e-05, + "loss": 3.5221, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868165698460987e-05, + "loss": 3.522, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859796129754196e-05, + "loss": 3.5216, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851410182243676e-05, + "loss": 3.5258, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843024234733156e-05, + "loss": 3.5183, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883463828722264e-05, + "loss": 3.522, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826268718515848e-05, + "loss": 3.5174, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817882771005328e-05, + "loss": 3.5199, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809496823494808e-05, + "loss": 3.5172, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801110875984284e-05, + "loss": 3.5152, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.87927413072775e-05, + "loss": 3.5261, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878435535976698e-05, + "loss": 3.5135, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877596941225646e-05, + "loss": 3.526, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767583464745933e-05, + "loss": 3.511, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875921389603915e-05, + "loss": 3.5107, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8464231491088867, + "eval_runtime": 308.6919, + "eval_samples_per_second": 1236.155, + "eval_steps_per_second": 38.631, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.875082794852863e-05, + "loss": 3.5118, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874244200101811e-05, + "loss": 3.5125, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734056053507586e-05, + "loss": 3.5227, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.87256864848008e-05, + "loss": 3.5195, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871730053729028e-05, + "loss": 3.5247, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708914589779755e-05, + "loss": 3.514, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700528642269238e-05, + "loss": 3.5076, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692159073562454e-05, + "loss": 3.5086, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683773126051934e-05, + "loss": 3.5209, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675387178541407e-05, + "loss": 3.515, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8667001231030887e-05, + "loss": 3.5251, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658631662324103e-05, + "loss": 3.5134, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865024571481358e-05, + "loss": 3.5096, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864185976730306e-05, + "loss": 3.5044, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863347381979254e-05, + "loss": 3.5056, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625104251085755e-05, + "loss": 3.5075, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861671830357523e-05, + "loss": 3.5123, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860833235606471e-05, + "loss": 3.5092, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599946408554192e-05, + "loss": 3.5067, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591576839847404e-05, + "loss": 3.5296, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858319089233688e-05, + "loss": 3.5177, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857480494482636e-05, + "loss": 3.5204, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856641899731584e-05, + "loss": 3.5106, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558049428609053e-05, + "loss": 3.5217, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549663481098533e-05, + "loss": 3.5073, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541277533588013e-05, + "loss": 3.5131, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532891586077493e-05, + "loss": 3.5132, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524522017370702e-05, + "loss": 3.5069, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516136069860182e-05, + "loss": 3.502, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507750122349662e-05, + "loss": 3.5028, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499364174839142e-05, + "loss": 3.5185, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8490994606132355e-05, + "loss": 3.5148, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482608658621835e-05, + "loss": 3.5149, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474222711111314e-05, + "loss": 3.5179, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465836763600794e-05, + "loss": 3.5155, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457467194894007e-05, + "loss": 3.5163, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449081247383487e-05, + "loss": 3.5057, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440695299872967e-05, + "loss": 3.5104, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432309352362447e-05, + "loss": 3.501, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423939783655656e-05, + "loss": 3.5143, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415553836145136e-05, + "loss": 3.5031, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407167888634616e-05, + "loss": 3.5196, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398781941124096e-05, + "loss": 3.5092, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390412372417308e-05, + "loss": 3.5087, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382026424906788e-05, + "loss": 3.5149, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373640477396268e-05, + "loss": 3.5075, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365254529885748e-05, + "loss": 3.5052, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356884961178957e-05, + "loss": 3.4913, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834849901366844e-05, + "loss": 3.5055, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.834011306615792e-05, + "loss": 3.5125, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.83317271186474e-05, + "loss": 3.5117, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832335754994061e-05, + "loss": 3.5043, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831497160243009e-05, + "loss": 3.5, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830658565491957e-05, + "loss": 3.502, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829819970740905e-05, + "loss": 3.4938, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289813759898533e-05, + "loss": 3.5228, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281444191191742e-05, + "loss": 3.4957, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273058243681222e-05, + "loss": 3.5168, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264672296170702e-05, + "loss": 3.5083, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256286348660182e-05, + "loss": 3.4963, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247916779953394e-05, + "loss": 3.5104, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239530832442874e-05, + "loss": 3.5069, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231144884932354e-05, + "loss": 3.4982, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222758937421834e-05, + "loss": 3.5011, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214389368715043e-05, + "loss": 3.5121, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8206003421204523e-05, + "loss": 3.5053, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197617473694003e-05, + "loss": 3.4994, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189231526183486e-05, + "loss": 3.5001, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180861957476696e-05, + "loss": 3.4986, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172476009966175e-05, + "loss": 3.5031, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164090062455655e-05, + "loss": 3.5198, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155704114945135e-05, + "loss": 3.5031, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147334546238348e-05, + "loss": 3.5152, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138948598727828e-05, + "loss": 3.5153, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130562651217308e-05, + "loss": 3.5122, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122176703706788e-05, + "loss": 3.5023, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113807134999997e-05, + "loss": 3.5141, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105421187489477e-05, + "loss": 3.5129, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8097035239978957e-05, + "loss": 3.5045, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808864929246844e-05, + "loss": 3.507, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.808027972376165e-05, + "loss": 3.5117, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.807189377625113e-05, + "loss": 3.5172, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806350782874061e-05, + "loss": 3.506, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805512188123009e-05, + "loss": 3.4948, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.80467523125233e-05, + "loss": 3.5007, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803836636501278e-05, + "loss": 3.5134, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802998041750226e-05, + "loss": 3.511, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802159446999174e-05, + "loss": 3.5141, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801322490128495e-05, + "loss": 3.505, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800483895377443e-05, + "loss": 3.5007, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799645300626391e-05, + "loss": 3.4995, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988067058753394e-05, + "loss": 3.5053, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979697490046603e-05, + "loss": 3.5079, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971311542536083e-05, + "loss": 3.5073, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7962925595025563e-05, + "loss": 3.5265, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954539647515043e-05, + "loss": 3.5131, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946170078808255e-05, + "loss": 3.4976, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937784131297735e-05, + "loss": 3.5111, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929398183787215e-05, + "loss": 3.5077, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921012236276695e-05, + "loss": 3.5119, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912642667569904e-05, + "loss": 3.5098, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904256720059384e-05, + "loss": 3.5044, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895870772548864e-05, + "loss": 3.5036, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887484825038347e-05, + "loss": 3.5136, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879115256331557e-05, + "loss": 3.4926, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870729308821036e-05, + "loss": 3.5054, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862343361310516e-05, + "loss": 3.5017, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853973792603726e-05, + "loss": 3.5074, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784558784509321e-05, + "loss": 3.4944, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783720189758269e-05, + "loss": 3.5103, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782881595007217e-05, + "loss": 3.4986, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820446381365378e-05, + "loss": 3.5038, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812060433854858e-05, + "loss": 3.5036, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803674486344338e-05, + "loss": 3.5044, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795288538833818e-05, + "loss": 3.5222, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778691897012703e-05, + "loss": 3.5128, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777854940142024e-05, + "loss": 3.5078, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.777016345390972e-05, + "loss": 3.5047, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.77617775063992e-05, + "loss": 3.5093, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775339155888868e-05, + "loss": 3.5026, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745005611378163e-05, + "loss": 3.5005, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736619663867643e-05, + "loss": 3.5017, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728233716357122e-05, + "loss": 3.5029, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719847768846602e-05, + "loss": 3.5039, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771147820013981e-05, + "loss": 3.4963, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770309225262929e-05, + "loss": 3.5042, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769470630511877e-05, + "loss": 3.4996, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768632035760825e-05, + "loss": 3.5017, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677950788901464e-05, + "loss": 3.4973, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669564841390944e-05, + "loss": 3.515, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661178893880424e-05, + "loss": 3.521, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652792946369904e-05, + "loss": 3.5068, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644423377663113e-05, + "loss": 3.497, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636037430152596e-05, + "loss": 3.5064, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627651482642076e-05, + "loss": 3.5097, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761926553513155e-05, + "loss": 3.5118, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610895966424765e-05, + "loss": 3.5081, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602510018914245e-05, + "loss": 3.5112, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594124071403725e-05, + "loss": 3.5013, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.75857381238932e-05, + "loss": 3.5128, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577368555186418e-05, + "loss": 3.5029, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568998986479627e-05, + "loss": 3.5101, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560613038969107e-05, + "loss": 3.5063, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552227091458587e-05, + "loss": 3.4972, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543841143948066e-05, + "loss": 3.5132, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753545519643755e-05, + "loss": 3.5023, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527069248927023e-05, + "loss": 3.5127, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518683301416503e-05, + "loss": 3.4959, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510297353905983e-05, + "loss": 3.4996, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8467795848846436, + "eval_runtime": 308.8003, + "eval_samples_per_second": 1235.721, + "eval_steps_per_second": 38.617, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501911406395463e-05, + "loss": 3.4998, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493525458884943e-05, + "loss": 3.4959, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485139511374426e-05, + "loss": 3.5123, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476753563863906e-05, + "loss": 3.5046, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468383995157115e-05, + "loss": 3.5164, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459998047646595e-05, + "loss": 3.4975, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451612100136075e-05, + "loss": 3.4973, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443226152625555e-05, + "loss": 3.4934, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434856583918768e-05, + "loss": 3.5069, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426470636408248e-05, + "loss": 3.5078, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418084688897728e-05, + "loss": 3.5064, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409715120190937e-05, + "loss": 3.5033, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401329172680417e-05, + "loss": 3.496, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392943225169897e-05, + "loss": 3.4934, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738455727765938e-05, + "loss": 3.4922, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737617133014886e-05, + "loss": 3.4939, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736780176144207e-05, + "loss": 3.4973, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735941581393155e-05, + "loss": 3.4962, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735102986642103e-05, + "loss": 3.4949, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734264391891051e-05, + "loss": 3.519, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733427435020372e-05, + "loss": 3.5035, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.73258884026932e-05, + "loss": 3.5078, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731750245518268e-05, + "loss": 3.4978, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730911650767216e-05, + "loss": 3.511, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.730074693896537e-05, + "loss": 3.49, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729236099145485e-05, + "loss": 3.5028, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283975043944334e-05, + "loss": 3.5007, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275605475237543e-05, + "loss": 3.4972, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267219527727023e-05, + "loss": 3.4872, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258833580216503e-05, + "loss": 3.4903, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250447632705982e-05, + "loss": 3.5062, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242078063999195e-05, + "loss": 3.5035, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233692116488675e-05, + "loss": 3.5016, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225306168978155e-05, + "loss": 3.5031, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216920221467635e-05, + "loss": 3.4997, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208550652760844e-05, + "loss": 3.5063, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200164705250324e-05, + "loss": 3.4915, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191778757739804e-05, + "loss": 3.4947, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183392810229287e-05, + "loss": 3.488, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175023241522496e-05, + "loss": 3.5029, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166637294011976e-05, + "loss": 3.4915, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158251346501456e-05, + "loss": 3.5032, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149865398990936e-05, + "loss": 3.4973, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.714149583028415e-05, + "loss": 3.4929, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713310988277363e-05, + "loss": 3.5066, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712472393526311e-05, + "loss": 3.4939, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711633798775259e-05, + "loss": 3.4946, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107968419045798e-05, + "loss": 3.4779, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099582471535278e-05, + "loss": 3.4934, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091196524024758e-05, + "loss": 3.4993, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708281057651424e-05, + "loss": 3.4981, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707444100780745e-05, + "loss": 3.4973, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706605506029693e-05, + "loss": 3.4838, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705766911278641e-05, + "loss": 3.4938, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.704928316527589e-05, + "loss": 3.4782, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040913596569102e-05, + "loss": 3.506, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032527649058582e-05, + "loss": 3.4835, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024141701548062e-05, + "loss": 3.4997, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015755754037542e-05, + "loss": 3.5016, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700738618533075e-05, + "loss": 3.4805, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699900023782023e-05, + "loss": 3.4925, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.699061429030971e-05, + "loss": 3.4968, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982228342799195e-05, + "loss": 3.4845, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973858774092404e-05, + "loss": 3.4886, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965472826581884e-05, + "loss": 3.4957, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957086879071364e-05, + "loss": 3.4957, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948700931560843e-05, + "loss": 3.4849, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940331362854056e-05, + "loss": 3.49, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931945415343536e-05, + "loss": 3.4845, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923559467833016e-05, + "loss": 3.4916, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915173520322496e-05, + "loss": 3.5079, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906803951615705e-05, + "loss": 3.4898, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898418004105185e-05, + "loss": 3.5037, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6890032056594665e-05, + "loss": 3.5007, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881646109084145e-05, + "loss": 3.5004, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873276540377357e-05, + "loss": 3.4881, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864890592866837e-05, + "loss": 3.5047, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856504645356317e-05, + "loss": 3.4961, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848135076649526e-05, + "loss": 3.4981, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683974912913901e-05, + "loss": 3.494, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683136318162849e-05, + "loss": 3.4982, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682297723411797e-05, + "loss": 3.5077, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681459128660745e-05, + "loss": 3.4926, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680620533909693e-05, + "loss": 3.4824, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797819391586403e-05, + "loss": 3.486, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789433444075886e-05, + "loss": 3.5021, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.67810638753691e-05, + "loss": 3.4995, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772677927858575e-05, + "loss": 3.5037, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764291980348055e-05, + "loss": 3.4888, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755906032837535e-05, + "loss": 3.4905, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674753646413075e-05, + "loss": 3.484, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739150516620227e-05, + "loss": 3.4903, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730764569109707e-05, + "loss": 3.4966, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722378621599187e-05, + "loss": 3.4965, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714009052892403e-05, + "loss": 3.5135, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705623105381876e-05, + "loss": 3.4966, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697237157871356e-05, + "loss": 3.4884, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688851210360836e-05, + "loss": 3.4972, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668048164165405e-05, + "loss": 3.491, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667209569414353e-05, + "loss": 3.5015, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666370974663301e-05, + "loss": 3.4958, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665532379912249e-05, + "loss": 3.4906, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646954230415698e-05, + "loss": 3.4939, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663856828290518e-05, + "loss": 3.4991, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.663018233539466e-05, + "loss": 3.4806, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662179638788414e-05, + "loss": 3.4929, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661342681917735e-05, + "loss": 3.4857, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.660504087166683e-05, + "loss": 3.4948, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659665492415631e-05, + "loss": 3.4851, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658826897664579e-05, + "loss": 3.4954, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579899407939002e-05, + "loss": 3.4841, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571513460428482e-05, + "loss": 3.4888, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563127512917962e-05, + "loss": 3.4943, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554741565407442e-05, + "loss": 3.4895, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654637199670065e-05, + "loss": 3.5106, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537986049190135e-05, + "loss": 3.5026, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529616480483344e-05, + "loss": 3.4968, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521230532972824e-05, + "loss": 3.4882, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512844585462304e-05, + "loss": 3.4921, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504458637951784e-05, + "loss": 3.4908, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496072690441264e-05, + "loss": 3.4904, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487686742930744e-05, + "loss": 3.4908, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479300795420227e-05, + "loss": 3.4863, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470914847909707e-05, + "loss": 3.4952, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462545279202916e-05, + "loss": 3.4827, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454159331692396e-05, + "loss": 3.4897, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445773384181876e-05, + "loss": 3.4885, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437387436671356e-05, + "loss": 3.4895, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642901786796457e-05, + "loss": 3.4856, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420631920454048e-05, + "loss": 3.5033, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412245972943528e-05, + "loss": 3.5058, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403860025433008e-05, + "loss": 3.4967, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395490456726217e-05, + "loss": 3.482, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387104509215697e-05, + "loss": 3.4975, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637871856170518e-05, + "loss": 3.495, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.637033261419466e-05, + "loss": 3.4991, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636196304548787e-05, + "loss": 3.4943, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635357709797735e-05, + "loss": 3.4936, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.634519115046683e-05, + "loss": 3.4914, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633680520295631e-05, + "loss": 3.4994, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328435634249522e-05, + "loss": 3.495, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320049686739002e-05, + "loss": 3.4936, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311663739228482e-05, + "loss": 3.4934, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303277791717962e-05, + "loss": 3.487, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629490822301117e-05, + "loss": 3.5003, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628652227550065e-05, + "loss": 3.4949, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278136327990134e-05, + "loss": 3.494, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269750380479614e-05, + "loss": 3.4848, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261380811772823e-05, + "loss": 3.4875, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.848353147506714, + "eval_runtime": 305.5691, + "eval_samples_per_second": 1248.788, + "eval_steps_per_second": 39.026, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252994864262303e-05, + "loss": 3.4904, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244608916751783e-05, + "loss": 3.485, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236222969241263e-05, + "loss": 3.4972, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227853400534476e-05, + "loss": 3.4934, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219467453023956e-05, + "loss": 3.5049, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6211081505513436e-05, + "loss": 3.486, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202695558002916e-05, + "loss": 3.4852, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194325989296125e-05, + "loss": 3.4773, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6185940041785605e-05, + "loss": 3.4936, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177554094275088e-05, + "loss": 3.494, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169168146764568e-05, + "loss": 3.4932, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160798578057777e-05, + "loss": 3.4893, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152412630547257e-05, + "loss": 3.4851, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6144026683036737e-05, + "loss": 3.4817, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135640735526217e-05, + "loss": 3.4797, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.612727116681943e-05, + "loss": 3.4849, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611888521930891e-05, + "loss": 3.4846, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611049927179839e-05, + "loss": 3.4835, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.610211332428787e-05, + "loss": 3.4831, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.609372737677735e-05, + "loss": 3.5067, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085357808070558e-05, + "loss": 3.4909, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.607697186056004e-05, + "loss": 3.4899, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606858591304952e-05, + "loss": 3.4894, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.606021634434273e-05, + "loss": 3.4953, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605183039683221e-05, + "loss": 3.4797, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.604344444932169e-05, + "loss": 3.4952, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603505850181117e-05, + "loss": 3.4852, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026688933104383e-05, + "loss": 3.4833, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018302985593863e-05, + "loss": 3.4726, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009917038083343e-05, + "loss": 3.4802, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001531090572823e-05, + "loss": 3.4898, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993161521866032e-05, + "loss": 3.4919, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984775574355512e-05, + "loss": 3.495, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976389626844992e-05, + "loss": 3.4933, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5968003679334475e-05, + "loss": 3.4819, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959634110627684e-05, + "loss": 3.4964, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951248163117164e-05, + "loss": 3.4789, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942862215606644e-05, + "loss": 3.4871, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934476268096124e-05, + "loss": 3.4742, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5926106699389337e-05, + "loss": 3.4901, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917720751878817e-05, + "loss": 3.4801, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909334804368297e-05, + "loss": 3.491, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900948856857777e-05, + "loss": 3.4882, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892579288150986e-05, + "loss": 3.4779, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884193340640466e-05, + "loss": 3.4941, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875807393129946e-05, + "loss": 3.4846, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867421445619422e-05, + "loss": 3.4803, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859051876912638e-05, + "loss": 3.4687, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850665929402118e-05, + "loss": 3.4787, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842279981891598e-05, + "loss": 3.4886, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833894034381074e-05, + "loss": 3.484, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582552446567429e-05, + "loss": 3.484, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581713851816377e-05, + "loss": 3.4737, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.580875257065325e-05, + "loss": 3.4804, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800366623142723e-05, + "loss": 3.4672, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791980675632203e-05, + "loss": 3.4904, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578361110692542e-05, + "loss": 3.4778, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775225159414896e-05, + "loss": 3.484, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766839211904376e-05, + "loss": 3.4886, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575846964319759e-05, + "loss": 3.4721, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.575008369568707e-05, + "loss": 3.4787, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741697748176545e-05, + "loss": 3.4859, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733311800666028e-05, + "loss": 3.4729, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724925853155508e-05, + "loss": 3.4791, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716556284448724e-05, + "loss": 3.4801, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708170336938197e-05, + "loss": 3.4857, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699784389427677e-05, + "loss": 3.4699, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691414820720893e-05, + "loss": 3.4788, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568302887321037e-05, + "loss": 3.4723, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567464292569985e-05, + "loss": 3.4764, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.566625697818933e-05, + "loss": 3.4906, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657887409482545e-05, + "loss": 3.4791, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564950146197202e-05, + "loss": 3.4929, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.56411155144615e-05, + "loss": 3.4913, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632729566950982e-05, + "loss": 3.4918, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624359998244198e-05, + "loss": 3.4727, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561597405073367e-05, + "loss": 3.4899, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560758810322315e-05, + "loss": 3.4903, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559920215571263e-05, + "loss": 3.4803, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590832587005843e-05, + "loss": 3.4848, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582446639495323e-05, + "loss": 3.4865, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574060691984803e-05, + "loss": 3.4975, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565674744474283e-05, + "loss": 3.4816, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557305175767492e-05, + "loss": 3.4699, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548919228256972e-05, + "loss": 3.4783, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540533280746452e-05, + "loss": 3.4861, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532147333235935e-05, + "loss": 3.4886, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523777764529145e-05, + "loss": 3.4897, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515391817018625e-05, + "loss": 3.4797, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5507005869508104e-05, + "loss": 3.4817, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498619921997584e-05, + "loss": 3.4714, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490250353290797e-05, + "loss": 3.4802, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481864405780277e-05, + "loss": 3.4793, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473478458269757e-05, + "loss": 3.4909, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465092510759237e-05, + "loss": 3.504, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456722942052446e-05, + "loss": 3.4817, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448336994541926e-05, + "loss": 3.4737, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5439951047031406e-05, + "loss": 3.486, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.543156509952089e-05, + "loss": 3.4801, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423195530814098e-05, + "loss": 3.4904, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414809583303578e-05, + "loss": 3.4821, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406423635793058e-05, + "loss": 3.4792, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398037688282538e-05, + "loss": 3.4805, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538966811957575e-05, + "loss": 3.4893, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538128217206523e-05, + "loss": 3.4679, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537289622455471e-05, + "loss": 3.4774, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536451027704419e-05, + "loss": 3.4717, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535612432953367e-05, + "loss": 3.4872, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534775476082688e-05, + "loss": 3.4725, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533936881331636e-05, + "loss": 3.4828, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5330982865805843e-05, + "loss": 3.4739, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322613297099052e-05, + "loss": 3.4768, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314227349588532e-05, + "loss": 3.4794, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305841402078012e-05, + "loss": 3.4801, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297455454567492e-05, + "loss": 3.4949, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5289085885860704e-05, + "loss": 3.4921, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280716317153913e-05, + "loss": 3.4845, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272330369643393e-05, + "loss": 3.4781, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5263944422132873e-05, + "loss": 3.4794, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255558474622353e-05, + "loss": 3.4814, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247172527111833e-05, + "loss": 3.4747, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238786579601313e-05, + "loss": 3.4778, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230400632090796e-05, + "loss": 3.4808, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5222014684580276e-05, + "loss": 3.4792, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213645115873486e-05, + "loss": 3.4753, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205259168362965e-05, + "loss": 3.4746, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196873220852445e-05, + "loss": 3.4749, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188487273341925e-05, + "loss": 3.479, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180117704635138e-05, + "loss": 3.4713, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171731757124618e-05, + "loss": 3.4922, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163345809614098e-05, + "loss": 3.4904, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154959862103578e-05, + "loss": 3.4893, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146590293396787e-05, + "loss": 3.4675, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138204345886267e-05, + "loss": 3.4844, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512981839837575e-05, + "loss": 3.4879, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512143245086523e-05, + "loss": 3.4824, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511306288215844e-05, + "loss": 3.484, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.510467693464792e-05, + "loss": 3.4812, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.50962909871374e-05, + "loss": 3.4791, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508790503962688e-05, + "loss": 3.4878, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507953547092009e-05, + "loss": 3.4826, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.50711659022133e-05, + "loss": 3.4826, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506277995470278e-05, + "loss": 3.484, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505439400719226e-05, + "loss": 3.4726, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504600805968174e-05, + "loss": 3.4872, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503762211217122e-05, + "loss": 3.4852, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.50292361646607e-05, + "loss": 3.4825, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020850217150184e-05, + "loss": 3.471, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012464269639664e-05, + "loss": 3.475, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8495712280273438, + "eval_runtime": 308.2487, + "eval_samples_per_second": 1237.932, + "eval_steps_per_second": 38.686, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004078322129144e-05, + "loss": 3.4772, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499569237461862e-05, + "loss": 3.4743, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.49873064271081e-05, + "loss": 3.4802, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497892047959758e-05, + "loss": 3.4837, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970550910890793e-05, + "loss": 3.4958, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962164963380273e-05, + "loss": 3.4739, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953779015869753e-05, + "loss": 3.4723, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945393068359233e-05, + "loss": 3.4639, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493702349965244e-05, + "loss": 3.4857, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492863755214192e-05, + "loss": 3.4823, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920251604631405e-05, + "loss": 3.477, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911865657120885e-05, + "loss": 3.4801, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903496088414094e-05, + "loss": 3.4712, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895110140903574e-05, + "loss": 3.4764, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886724193393054e-05, + "loss": 3.465, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878338245882534e-05, + "loss": 3.4764, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869968677175746e-05, + "loss": 3.4707, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861582729665226e-05, + "loss": 3.4717, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853196782154706e-05, + "loss": 3.4745, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844810834644186e-05, + "loss": 3.4911, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836441265937395e-05, + "loss": 3.4739, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828055318426875e-05, + "loss": 3.48, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481966937091636e-05, + "loss": 3.4785, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481128342340584e-05, + "loss": 3.4843, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802913854699048e-05, + "loss": 3.4706, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794527907188528e-05, + "loss": 3.4806, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786141959678008e-05, + "loss": 3.4756, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777756012167484e-05, + "loss": 3.47, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.47693864434607e-05, + "loss": 3.4632, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476100049595018e-05, + "loss": 3.4686, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475261454843966e-05, + "loss": 3.4775, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744228600929136e-05, + "loss": 3.4796, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.473585903222235e-05, + "loss": 3.482, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.472747308471183e-05, + "loss": 3.4787, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.471908713720131e-05, + "loss": 3.4706, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471070118969079e-05, + "loss": 3.4847, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702331620984e-05, + "loss": 3.4703, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469394567347348e-05, + "loss": 3.4702, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685559725962958e-05, + "loss": 3.4627, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677190157256174e-05, + "loss": 3.4748, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668804209745654e-05, + "loss": 3.4702, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660418262235134e-05, + "loss": 3.4816, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465203231472461e-05, + "loss": 3.4777, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643662746017823e-05, + "loss": 3.4658, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635276798507303e-05, + "loss": 3.4821, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626890850996783e-05, + "loss": 3.4727, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618504903486263e-05, + "loss": 3.4683, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610118955975742e-05, + "loss": 3.4608, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601749387268955e-05, + "loss": 3.4634, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459336343975843e-05, + "loss": 3.4756, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458497749224791e-05, + "loss": 3.4707, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457659154473739e-05, + "loss": 3.4714, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568221976030607e-05, + "loss": 3.4622, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559836028520084e-05, + "loss": 3.4727, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551450081009564e-05, + "loss": 3.4565, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543064133499044e-05, + "loss": 3.4748, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534694564792253e-05, + "loss": 3.4629, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526308617281736e-05, + "loss": 3.4733, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517922669771216e-05, + "loss": 3.4715, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509536722260696e-05, + "loss": 3.4676, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501167153553905e-05, + "loss": 3.4651, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492781206043385e-05, + "loss": 3.475, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484395258532865e-05, + "loss": 3.4581, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476009311022345e-05, + "loss": 3.4684, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467639742315558e-05, + "loss": 3.4714, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459253794805038e-05, + "loss": 3.4718, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450867847294517e-05, + "loss": 3.4606, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442481899783997e-05, + "loss": 3.4675, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434112331077207e-05, + "loss": 3.4632, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442572638356669e-05, + "loss": 3.4606, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441734043605617e-05, + "loss": 3.4768, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440897086734938e-05, + "loss": 3.4694, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440058491983886e-05, + "loss": 3.481, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439219897232834e-05, + "loss": 3.4793, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438381302481782e-05, + "loss": 3.4821, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.437544345611103e-05, + "loss": 3.4624, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436705750860051e-05, + "loss": 3.4717, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435867156108999e-05, + "loss": 3.4827, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.43503019923832e-05, + "loss": 3.4679, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434191604487268e-05, + "loss": 3.4707, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433353009736216e-05, + "loss": 3.4713, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325144149851644e-05, + "loss": 3.4869, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316758202341124e-05, + "loss": 3.469, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308372254830603e-05, + "loss": 3.4563, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299986307320083e-05, + "loss": 3.4656, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429160035980956e-05, + "loss": 3.4736, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283230791102772e-05, + "loss": 3.4771, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274844843592252e-05, + "loss": 3.4781, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266458896081732e-05, + "loss": 3.4658, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258072948571212e-05, + "loss": 3.4693, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249703379864425e-05, + "loss": 3.4639, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241317432353905e-05, + "loss": 3.4649, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423293148484338e-05, + "loss": 3.4704, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422454553733286e-05, + "loss": 3.4756, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216175968626077e-05, + "loss": 3.4924, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207790021115557e-05, + "loss": 3.4757, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199404073605034e-05, + "loss": 3.4595, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191018126094514e-05, + "loss": 3.473, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182648557387726e-05, + "loss": 3.4649, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174262609877206e-05, + "loss": 3.4783, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165876662366686e-05, + "loss": 3.4734, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157490714856166e-05, + "loss": 3.4696, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414912114614938e-05, + "loss": 3.4681, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140735198638855e-05, + "loss": 3.4765, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132349251128335e-05, + "loss": 3.458, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123963303617815e-05, + "loss": 3.4694, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411559373491103e-05, + "loss": 3.4566, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107207787400507e-05, + "loss": 3.4755, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098821839889987e-05, + "loss": 3.4635, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090435892379467e-05, + "loss": 3.468, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082066323672676e-05, + "loss": 3.4615, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.407368037616216e-05, + "loss": 3.4671, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406529442865164e-05, + "loss": 3.4694, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405690848114112e-05, + "loss": 3.467, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404853891243433e-05, + "loss": 3.4816, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404015296492381e-05, + "loss": 3.4824, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403178339621702e-05, + "loss": 3.4724, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.40233974487065e-05, + "loss": 3.4656, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.401501150119598e-05, + "loss": 3.4683, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400662555368546e-05, + "loss": 3.4727, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399823960617494e-05, + "loss": 3.4564, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398985365866442e-05, + "loss": 3.4709, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.39814677111539e-05, + "loss": 3.4617, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397308176364338e-05, + "loss": 3.4698, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964712194936593e-05, + "loss": 3.4669, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956326247426073e-05, + "loss": 3.4646, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947940299915553e-05, + "loss": 3.4595, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939554352405033e-05, + "loss": 3.4697, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931184783698242e-05, + "loss": 3.4618, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922798836187722e-05, + "loss": 3.4783, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914412888677206e-05, + "loss": 3.476, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906026941166686e-05, + "loss": 3.4843, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897657372459895e-05, + "loss": 3.4545, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889271424949375e-05, + "loss": 3.4765, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880885477438855e-05, + "loss": 3.4756, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387249952992833e-05, + "loss": 3.4717, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864129961221547e-05, + "loss": 3.4741, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855744013711027e-05, + "loss": 3.4729, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847358066200507e-05, + "loss": 3.4672, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838972118689984e-05, + "loss": 3.4786, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830602549983196e-05, + "loss": 3.4655, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822216602472676e-05, + "loss": 3.4722, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813830654962156e-05, + "loss": 3.4714, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805444707451636e-05, + "loss": 3.4643, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379707513874485e-05, + "loss": 3.4719, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378868919123433e-05, + "loss": 3.4775, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780303243723805e-05, + "loss": 3.4701, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771917296213285e-05, + "loss": 3.4582, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.37635477275065e-05, + "loss": 3.4666, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8494863510131836, + "eval_runtime": 307.8516, + "eval_samples_per_second": 1239.529, + "eval_steps_per_second": 38.736, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375516177999598e-05, + "loss": 3.4715, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746775832485457e-05, + "loss": 3.4601, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738389884974937e-05, + "loss": 3.4673, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.373002031626815e-05, + "loss": 3.4752, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.372163436875763e-05, + "loss": 3.4805, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.371324842124711e-05, + "loss": 3.4681, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370486247373659e-05, + "loss": 3.4575, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696492905029802e-05, + "loss": 3.4522, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368810695751928e-05, + "loss": 3.4708, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.367972101000876e-05, + "loss": 3.4724, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.367133506249824e-05, + "loss": 3.4633, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662965493791454e-05, + "loss": 3.4699, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.365457954628093e-05, + "loss": 3.4586, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364619359877041e-05, + "loss": 3.4646, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363780765125989e-05, + "loss": 3.4559, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629438082553103e-05, + "loss": 3.4631, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3621052135042583e-05, + "loss": 3.4555, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612666187532063e-05, + "loss": 3.4642, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604280240021543e-05, + "loss": 3.4576, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595910671314752e-05, + "loss": 3.4819, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587524723804232e-05, + "loss": 3.4664, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579138776293712e-05, + "loss": 3.474, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570752828783192e-05, + "loss": 3.4634, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562383260076405e-05, + "loss": 3.4704, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553997312565885e-05, + "loss": 3.4587, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545611365055365e-05, + "loss": 3.4693, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537225417544845e-05, + "loss": 3.4672, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528855848838054e-05, + "loss": 3.4557, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520469901327537e-05, + "loss": 3.4499, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512083953817017e-05, + "loss": 3.4558, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503698006306497e-05, + "loss": 3.4685, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495328437599706e-05, + "loss": 3.4645, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486942490089186e-05, + "loss": 3.4703, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478556542578666e-05, + "loss": 3.4729, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470170595068146e-05, + "loss": 3.4603, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346180102636136e-05, + "loss": 3.4688, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3453415078850838e-05, + "loss": 3.462, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3445029131340318e-05, + "loss": 3.4598, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436643183829798e-05, + "loss": 3.4481, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428273615123007e-05, + "loss": 3.4666, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.341988766761249e-05, + "loss": 3.4586, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.341150172010197e-05, + "loss": 3.4706, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340311577259145e-05, + "loss": 3.4627, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339474620388466e-05, + "loss": 3.4552, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338636025637414e-05, + "loss": 3.4714, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.337797430886362e-05, + "loss": 3.4583, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.33695883613531e-05, + "loss": 3.4579, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361218792646312e-05, + "loss": 3.4498, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352832845135792e-05, + "loss": 3.4484, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344446897625272e-05, + "loss": 3.4613, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3336060950114752e-05, + "loss": 3.4615, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332769138140796e-05, + "loss": 3.4581, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331930543389744e-05, + "loss": 3.4521, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310919486386924e-05, + "loss": 3.4616, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302533538876404e-05, + "loss": 3.4422, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294163970169613e-05, + "loss": 3.4662, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285778022659093e-05, + "loss": 3.4527, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277392075148573e-05, + "loss": 3.4603, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3269006127638053e-05, + "loss": 3.4598, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260636558931266e-05, + "loss": 3.457, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252250611420746e-05, + "loss": 3.4532, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243864663910226e-05, + "loss": 3.4619, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235478716399702e-05, + "loss": 3.4534, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3227109147692915e-05, + "loss": 3.4536, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3218723200182395e-05, + "loss": 3.4619, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210337252671878e-05, + "loss": 3.4608, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201951305161355e-05, + "loss": 3.447, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193581736454567e-05, + "loss": 3.4592, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185195788944047e-05, + "loss": 3.4501, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176809841433527e-05, + "loss": 3.4494, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168423893923007e-05, + "loss": 3.4662, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.316005432521622e-05, + "loss": 3.4599, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.31516683777057e-05, + "loss": 3.4663, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143282430195176e-05, + "loss": 3.4633, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134896482684656e-05, + "loss": 3.4751, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126526913977868e-05, + "loss": 3.4538, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118140966467348e-05, + "loss": 3.4582, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109755018956828e-05, + "loss": 3.4694, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101369071446308e-05, + "loss": 3.4536, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309299950273952e-05, + "loss": 3.4633, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084613555229e-05, + "loss": 3.4645, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076227607718477e-05, + "loss": 3.4684, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.306784166020796e-05, + "loss": 3.4596, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305945571269744e-05, + "loss": 3.4488, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305106976518692e-05, + "loss": 3.4534, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.30426838176764e-05, + "loss": 3.4612, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303431424896961e-05, + "loss": 3.4657, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.302592830145909e-05, + "loss": 3.4659, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301754235394857e-05, + "loss": 3.4565, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.300915640643805e-05, + "loss": 3.4589, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000786837731262e-05, + "loss": 3.4518, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992400890220742e-05, + "loss": 3.4523, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2984014942710222e-05, + "loss": 3.4567, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2975628995199702e-05, + "loss": 3.4665, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967259426492914e-05, + "loss": 3.4798, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958873478982394e-05, + "loss": 3.4669, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950487531471874e-05, + "loss": 3.444, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942101583961354e-05, + "loss": 3.4646, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933732015254563e-05, + "loss": 3.4543, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925346067744043e-05, + "loss": 3.4681, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916960120233523e-05, + "loss": 3.4584, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908574172723003e-05, + "loss": 3.4561, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900204604016216e-05, + "loss": 3.4573, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891818656505695e-05, + "loss": 3.4585, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883432708995175e-05, + "loss": 3.451, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875046761484655e-05, + "loss": 3.457, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866677192777864e-05, + "loss": 3.4459, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858291245267348e-05, + "loss": 3.467, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849905297756828e-05, + "loss": 3.4528, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841519350246304e-05, + "loss": 3.4542, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833149781539517e-05, + "loss": 3.4482, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824763834028997e-05, + "loss": 3.4586, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816377886518477e-05, + "loss": 3.4581, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2807991939007957e-05, + "loss": 3.4565, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279962237030117e-05, + "loss": 3.4707, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279123642279065e-05, + "loss": 3.4675, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782866854083858e-05, + "loss": 3.4626, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774480906573338e-05, + "loss": 3.4573, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766094959062818e-05, + "loss": 3.4546, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.27577090115523e-05, + "loss": 3.4648, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2749323064041778e-05, + "loss": 3.4485, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740937116531258e-05, + "loss": 3.4594, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732551169020738e-05, + "loss": 3.4471, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724165221510218e-05, + "loss": 3.4621, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271579565280343e-05, + "loss": 3.4484, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.270740970529291e-05, + "loss": 3.4564, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.269902375778239e-05, + "loss": 3.4536, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.269063781027187e-05, + "loss": 3.4555, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268226824156508e-05, + "loss": 3.4536, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.267388229405456e-05, + "loss": 3.4629, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.266549634654404e-05, + "loss": 3.4669, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657110399033523e-05, + "loss": 3.4706, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648740830326732e-05, + "loss": 3.4446, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.264035488281621e-05, + "loss": 3.4628, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.263196893530569e-05, + "loss": 3.4627, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262358298779517e-05, + "loss": 3.4634, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615213419088384e-05, + "loss": 3.4595, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606827471577864e-05, + "loss": 3.4613, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598441524067344e-05, + "loss": 3.4558, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590055576556824e-05, + "loss": 3.4702, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581686007850033e-05, + "loss": 3.4502, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573300060339513e-05, + "loss": 3.4645, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564914112828993e-05, + "loss": 3.4566, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556528165318473e-05, + "loss": 3.456, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548158596611685e-05, + "loss": 3.4596, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539772649101165e-05, + "loss": 3.4602, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531386701590645e-05, + "loss": 3.4633, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2523000754080125e-05, + "loss": 3.4435, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514631185373338e-05, + "loss": 3.4571, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.851583480834961, + "eval_runtime": 307.8626, + "eval_samples_per_second": 1239.485, + "eval_steps_per_second": 38.735, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506245237862818e-05, + "loss": 3.4548, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497859290352298e-05, + "loss": 3.4493, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489473342841778e-05, + "loss": 3.4548, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481087395331254e-05, + "loss": 3.4653, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472717826624467e-05, + "loss": 3.472, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464331879113947e-05, + "loss": 3.4538, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2455945931603427e-05, + "loss": 3.4437, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2447559984092907e-05, + "loss": 3.4473, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243919041538612e-05, + "loss": 3.4536, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.24308044678756e-05, + "loss": 3.4633, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242241852036508e-05, + "loss": 3.4522, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414032572854555e-05, + "loss": 3.4575, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240566300414777e-05, + "loss": 3.4515, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239727705663725e-05, + "loss": 3.4502, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388891109126728e-05, + "loss": 3.4491, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380505161616208e-05, + "loss": 3.4498, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237213559290942e-05, + "loss": 3.4463, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.23637496453989e-05, + "loss": 3.4484, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.235536369788838e-05, + "loss": 3.4515, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234697775037786e-05, + "loss": 3.467, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338608181671073e-05, + "loss": 3.4556, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330222234160553e-05, + "loss": 3.463, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.232183628665003e-05, + "loss": 3.4493, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.231345033913951e-05, + "loss": 3.4618, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305080770432725e-05, + "loss": 3.4469, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.22966948229222e-05, + "loss": 3.4599, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.228830887541168e-05, + "loss": 3.4507, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227992292790116e-05, + "loss": 3.4445, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271553359194374e-05, + "loss": 3.4435, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263167411683854e-05, + "loss": 3.4451, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254781464173334e-05, + "loss": 3.4553, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246395516662814e-05, + "loss": 3.4545, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238025947956026e-05, + "loss": 3.4579, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229640000445503e-05, + "loss": 3.4643, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221254052934983e-05, + "loss": 3.4429, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212884484228195e-05, + "loss": 3.4612, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204498536717675e-05, + "loss": 3.453, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196112589207155e-05, + "loss": 3.4441, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187726641696635e-05, + "loss": 3.4394, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179357072989848e-05, + "loss": 3.4486, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170971125479324e-05, + "loss": 3.4525, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162585177968808e-05, + "loss": 3.4565, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154199230458288e-05, + "loss": 3.4511, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145829661751497e-05, + "loss": 3.4455, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137443714240977e-05, + "loss": 3.463, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129057766730457e-05, + "loss": 3.4511, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120671819219937e-05, + "loss": 3.446, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112285871709416e-05, + "loss": 3.4389, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210391630300263e-05, + "loss": 3.4359, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209553035549211e-05, + "loss": 3.4525, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208714440798159e-05, + "loss": 3.4498, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078774839274798e-05, + "loss": 3.4464, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070388891764278e-05, + "loss": 3.4413, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2062002944253758e-05, + "loss": 3.4524, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205361699674324e-05, + "loss": 3.4284, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204524742803645e-05, + "loss": 3.4522, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203686148052593e-05, + "loss": 3.4436, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.202847553301541e-05, + "loss": 3.4441, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.202008958550489e-05, + "loss": 3.4537, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011720016798103e-05, + "loss": 3.4428, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003334069287583e-05, + "loss": 3.4419, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994948121777063e-05, + "loss": 3.4564, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986562174266543e-05, + "loss": 3.4374, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197819260555975e-05, + "loss": 3.4426, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196980665804923e-05, + "loss": 3.4487, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.196142071053871e-05, + "loss": 3.4485, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953034763028195e-05, + "loss": 3.4376, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944665194321404e-05, + "loss": 3.4456, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936279246810884e-05, + "loss": 3.4381, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927893299300364e-05, + "loss": 3.4395, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919507351789844e-05, + "loss": 3.4516, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911137783083056e-05, + "loss": 3.4481, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902751835572536e-05, + "loss": 3.4558, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894365888062016e-05, + "loss": 3.4494, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885979940551496e-05, + "loss": 3.4662, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877593993040976e-05, + "loss": 3.442, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869224424334185e-05, + "loss": 3.4496, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860838476823665e-05, + "loss": 3.4588, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185245252931315e-05, + "loss": 3.441, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844082960606358e-05, + "loss": 3.4505, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835697013095838e-05, + "loss": 3.4528, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827311065585318e-05, + "loss": 3.4576, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818925118074798e-05, + "loss": 3.4473, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810539170564277e-05, + "loss": 3.4383, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802153223053757e-05, + "loss": 3.4396, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793767275543237e-05, + "loss": 3.4506, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785381328032717e-05, + "loss": 3.4568, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1777011759325926e-05, + "loss": 3.4537, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768625811815406e-05, + "loss": 3.4498, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760239864304886e-05, + "loss": 3.4408, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175185391679437e-05, + "loss": 3.4437, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174348434808758e-05, + "loss": 3.4437, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173509840057706e-05, + "loss": 3.4439, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172671245306654e-05, + "loss": 3.4574, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171832650555602e-05, + "loss": 3.4644, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.170995693684923e-05, + "loss": 3.4558, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.170157098933871e-05, + "loss": 3.4395, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.169318504182819e-05, + "loss": 3.4498, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.168479909431767e-05, + "loss": 3.4442, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.167642952561088e-05, + "loss": 3.4555, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166804357810036e-05, + "loss": 3.4467, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165965763058984e-05, + "loss": 3.4522, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.165127168307932e-05, + "loss": 3.4472, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642902114372532e-05, + "loss": 3.4429, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634516166862012e-05, + "loss": 3.4435, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626130219351492e-05, + "loss": 3.4435, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617744271840972e-05, + "loss": 3.4351, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.160937470313418e-05, + "loss": 3.454, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600988755623665e-05, + "loss": 3.4432, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592602808113145e-05, + "loss": 3.4431, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584233239406354e-05, + "loss": 3.4405, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575847291895834e-05, + "loss": 3.444, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567461344385314e-05, + "loss": 3.4498, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1559075396874794e-05, + "loss": 3.4448, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550705828168006e-05, + "loss": 3.4606, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542319880657486e-05, + "loss": 3.4559, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533950311950695e-05, + "loss": 3.4537, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525564364440175e-05, + "loss": 3.449, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517178416929655e-05, + "loss": 3.4381, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508792469419135e-05, + "loss": 3.4563, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150040652190862e-05, + "loss": 3.4428, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.14920205743981e-05, + "loss": 3.4441, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483634626887575e-05, + "loss": 3.4365, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475248679377055e-05, + "loss": 3.4497, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466879110670267e-05, + "loss": 3.4382, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458493163159747e-05, + "loss": 3.4445, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450107215649227e-05, + "loss": 3.4405, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441721268138707e-05, + "loss": 3.4478, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143335169943192e-05, + "loss": 3.4416, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.14249657519214e-05, + "loss": 3.4561, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416579804410876e-05, + "loss": 3.4525, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408193856900356e-05, + "loss": 3.4604, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399824288193572e-05, + "loss": 3.4343, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139143834068305e-05, + "loss": 3.4541, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138305239317253e-05, + "loss": 3.4515, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137466644566201e-05, + "loss": 3.451, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136629687695522e-05, + "loss": 3.452, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.13579109294447e-05, + "loss": 3.45, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.134952498193418e-05, + "loss": 3.4405, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.134113903442366e-05, + "loss": 3.4641, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332769465716873e-05, + "loss": 3.436, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132438351820635e-05, + "loss": 3.4518, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.131599757069583e-05, + "loss": 3.4476, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130761162318531e-05, + "loss": 3.4466, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299242054478522e-05, + "loss": 3.4479, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290856106968002e-05, + "loss": 3.4477, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282470159457482e-05, + "loss": 3.453, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274084211946962e-05, + "loss": 3.4314, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126571464324017e-05, + "loss": 3.4483, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.85245943069458, + "eval_runtime": 334.6358, + "eval_samples_per_second": 1140.317, + "eval_steps_per_second": 35.636, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257328695729655e-05, + "loss": 3.4477, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248942748219135e-05, + "loss": 3.4382, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240556800708615e-05, + "loss": 3.4439, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232187232001824e-05, + "loss": 3.4527, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223801284491304e-05, + "loss": 3.4595, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215415336980784e-05, + "loss": 3.4468, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1207029389470264e-05, + "loss": 3.435, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1198659820763476e-05, + "loss": 3.4365, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1190273873252956e-05, + "loss": 3.4449, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181887925742436e-05, + "loss": 3.4486, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173501978231916e-05, + "loss": 3.4405, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165132409525125e-05, + "loss": 3.4473, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1156746462014605e-05, + "loss": 3.4436, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114836051450409e-05, + "loss": 3.4401, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1139974566993568e-05, + "loss": 3.4344, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1131604998286777e-05, + "loss": 3.4362, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1123219050776257e-05, + "loss": 3.4402, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1114833103265737e-05, + "loss": 3.4377, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1106447155755217e-05, + "loss": 3.4415, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109807758704843e-05, + "loss": 3.4504, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108969163953791e-05, + "loss": 3.4479, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108130569202739e-05, + "loss": 3.4507, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107291974451687e-05, + "loss": 3.44, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106455017581008e-05, + "loss": 3.4465, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.105616422829956e-05, + "loss": 3.4362, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047778280789042e-05, + "loss": 3.4543, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039392333278522e-05, + "loss": 3.4356, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.103102276457173e-05, + "loss": 3.4351, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.102263681706121e-05, + "loss": 3.4319, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.101425086955069e-05, + "loss": 3.4349, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.100586492204017e-05, + "loss": 3.4417, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997495353333383e-05, + "loss": 3.4454, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989109405822863e-05, + "loss": 3.4488, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980723458312343e-05, + "loss": 3.445, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972337510801823e-05, + "loss": 3.4364, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963967942095032e-05, + "loss": 3.449, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955581994584512e-05, + "loss": 3.4458, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947196047073996e-05, + "loss": 3.4292, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938810099563476e-05, + "loss": 3.4323, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930440530856685e-05, + "loss": 3.4362, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0922054583346165e-05, + "loss": 3.4405, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913668635835645e-05, + "loss": 3.4463, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905282688325125e-05, + "loss": 3.4386, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0896913119618337e-05, + "loss": 3.4348, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888527172107817e-05, + "loss": 3.4492, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0880141224597297e-05, + "loss": 3.4417, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871755277086774e-05, + "loss": 3.4388, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863385708379986e-05, + "loss": 3.424, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0854999760869466e-05, + "loss": 3.4229, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0846613813358946e-05, + "loss": 3.4462, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0838227865848426e-05, + "loss": 3.435, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.082985829714164e-05, + "loss": 3.4412, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.082147234963112e-05, + "loss": 3.4332, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0813086402120595e-05, + "loss": 3.4354, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0804700454610078e-05, + "loss": 3.4201, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079633088590329e-05, + "loss": 3.4404, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078794493839277e-05, + "loss": 3.4338, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0779558990882247e-05, + "loss": 3.4329, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0771173043371727e-05, + "loss": 3.4457, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.076280347466494e-05, + "loss": 3.4321, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075441752715442e-05, + "loss": 3.43, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.07460315796439e-05, + "loss": 3.4465, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073764563213338e-05, + "loss": 3.4288, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729276063426592e-05, + "loss": 3.4257, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.072089011591607e-05, + "loss": 3.4427, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071250416840555e-05, + "loss": 3.4364, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.070411822089503e-05, + "loss": 3.4259, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695748652188244e-05, + "loss": 3.4392, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.068736270467772e-05, + "loss": 3.4274, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.06789767571672e-05, + "loss": 3.4277, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.067059080965668e-05, + "loss": 3.4432, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.066222124094989e-05, + "loss": 3.4385, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653835293439373e-05, + "loss": 3.4428, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645465724732586e-05, + "loss": 3.4372, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0637079777222066e-05, + "loss": 3.4558, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628693829711542e-05, + "loss": 3.4343, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620307882201022e-05, + "loss": 3.4409, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0611921934690502e-05, + "loss": 3.4468, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603535987179982e-05, + "loss": 3.4304, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0595166418473195e-05, + "loss": 3.4365, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586780470962675e-05, + "loss": 3.4457, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578394523452155e-05, + "loss": 3.4468, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0570008575941635e-05, + "loss": 3.4401, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0561622628431114e-05, + "loss": 3.4296, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0553236680920594e-05, + "loss": 3.4247, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544850733410074e-05, + "loss": 3.4409, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0536481164703287e-05, + "loss": 3.4479, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528095217192767e-05, + "loss": 3.4417, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519709269682247e-05, + "loss": 3.4401, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511323322171723e-05, + "loss": 3.4251, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0502953753464936e-05, + "loss": 3.4369, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049456780595442e-05, + "loss": 3.4324, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.04861818584439e-05, + "loss": 3.4381, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477795910933376e-05, + "loss": 3.4406, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469426342226588e-05, + "loss": 3.4551, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0461040394716068e-05, + "loss": 3.4453, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452654447205548e-05, + "loss": 3.4308, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444268499695028e-05, + "loss": 3.4364, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043589893098824e-05, + "loss": 3.4348, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042751298347772e-05, + "loss": 3.4459, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0419127035967197e-05, + "loss": 3.4351, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410741088456677e-05, + "loss": 3.4457, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.040237151974989e-05, + "loss": 3.4372, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393985572239373e-05, + "loss": 3.4248, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.038559962472885e-05, + "loss": 3.438, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037721367721833e-05, + "loss": 3.4306, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0368844108511542e-05, + "loss": 3.4275, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.036045816100102e-05, + "loss": 3.4387, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0352072213490502e-05, + "loss": 3.4351, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343686265979982e-05, + "loss": 3.4298, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335316697273194e-05, + "loss": 3.4332, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032693074976267e-05, + "loss": 3.4304, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031854480225215e-05, + "loss": 3.4414, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.031015885474163e-05, + "loss": 3.4314, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301789286034843e-05, + "loss": 3.4515, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293403338524323e-05, + "loss": 3.4474, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0285017391013803e-05, + "loss": 3.4433, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276647822307016e-05, + "loss": 3.4379, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268261874796492e-05, + "loss": 3.4273, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0259875927285972e-05, + "loss": 3.4417, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251489979775452e-05, + "loss": 3.4365, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0243104032264935e-05, + "loss": 3.4306, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234718084754415e-05, + "loss": 3.4285, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226332137243895e-05, + "loss": 3.4403, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0217962568537104e-05, + "loss": 3.4278, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0209576621026584e-05, + "loss": 3.4356, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0201190673516064e-05, + "loss": 3.4282, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192804726005544e-05, + "loss": 3.4399, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184435157298757e-05, + "loss": 3.4267, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0176049209788237e-05, + "loss": 3.4474, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167663262277717e-05, + "loss": 3.4385, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159277314767197e-05, + "loss": 3.4499, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0150907746060406e-05, + "loss": 3.4248, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014252179854989e-05, + "loss": 3.444, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013413585103937e-05, + "loss": 3.4385, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.012574990352885e-05, + "loss": 3.4417, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117363956018326e-05, + "loss": 3.4389, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0108994387311538e-05, + "loss": 3.4352, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100608439801018e-05, + "loss": 3.4346, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092222492290498e-05, + "loss": 3.4504, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0083836544779978e-05, + "loss": 3.4267, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.007546697607319e-05, + "loss": 3.4414, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.00670974073664e-05, + "loss": 3.4386, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.005871145985588e-05, + "loss": 3.4361, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.005032551234536e-05, + "loss": 3.4385, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041939564834843e-05, + "loss": 3.4347, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033553617324323e-05, + "loss": 3.4456, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.00251676698138e-05, + "loss": 3.4187, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0016798101107012e-05, + "loss": 3.4417, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.853367567062378, + "eval_runtime": 332.8889, + "eval_samples_per_second": 1146.301, + "eval_steps_per_second": 35.823, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008412153596492e-05, + "loss": 3.4296, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 2.000002620608597e-05, + "loss": 3.4302, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.999164025857545e-05, + "loss": 3.4329, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.998325431106493e-05, + "loss": 3.4392, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9974884742358144e-05, + "loss": 3.4503, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996649879484762e-05, + "loss": 3.433, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.99581128473371e-05, + "loss": 3.4276, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.994972689982658e-05, + "loss": 3.4264, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941357331119796e-05, + "loss": 3.4286, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932971383609273e-05, + "loss": 3.443, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924585436098753e-05, + "loss": 3.4297, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916199488588233e-05, + "loss": 3.4394, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907829919881442e-05, + "loss": 3.4295, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899443972370922e-05, + "loss": 3.4256, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9891058024860405e-05, + "loss": 3.427, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882672077349885e-05, + "loss": 3.4243, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874302508643094e-05, + "loss": 3.4295, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865916561132574e-05, + "loss": 3.4267, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857530613622054e-05, + "loss": 3.4312, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9849144666111534e-05, + "loss": 3.4389, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840775097404747e-05, + "loss": 3.439, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832389149894227e-05, + "loss": 3.4428, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9824003202383707e-05, + "loss": 3.4295, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815617254873187e-05, + "loss": 3.4358, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807247686166396e-05, + "loss": 3.4296, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798861738655876e-05, + "loss": 3.4406, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.979047579114536e-05, + "loss": 3.4282, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.978208984363484e-05, + "loss": 3.4273, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773720274928048e-05, + "loss": 3.4239, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765334327417528e-05, + "loss": 3.4237, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756948379907008e-05, + "loss": 3.4257, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748562432396488e-05, + "loss": 3.4395, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.97401928636897e-05, + "loss": 3.4353, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973180691617918e-05, + "loss": 3.4371, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972342096866866e-05, + "loss": 3.4266, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971503502115814e-05, + "loss": 3.4391, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.970666545245135e-05, + "loss": 3.4342, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969827950494083e-05, + "loss": 3.4204, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689893557430313e-05, + "loss": 3.4224, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681507609919793e-05, + "loss": 3.4243, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673138041213e-05, + "loss": 3.4271, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966475209370248e-05, + "loss": 3.4344, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965636614619196e-05, + "loss": 3.4309, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.964798019868144e-05, + "loss": 3.4256, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639610629974654e-05, + "loss": 3.4367, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631224682464134e-05, + "loss": 3.4294, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622838734953614e-05, + "loss": 3.4328, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614452787443094e-05, + "loss": 3.4153, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9606083218736303e-05, + "loss": 3.4058, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597697271225783e-05, + "loss": 3.4389, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589311323715266e-05, + "loss": 3.4235, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580925376204746e-05, + "loss": 3.4312, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572555807497955e-05, + "loss": 3.4253, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564169859987435e-05, + "loss": 3.4209, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555783912476915e-05, + "loss": 3.4154, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9547397964966395e-05, + "loss": 3.4268, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9539028396259608e-05, + "loss": 3.419, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530642448749088e-05, + "loss": 3.426, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522256501238568e-05, + "loss": 3.4371, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513870553728044e-05, + "loss": 3.4204, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505500985021257e-05, + "loss": 3.4195, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9497115037510737e-05, + "loss": 3.436, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948872909000022e-05, + "loss": 3.4168, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.948035952129343e-05, + "loss": 3.417, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.947197357378291e-05, + "loss": 3.4322, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.946358762627239e-05, + "loss": 3.4193, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455201678761866e-05, + "loss": 3.4164, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.944683211005508e-05, + "loss": 3.4255, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943844616254456e-05, + "loss": 3.418, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.943006021503404e-05, + "loss": 3.4143, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421674267523518e-05, + "loss": 3.435, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.941330469881673e-05, + "loss": 3.4262, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.940491875130621e-05, + "loss": 3.43, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.939653280379569e-05, + "loss": 3.4287, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.938814685628517e-05, + "loss": 3.4469, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379777287578383e-05, + "loss": 3.422, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371391340067863e-05, + "loss": 3.4326, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.936300539255734e-05, + "loss": 3.4324, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.935461944504682e-05, + "loss": 3.421, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346249876340035e-05, + "loss": 3.4246, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337863928829515e-05, + "loss": 3.4391, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932947798131899e-05, + "loss": 3.4337, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.932109203380847e-05, + "loss": 3.4342, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931270608629795e-05, + "loss": 3.4166, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930432013878743e-05, + "loss": 3.4104, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929593419127691e-05, + "loss": 3.4316, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.928754824376639e-05, + "loss": 3.4367, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279178675059604e-05, + "loss": 3.433, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270792727549084e-05, + "loss": 3.4293, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262406780038564e-05, + "loss": 3.4162, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9254020832528044e-05, + "loss": 3.4242, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9245651263821253e-05, + "loss": 3.4236, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9237265316310736e-05, + "loss": 3.4239, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228879368800216e-05, + "loss": 3.4362, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220493421289696e-05, + "loss": 3.4393, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9212123852582905e-05, + "loss": 3.4366, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9203737905072385e-05, + "loss": 3.4215, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9195351957561865e-05, + "loss": 3.4221, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186982388855078e-05, + "loss": 3.4258, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178596441344558e-05, + "loss": 3.4338, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9170210493834037e-05, + "loss": 3.4252, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161824546323517e-05, + "loss": 3.4342, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153454977616727e-05, + "loss": 3.4258, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9145069030106206e-05, + "loss": 3.4181, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913668308259569e-05, + "loss": 3.425, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912829713508517e-05, + "loss": 3.4196, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.911992756637838e-05, + "loss": 3.4189, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.911154161886786e-05, + "loss": 3.4287, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.910315567135734e-05, + "loss": 3.4269, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909476972384682e-05, + "loss": 3.4206, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908640015514003e-05, + "loss": 3.4198, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.907801420762951e-05, + "loss": 3.4174, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.906962826011899e-05, + "loss": 3.4305, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061242312608468e-05, + "loss": 3.4205, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.905287274390168e-05, + "loss": 3.4428, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.904448679639116e-05, + "loss": 3.4379, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036100848880643e-05, + "loss": 3.4313, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027731280173853e-05, + "loss": 3.4225, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019345332663333e-05, + "loss": 3.4198, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010959385152812e-05, + "loss": 3.4285, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002573437642292e-05, + "loss": 3.4246, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.899418749013177e-05, + "loss": 3.4188, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985801542621252e-05, + "loss": 3.4198, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977415595110732e-05, + "loss": 3.429, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896904602640394e-05, + "loss": 3.4197, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896066007889342e-05, + "loss": 3.4221, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.89522741313829e-05, + "loss": 3.4146, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.894388818387238e-05, + "loss": 3.4309, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935518615165594e-05, + "loss": 3.4181, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8927132667655074e-05, + "loss": 3.4321, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918746720144554e-05, + "loss": 3.4293, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910360772634034e-05, + "loss": 3.4379, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8901991203927243e-05, + "loss": 3.4183, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8893605256416723e-05, + "loss": 3.4356, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8885219308906206e-05, + "loss": 3.4239, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876833361395686e-05, + "loss": 3.4303, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868463792688895e-05, + "loss": 3.4305, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8860077845178375e-05, + "loss": 3.4214, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851691897667855e-05, + "loss": 3.4257, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8843305950157335e-05, + "loss": 3.4398, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8834936381450547e-05, + "loss": 3.4171, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826550433940027e-05, + "loss": 3.429, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818164486429507e-05, + "loss": 3.4318, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809778538918987e-05, + "loss": 3.4275, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801408970212196e-05, + "loss": 3.4228, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8793023022701676e-05, + "loss": 3.4241, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.878463707519116e-05, + "loss": 3.4332, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.877625112768064e-05, + "loss": 3.4133, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.876788155897385e-05, + "loss": 3.4295, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.855191707611084, + "eval_runtime": 305.2312, + "eval_samples_per_second": 1250.17, + "eval_steps_per_second": 39.069, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.875949561146333e-05, + "loss": 3.4217, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.875110966395281e-05, + "loss": 3.4191, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.874272371644229e-05, + "loss": 3.4216, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.87343541477355e-05, + "loss": 3.431, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.872596820022498e-05, + "loss": 3.4403, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.871758225271446e-05, + "loss": 3.4212, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.870919630520394e-05, + "loss": 3.4179, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.870082673649715e-05, + "loss": 3.4219, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.869244078898663e-05, + "loss": 3.4148, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8684054841476113e-05, + "loss": 3.4359, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675668893965593e-05, + "loss": 3.4162, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8667299325258802e-05, + "loss": 3.4241, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658913377748282e-05, + "loss": 3.4282, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8650527430237762e-05, + "loss": 3.4134, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8642141482727242e-05, + "loss": 3.4137, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633771914020455e-05, + "loss": 3.4144, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625385966509935e-05, + "loss": 3.4184, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8617000018999415e-05, + "loss": 3.4222, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.860861407148889e-05, + "loss": 3.4169, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8600244502782104e-05, + "loss": 3.4256, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591858555271584e-05, + "loss": 3.4288, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583472607761067e-05, + "loss": 3.4329, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8575086660250544e-05, + "loss": 3.4232, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566717091543756e-05, + "loss": 3.4174, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8558331144033236e-05, + "loss": 3.4211, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8549945196522716e-05, + "loss": 3.4292, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8541559249012193e-05, + "loss": 3.4199, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.853318968030541e-05, + "loss": 3.4191, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.852480373279489e-05, + "loss": 3.4119, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516417785284365e-05, + "loss": 3.4117, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8508031837773845e-05, + "loss": 3.4142, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499662269067057e-05, + "loss": 3.4288, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8491276321556537e-05, + "loss": 3.4269, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8482890374046017e-05, + "loss": 3.4264, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8474504426535497e-05, + "loss": 3.4164, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.846613485782871e-05, + "loss": 3.4208, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.845774891031819e-05, + "loss": 3.4275, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8449362962807666e-05, + "loss": 3.4107, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440977015297146e-05, + "loss": 3.4143, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8432607446590362e-05, + "loss": 3.4121, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.842422149907984e-05, + "loss": 3.4168, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.841583555156932e-05, + "loss": 3.4242, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.84074496040588e-05, + "loss": 3.4201, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.839908003535201e-05, + "loss": 3.4131, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.839069408784149e-05, + "loss": 3.4254, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.838230814033097e-05, + "loss": 3.4201, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837392219282045e-05, + "loss": 3.4185, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8365552624113663e-05, + "loss": 3.4093, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.835716667660314e-05, + "loss": 3.392, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.834878072909262e-05, + "loss": 3.4313, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.83403947815821e-05, + "loss": 3.412, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8332025212875312e-05, + "loss": 3.428, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323639265364792e-05, + "loss": 3.408, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8315253317854272e-05, + "loss": 3.4128, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8306867370343752e-05, + "loss": 3.4058, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.829849780163696e-05, + "loss": 3.4133, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8290111854126445e-05, + "loss": 3.4126, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281725906615925e-05, + "loss": 3.4157, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273339959105405e-05, + "loss": 3.4305, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264970390398614e-05, + "loss": 3.4085, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256584442888094e-05, + "loss": 3.4087, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8248198495377574e-05, + "loss": 3.4262, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239812547867054e-05, + "loss": 3.4106, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8231442979160266e-05, + "loss": 3.4059, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8223057031649746e-05, + "loss": 3.4212, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214671084139226e-05, + "loss": 3.4133, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206285136628706e-05, + "loss": 3.4056, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197915567921915e-05, + "loss": 3.4171, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.81895296204114e-05, + "loss": 3.4073, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.818114367290088e-05, + "loss": 3.4082, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8172757725390358e-05, + "loss": 3.4204, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164388156683567e-05, + "loss": 3.4169, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8156002209173047e-05, + "loss": 3.4217, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814763264046626e-05, + "loss": 3.4187, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813924669295574e-05, + "loss": 3.4353, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.813086074544522e-05, + "loss": 3.409, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.81224747979347e-05, + "loss": 3.4288, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.811408885042418e-05, + "loss": 3.4152, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.810570290291366e-05, + "loss": 3.4166, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.809733333420687e-05, + "loss": 3.4146, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088947386696352e-05, + "loss": 3.4269, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080561439185832e-05, + "loss": 3.423, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8072175491675312e-05, + "loss": 3.4272, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806378954416479e-05, + "loss": 3.4041, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.805540359665427e-05, + "loss": 3.4039, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.804701764914375e-05, + "loss": 3.4205, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.803863170163323e-05, + "loss": 3.426, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.803026213292644e-05, + "loss": 3.4179, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.802187618541592e-05, + "loss": 3.4219, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.80134902379054e-05, + "loss": 3.4078, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.800510429039488e-05, + "loss": 3.4148, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.799673472168809e-05, + "loss": 3.4138, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.798834877417757e-05, + "loss": 3.4108, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979962826667053e-05, + "loss": 3.4239, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971576879156533e-05, + "loss": 3.4313, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7963207310449742e-05, + "loss": 3.4276, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7954821362939222e-05, + "loss": 3.4106, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7946435415428702e-05, + "loss": 3.4123, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7938049467918182e-05, + "loss": 3.4154, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7929679899211395e-05, + "loss": 3.4217, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7921293951700874e-05, + "loss": 3.4157, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912908004190354e-05, + "loss": 3.4232, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904538435483564e-05, + "loss": 3.4179, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7896152487973043e-05, + "loss": 3.4106, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7887766540462523e-05, + "loss": 3.4134, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7879380592952007e-05, + "loss": 3.408, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7871011024245216e-05, + "loss": 3.4111, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862625076734696e-05, + "loss": 3.4183, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7854239129224176e-05, + "loss": 3.4179, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845853181713656e-05, + "loss": 3.4089, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837483613006868e-05, + "loss": 3.4109, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7829097665496348e-05, + "loss": 3.4027, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7820711717985828e-05, + "loss": 3.4191, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7812325770475308e-05, + "loss": 3.4077, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803956201768517e-05, + "loss": 3.4309, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7795570254257997e-05, + "loss": 3.4251, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7787184306747477e-05, + "loss": 3.4263, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777881473804069e-05, + "loss": 3.4131, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.777042879053017e-05, + "loss": 3.4111, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.776204284301965e-05, + "loss": 3.4199, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.775365689550913e-05, + "loss": 3.4159, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.774527094799861e-05, + "loss": 3.4091, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.773688500048809e-05, + "loss": 3.4068, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772849905297757e-05, + "loss": 3.4167, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.7720129484270782e-05, + "loss": 3.4126, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.7711743536760262e-05, + "loss": 3.4125, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7703357589249742e-05, + "loss": 3.4079, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694971641739218e-05, + "loss": 3.4154, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686585694228698e-05, + "loss": 3.41, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7678216125521914e-05, + "loss": 3.4219, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766983017801139e-05, + "loss": 3.416, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.766144423050087e-05, + "loss": 3.4331, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7653074661794083e-05, + "loss": 3.4056, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7644688714283563e-05, + "loss": 3.4243, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.763630276677304e-05, + "loss": 3.4144, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627916819262523e-05, + "loss": 3.4224, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619530871752003e-05, + "loss": 3.4196, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7611161303045212e-05, + "loss": 3.4119, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602775355534692e-05, + "loss": 3.4146, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7594389408024172e-05, + "loss": 3.4346, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7586003460513652e-05, + "loss": 3.4058, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7577633891806864e-05, + "loss": 3.4211, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7569247944296344e-05, + "loss": 3.419, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560861996785824e-05, + "loss": 3.417, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552476049275304e-05, + "loss": 3.4116, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7544106480568513e-05, + "loss": 3.4144, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7535720533057993e-05, + "loss": 3.4193, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7527334585547477e-05, + "loss": 3.4112, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518965016840686e-05, + "loss": 3.4152, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.855832576751709, + "eval_runtime": 306.3042, + "eval_samples_per_second": 1245.791, + "eval_steps_per_second": 38.932, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510579069330166e-05, + "loss": 3.4063, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7502193121819646e-05, + "loss": 3.4087, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493807174309126e-05, + "loss": 3.4113, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485421226798606e-05, + "loss": 3.423, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7477051658091818e-05, + "loss": 3.4276, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468665710581298e-05, + "loss": 3.4121, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7460279763070778e-05, + "loss": 3.4089, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451893815560258e-05, + "loss": 3.4093, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7443524246853467e-05, + "loss": 3.4057, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7435138299342947e-05, + "loss": 3.4244, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.742675235183243e-05, + "loss": 3.4068, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741836640432191e-05, + "loss": 3.416, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.740999683561512e-05, + "loss": 3.4182, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.74016108881046e-05, + "loss": 3.4029, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.739322494059408e-05, + "loss": 3.4048, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.738483899308356e-05, + "loss": 3.4041, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376469424376772e-05, + "loss": 3.4097, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736808347686625e-05, + "loss": 3.4079, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.735969752935573e-05, + "loss": 3.4077, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.735131158184521e-05, + "loss": 3.4168, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.734294201313842e-05, + "loss": 3.4183, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.73345560656279e-05, + "loss": 3.4204, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7326170118117384e-05, + "loss": 3.4152, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317784170606864e-05, + "loss": 3.408, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7309414601900073e-05, + "loss": 3.4146, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7301028654389553e-05, + "loss": 3.4179, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7292642706879033e-05, + "loss": 3.4069, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7284256759368513e-05, + "loss": 3.4114, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275887190661725e-05, + "loss": 3.4046, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267501243151205e-05, + "loss": 3.3995, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7259115295640685e-05, + "loss": 3.4052, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7250729348130165e-05, + "loss": 3.4151, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7242359779423374e-05, + "loss": 3.4189, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233973831912854e-05, + "loss": 3.4126, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7225587884402338e-05, + "loss": 3.4107, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7217201936891814e-05, + "loss": 3.4063, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208848746988756e-05, + "loss": 3.4229, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200462799478236e-05, + "loss": 3.403, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7192076851967716e-05, + "loss": 3.4027, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.71836909044572e-05, + "loss": 3.401, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717530495694668e-05, + "loss": 3.4074, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.716691900943616e-05, + "loss": 3.4071, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.715853306192564e-05, + "loss": 3.4123, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7150147114415116e-05, + "loss": 3.4088, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141777545708328e-05, + "loss": 3.4126, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133391598197808e-05, + "loss": 3.41, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7125005650687288e-05, + "loss": 3.4047, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116619703176768e-05, + "loss": 3.4026, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.710825013446998e-05, + "loss": 3.383, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709986418695946e-05, + "loss": 3.4195, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7091478239448937e-05, + "loss": 3.4004, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7083092291938417e-05, + "loss": 3.417, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074722723231633e-05, + "loss": 3.4042, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7066336775721113e-05, + "loss": 3.4013, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.705795082821059e-05, + "loss": 3.3919, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.704956488070007e-05, + "loss": 3.4045, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.704119531199328e-05, + "loss": 3.4057, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.703280936448276e-05, + "loss": 3.3989, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.702442341697224e-05, + "loss": 3.4191, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701603746946172e-05, + "loss": 3.4024, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7007667900754934e-05, + "loss": 3.393, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699928195324441e-05, + "loss": 3.4142, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.699089600573389e-05, + "loss": 3.4026, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.698251005822337e-05, + "loss": 3.3966, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6974140489516583e-05, + "loss": 3.4109, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965754542006063e-05, + "loss": 3.4029, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6957368594495543e-05, + "loss": 3.3949, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6948982646985023e-05, + "loss": 3.4077, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6940613078278232e-05, + "loss": 3.3965, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6932227130767715e-05, + "loss": 3.396, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923841183257195e-05, + "loss": 3.4078, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6915455235746675e-05, + "loss": 3.4103, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6907085667039884e-05, + "loss": 3.4112, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898699719529364e-05, + "loss": 3.404, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6890313772018844e-05, + "loss": 3.426, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881927824508324e-05, + "loss": 3.4001, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873558255801537e-05, + "loss": 3.4156, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6865172308291017e-05, + "loss": 3.407, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856786360780497e-05, + "loss": 3.4041, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848416792073706e-05, + "loss": 3.4013, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6840030844563186e-05, + "loss": 3.4184, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.683164489705267e-05, + "loss": 3.4091, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.682325894954215e-05, + "loss": 3.4199, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.681487300203163e-05, + "loss": 3.393, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.680648705452111e-05, + "loss": 3.3924, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.679810110701059e-05, + "loss": 3.4089, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789715159500065e-05, + "loss": 3.418, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6781345590793278e-05, + "loss": 3.407, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.677295964328276e-05, + "loss": 3.4092, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6764573695772238e-05, + "loss": 3.4032, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6756187748261718e-05, + "loss": 3.4008, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.674781817955493e-05, + "loss": 3.4056, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.673943223204441e-05, + "loss": 3.4024, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6731046284533887e-05, + "loss": 3.411, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.672266033702337e-05, + "loss": 3.4215, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6714290768316583e-05, + "loss": 3.4194, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6705904820806063e-05, + "loss": 3.3999, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.669751887329554e-05, + "loss": 3.4004, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.668913292578502e-05, + "loss": 3.4057, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.668076335707823e-05, + "loss": 3.4103, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.667237740956771e-05, + "loss": 3.4093, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.666399146205719e-05, + "loss": 3.413, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665560551454667e-05, + "loss": 3.407, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6647235945839884e-05, + "loss": 3.4004, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.663884999832936e-05, + "loss": 3.403, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.663046405081884e-05, + "loss": 3.399, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6622078103308324e-05, + "loss": 3.4017, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613708534601536e-05, + "loss": 3.4061, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6605322587091013e-05, + "loss": 3.4078, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596936639580493e-05, + "loss": 3.3964, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6588567070873705e-05, + "loss": 3.4023, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6580181123363185e-05, + "loss": 3.3912, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6571795175852665e-05, + "loss": 3.4111, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6563409228342145e-05, + "loss": 3.4043, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6555023280831625e-05, + "loss": 3.4161, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6546653712124834e-05, + "loss": 3.418, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6538267764614314e-05, + "loss": 3.4174, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652989819590753e-05, + "loss": 3.4045, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.652151224839701e-05, + "loss": 3.4037, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6513126300886487e-05, + "loss": 3.4082, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504740353375966e-05, + "loss": 3.4102, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6496354405865446e-05, + "loss": 3.4, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487968458354926e-05, + "loss": 3.395, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6479582510844406e-05, + "loss": 3.4096, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6471196563333886e-05, + "loss": 3.4009, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.64628269946271e-05, + "loss": 3.4019, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.645444104711658e-05, + "loss": 3.3963, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.644605509960606e-05, + "loss": 3.4083, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.643766915209554e-05, + "loss": 3.3947, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6429299583388748e-05, + "loss": 3.414, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.642091363587823e-05, + "loss": 3.4064, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.641252768836771e-05, + "loss": 3.4204, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.640415811966092e-05, + "loss": 3.3935, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.63957721721504e-05, + "loss": 3.4132, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.638738622463988e-05, + "loss": 3.4113, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.637900027712936e-05, + "loss": 3.4074, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370630708422572e-05, + "loss": 3.4092, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6362244760912052e-05, + "loss": 3.4018, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6353858813401532e-05, + "loss": 3.4044, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6345472865891012e-05, + "loss": 3.4208, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.633710329718422e-05, + "loss": 3.3987, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.63287173496737e-05, + "loss": 3.4104, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6320347780966914e-05, + "loss": 3.4103, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6311961833456394e-05, + "loss": 3.4042, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6303575885945874e-05, + "loss": 3.4028, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6295189938435354e-05, + "loss": 3.4051, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6286803990924834e-05, + "loss": 3.4086, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627841804341431e-05, + "loss": 3.407, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6270032095903794e-05, + "loss": 3.3995, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.857192039489746, + "eval_runtime": 309.1054, + "eval_samples_per_second": 1234.501, + "eval_steps_per_second": 38.579, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.6261646148393274e-05, + "loss": 3.3983, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.6253276579686486e-05, + "loss": 3.3986, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6244890632175963e-05, + "loss": 3.4003, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6236504684665443e-05, + "loss": 3.4112, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6228118737154923e-05, + "loss": 3.4173, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6219749168448135e-05, + "loss": 3.4042, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6211363220937615e-05, + "loss": 3.4012, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6202977273427095e-05, + "loss": 3.3987, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.6194591325916575e-05, + "loss": 3.3959, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.6186221757209784e-05, + "loss": 3.4114, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.6177835809699264e-05, + "loss": 3.3998, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6169449862188747e-05, + "loss": 3.4068, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6161063914678227e-05, + "loss": 3.4074, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6152694345971436e-05, + "loss": 3.3914, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6144308398460916e-05, + "loss": 3.3983, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6135922450950396e-05, + "loss": 3.3875, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6127536503439876e-05, + "loss": 3.404, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.611916693473309e-05, + "loss": 3.3989, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.611078098722257e-05, + "loss": 3.3959, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.610239503971205e-05, + "loss": 3.4059, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6094025471005258e-05, + "loss": 3.4087, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6085639523494738e-05, + "loss": 3.4101, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.6077253575984218e-05, + "loss": 3.4068, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.60688676284737e-05, + "loss": 3.4002, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.606049805976691e-05, + "loss": 3.4049, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.605211211225639e-05, + "loss": 3.405, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.604372616474587e-05, + "loss": 3.3934, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.603534021723535e-05, + "loss": 3.4031, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6026970648528562e-05, + "loss": 3.3955, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6018584701018042e-05, + "loss": 3.3901, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6010198753507522e-05, + "loss": 3.3966, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.6001812805997002e-05, + "loss": 3.405, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.599344323729021e-05, + "loss": 3.4023, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.598505728977969e-05, + "loss": 3.4134, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.597667134226917e-05, + "loss": 3.3952, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5968285394758655e-05, + "loss": 3.4005, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959915826051864e-05, + "loss": 3.4103, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.5951529878541344e-05, + "loss": 3.3904, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.5943143931030824e-05, + "loss": 3.3966, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.5934757983520304e-05, + "loss": 3.3899, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5926388414813516e-05, + "loss": 3.3992, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5918002467302996e-05, + "loss": 3.3981, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5909616519792476e-05, + "loss": 3.4001, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5901230572281956e-05, + "loss": 3.4008, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.5892861003575165e-05, + "loss": 3.3998, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.5884475056064645e-05, + "loss": 3.4065, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.5876089108554125e-05, + "loss": 3.3915, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5867703161043608e-05, + "loss": 3.3956, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5859333592336817e-05, + "loss": 3.3717, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5850947644826297e-05, + "loss": 3.4096, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5842561697315777e-05, + "loss": 3.3913, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5834175749805257e-05, + "loss": 3.4054, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.582580618109847e-05, + "loss": 3.3978, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.581742023358795e-05, + "loss": 3.3909, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.580903428607743e-05, + "loss": 3.3821, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.580064833856691e-05, + "loss": 3.3916, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.579227876986012e-05, + "loss": 3.3982, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.57838928223496e-05, + "loss": 3.3868, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.577550687483908e-05, + "loss": 3.4095, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5767120927328562e-05, + "loss": 3.3981, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.575875135862177e-05, + "loss": 3.379, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.575036541111125e-05, + "loss": 3.4065, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.574197946360073e-05, + "loss": 3.3938, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5733593516090208e-05, + "loss": 3.3863, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5725223947383423e-05, + "loss": 3.3996, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.5716837999872903e-05, + "loss": 3.3941, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5708452052362383e-05, + "loss": 3.3851, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.570006610485186e-05, + "loss": 3.399, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5691696536145072e-05, + "loss": 3.388, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5683310588634552e-05, + "loss": 3.3848, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674924641124032e-05, + "loss": 3.4033, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5666538693613512e-05, + "loss": 3.3968, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5658169124906725e-05, + "loss": 3.4006, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5649799556199934e-05, + "loss": 3.3968, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5641413608689414e-05, + "loss": 3.4089, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5633027661178894e-05, + "loss": 3.396, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5624641713668374e-05, + "loss": 3.4071, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5616255766157857e-05, + "loss": 3.3955, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5607869818647334e-05, + "loss": 3.3949, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5599500249940546e-05, + "loss": 3.3933, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5591114302430026e-05, + "loss": 3.4063, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.5582728354919503e-05, + "loss": 3.4014, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5574342407408986e-05, + "loss": 3.4096, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5565956459898466e-05, + "loss": 3.3847, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5557570512387946e-05, + "loss": 3.3816, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5549184564877426e-05, + "loss": 3.4006, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5540798617366906e-05, + "loss": 3.4056, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.5532429048660115e-05, + "loss": 3.3953, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.5524043101149595e-05, + "loss": 3.4025, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.5515657153639078e-05, + "loss": 3.3938, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.5507271206128558e-05, + "loss": 3.3876, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.5498901637421767e-05, + "loss": 3.3935, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5490515689911247e-05, + "loss": 3.3942, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5482129742400727e-05, + "loss": 3.4024, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5473743794890207e-05, + "loss": 3.4065, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.546537422618342e-05, + "loss": 3.4132, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.54569882786729e-05, + "loss": 3.3849, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.544860233116238e-05, + "loss": 3.395, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.544021638365186e-05, + "loss": 3.3961, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.543184681494507e-05, + "loss": 3.4024, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.542346086743455e-05, + "loss": 3.3966, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5415074919924032e-05, + "loss": 3.4034, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5406688972413512e-05, + "loss": 3.3964, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.539831940370672e-05, + "loss": 3.3925, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.53899334561962e-05, + "loss": 3.3952, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.538154750868568e-05, + "loss": 3.3857, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5373161561175157e-05, + "loss": 3.3921, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5364791992468373e-05, + "loss": 3.3952, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5356406044957853e-05, + "loss": 3.3994, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5348020097447333e-05, + "loss": 3.3872, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.533963414993681e-05, + "loss": 3.3953, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5331264581230022e-05, + "loss": 3.3783, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5322878633719502e-05, + "loss": 3.4044, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5314492686208985e-05, + "loss": 3.3902, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5306123117502195e-05, + "loss": 3.4049, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5297737169991675e-05, + "loss": 3.4035, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5289351222481155e-05, + "loss": 3.4064, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5280981653774364e-05, + "loss": 3.3945, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5272595706263847e-05, + "loss": 3.3911, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5264209758753327e-05, + "loss": 3.4034, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5255823811242805e-05, + "loss": 3.3971, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5247437863732283e-05, + "loss": 3.392, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5239051916221763e-05, + "loss": 3.387, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5230665968711243e-05, + "loss": 3.3972, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5222280021200725e-05, + "loss": 3.389, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5213910452493934e-05, + "loss": 3.3958, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5205524504983416e-05, + "loss": 3.3858, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5197138557472896e-05, + "loss": 3.3974, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5188752609962376e-05, + "loss": 3.3849, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5180383041255586e-05, + "loss": 3.4062, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171997093745066e-05, + "loss": 3.3943, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5163611146234546e-05, + "loss": 3.4116, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5155241577527757e-05, + "loss": 3.3851, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5146855630017237e-05, + "loss": 3.4027, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5138469682506717e-05, + "loss": 3.3979, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5130083734996197e-05, + "loss": 3.3966, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5121714166289408e-05, + "loss": 3.4, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5113328218778888e-05, + "loss": 3.3903, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.510494227126837e-05, + "loss": 3.3968, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.509655632375785e-05, + "loss": 3.4075, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5088186755051058e-05, + "loss": 3.3921, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.507980080754054e-05, + "loss": 3.3991, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.507141486003002e-05, + "loss": 3.3992, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.50630289125195e-05, + "loss": 3.395, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.505465934381271e-05, + "loss": 3.3961, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.504627339630219e-05, + "loss": 3.3941, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.503788744879167e-05, + "loss": 3.3962, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.502950150128115e-05, + "loss": 3.3961, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5021131932574361e-05, + "loss": 3.3901, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.8578240871429443, + "eval_runtime": 303.7722, + "eval_samples_per_second": 1256.175, + "eval_steps_per_second": 39.256, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012745985063841e-05, + "loss": 3.4011, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5004360037553321e-05, + "loss": 3.3807, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995974090042803e-05, + "loss": 3.3927, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4987588142532283e-05, + "loss": 3.4028, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4979218573825494e-05, + "loss": 3.402, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970832626314974e-05, + "loss": 3.3948, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962446678804454e-05, + "loss": 3.3937, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4954060731293934e-05, + "loss": 3.3895, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945691162587144e-05, + "loss": 3.3862, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4937305215076624e-05, + "loss": 3.395, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928919267566104e-05, + "loss": 3.3949, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920533320055583e-05, + "loss": 3.3967, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4912163751348795e-05, + "loss": 3.3988, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903777803838275e-05, + "loss": 3.3813, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4895391856327757e-05, + "loss": 3.3869, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4887005908817233e-05, + "loss": 3.3784, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4878636340110447e-05, + "loss": 3.3935, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4870250392599927e-05, + "loss": 3.3899, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4861864445089407e-05, + "loss": 3.3857, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4853478497578886e-05, + "loss": 3.3949, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4845108928872098e-05, + "loss": 3.3965, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4836722981361578e-05, + "loss": 3.4008, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4828337033851056e-05, + "loss": 3.3964, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819951086340536e-05, + "loss": 3.3893, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4811581517633749e-05, + "loss": 3.3989, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4803195570123229e-05, + "loss": 3.3965, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4794809622612707e-05, + "loss": 3.3877, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4786423675102187e-05, + "loss": 3.392, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4778054106395401e-05, + "loss": 3.3856, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4769668158884881e-05, + "loss": 3.3802, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4761282211374358e-05, + "loss": 3.3907, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.475289626386384e-05, + "loss": 3.3938, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4744526695157052e-05, + "loss": 3.3912, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4736140747646528e-05, + "loss": 3.4008, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.472775480013601e-05, + "loss": 3.3884, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.471936885262549e-05, + "loss": 3.3903, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4710999283918702e-05, + "loss": 3.399, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.470261333640818e-05, + "loss": 3.3806, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.469422738889766e-05, + "loss": 3.3846, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.468584144138714e-05, + "loss": 3.3857, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4677471872680355e-05, + "loss": 3.3836, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4669085925169831e-05, + "loss": 3.3874, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660699977659311e-05, + "loss": 3.3926, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4652314030148793e-05, + "loss": 3.3921, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4643944461442002e-05, + "loss": 3.3875, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635558513931482e-05, + "loss": 3.3957, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4627172566420964e-05, + "loss": 3.3848, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618786618910444e-05, + "loss": 3.3854, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4610417050203654e-05, + "loss": 3.3637, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4602031102693134e-05, + "loss": 3.396, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593645155182614e-05, + "loss": 3.3809, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4585259207672094e-05, + "loss": 3.3933, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576889638965305e-05, + "loss": 3.385, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568503691454785e-05, + "loss": 3.3831, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4560117743944265e-05, + "loss": 3.3737, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551731796433745e-05, + "loss": 3.3814, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4543362227726956e-05, + "loss": 3.3927, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534976280216436e-05, + "loss": 3.3747, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4526590332705917e-05, + "loss": 3.401, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4518204385195397e-05, + "loss": 3.3851, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4509834816488608e-05, + "loss": 3.3692, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4501448868978088e-05, + "loss": 3.395, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4493062921467568e-05, + "loss": 3.3819, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4484676973957048e-05, + "loss": 3.3819, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4476307405250259e-05, + "loss": 3.3816, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4467921457739739e-05, + "loss": 3.3855, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4459535510229219e-05, + "loss": 3.3796, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.445116594152243e-05, + "loss": 3.3896, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.444277999401191e-05, + "loss": 3.3765, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.443439404650139e-05, + "loss": 3.3782, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4426008098990871e-05, + "loss": 3.3907, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.441763853028408e-05, + "loss": 3.3878, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.440925258277356e-05, + "loss": 3.3907, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400866635263042e-05, + "loss": 3.3845, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4392480687752522e-05, + "loss": 3.4031, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4384111119045732e-05, + "loss": 3.3848, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4375725171535212e-05, + "loss": 3.3982, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4367339224024692e-05, + "loss": 3.3842, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4358953276514172e-05, + "loss": 3.3877, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4350583707807383e-05, + "loss": 3.3808, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4342197760296863e-05, + "loss": 3.3948, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333811812786343e-05, + "loss": 3.3917, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4325425865275825e-05, + "loss": 3.3982, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4317039917765305e-05, + "loss": 3.3783, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308653970254781e-05, + "loss": 3.3738, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4300268022744263e-05, + "loss": 3.3859, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291882075233743e-05, + "loss": 3.3956, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283512506526952e-05, + "loss": 3.3871, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4275126559016434e-05, + "loss": 3.3918, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4266740611505913e-05, + "loss": 3.3848, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4258354663995393e-05, + "loss": 3.3801, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249985095288604e-05, + "loss": 3.3856, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4241599147778084e-05, + "loss": 3.382, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4233213200267564e-05, + "loss": 3.3926, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4224827252757044e-05, + "loss": 3.4003, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4216457684050255e-05, + "loss": 3.4007, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4208071736539735e-05, + "loss": 3.378, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199685789029216e-05, + "loss": 3.3841, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4191299841518696e-05, + "loss": 3.3872, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182930272811906e-05, + "loss": 3.3901, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4174544325301387e-05, + "loss": 3.3913, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4166158377790867e-05, + "loss": 3.3929, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4157772430280347e-05, + "loss": 3.3844, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4149402861573558e-05, + "loss": 3.3815, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4141016914063038e-05, + "loss": 3.3917, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4132630966552518e-05, + "loss": 3.3709, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4124245019041998e-05, + "loss": 3.3819, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4115875450335209e-05, + "loss": 3.3858, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4107489502824688e-05, + "loss": 3.3886, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4099103555314168e-05, + "loss": 3.3778, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.409071760780365e-05, + "loss": 3.3883, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.408234803909686e-05, + "loss": 3.3656, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4073962091586341e-05, + "loss": 3.3922, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.406557614407582e-05, + "loss": 3.3873, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.405720657536903e-05, + "loss": 3.3903, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4048820627858512e-05, + "loss": 3.3973, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4040434680347992e-05, + "loss": 3.3988, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4032065111641202e-05, + "loss": 3.3845, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4023679164130682e-05, + "loss": 3.3834, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4015293216620162e-05, + "loss": 3.391, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006907269109642e-05, + "loss": 3.3853, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3998521321599122e-05, + "loss": 3.3796, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3990135374088604e-05, + "loss": 3.3789, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.398174942657808e-05, + "loss": 3.3839, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.397336347906756e-05, + "loss": 3.3839, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964993910360774e-05, + "loss": 3.3829, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956607962850254e-05, + "loss": 3.3798, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3948222015339733e-05, + "loss": 3.3837, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939836067829213e-05, + "loss": 3.3739, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3931466499122425e-05, + "loss": 3.3948, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3923080551611905e-05, + "loss": 3.3837, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914694604101383e-05, + "loss": 3.4018, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3906325035394596e-05, + "loss": 3.3724, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897939087884076e-05, + "loss": 3.3957, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3889553140373554e-05, + "loss": 3.3904, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3881167192863034e-05, + "loss": 3.3851, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3872797624156248e-05, + "loss": 3.3885, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3864411676645728e-05, + "loss": 3.3815, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3856025729135205e-05, + "loss": 3.3899, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3847639781624686e-05, + "loss": 3.3951, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3839270212917899e-05, + "loss": 3.3791, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830884265407379e-05, + "loss": 3.3912, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.382251469670059e-05, + "loss": 3.39, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.381412874919007e-05, + "loss": 3.3853, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.380574280167955e-05, + "loss": 3.3845, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3797356854169028e-05, + "loss": 3.389, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788970906658508e-05, + "loss": 3.3821, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3780584959147988e-05, + "loss": 3.3894, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3772199011637468e-05, + "loss": 3.3801, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.8582446575164795, + "eval_runtime": 305.7393, + "eval_samples_per_second": 1248.093, + "eval_steps_per_second": 39.004, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.376381306412695e-05, + "loss": 3.3888, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3755443495420158e-05, + "loss": 3.3739, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.374705754790964e-05, + "loss": 3.3807, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.373867160039912e-05, + "loss": 3.3984, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.37302856528886e-05, + "loss": 3.3892, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.372191608418181e-05, + "loss": 3.3868, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.371353013667129e-05, + "loss": 3.3855, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.370514418916077e-05, + "loss": 3.3784, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.369675824165025e-05, + "loss": 3.3762, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3688388672943461e-05, + "loss": 3.3904, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3680002725432941e-05, + "loss": 3.3815, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3671616777922421e-05, + "loss": 3.3832, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3663230830411903e-05, + "loss": 3.3912, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3654861261705112e-05, + "loss": 3.3711, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3646475314194592e-05, + "loss": 3.3756, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3638089366684074e-05, + "loss": 3.3701, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3629703419173554e-05, + "loss": 3.3853, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3621333850466764e-05, + "loss": 3.3787, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3612947902956244e-05, + "loss": 3.3766, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3604561955445724e-05, + "loss": 3.3803, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3596176007935204e-05, + "loss": 3.3909, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3587806439228415e-05, + "loss": 3.3883, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3579420491717895e-05, + "loss": 3.3879, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3571034544207375e-05, + "loss": 3.3806, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3562648596696857e-05, + "loss": 3.3874, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3554279027990066e-05, + "loss": 3.381, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3545893080479546e-05, + "loss": 3.3802, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3537507132969027e-05, + "loss": 3.384, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3529137564262236e-05, + "loss": 3.3736, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3520751616751718e-05, + "loss": 3.3677, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3512365669241198e-05, + "loss": 3.3781, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3503979721730678e-05, + "loss": 3.3825, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3495610153023889e-05, + "loss": 3.3855, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.3487224205513369e-05, + "loss": 3.3903, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3478838258002849e-05, + "loss": 3.3783, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3470452310492329e-05, + "loss": 3.3826, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.346208274178554e-05, + "loss": 3.3916, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.345369679427502e-05, + "loss": 3.365, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.34453108467645e-05, + "loss": 3.3787, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3436924899253978e-05, + "loss": 3.3766, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.342855533054719e-05, + "loss": 3.3736, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.3420169383036672e-05, + "loss": 3.3774, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3411783435526152e-05, + "loss": 3.3831, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3403397488015628e-05, + "loss": 3.3858, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3395027919308842e-05, + "loss": 3.376, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3386641971798322e-05, + "loss": 3.3838, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3378256024287802e-05, + "loss": 3.3764, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.336987007677728e-05, + "loss": 3.373, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3361500508070493e-05, + "loss": 3.3574, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3353114560559973e-05, + "loss": 3.3868, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3344728613049451e-05, + "loss": 3.3735, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3336342665538931e-05, + "loss": 3.3827, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3327973096832144e-05, + "loss": 3.3759, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3319587149321625e-05, + "loss": 3.3693, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3311201201811102e-05, + "loss": 3.3651, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3302815254300582e-05, + "loss": 3.3729, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3294445685593796e-05, + "loss": 3.3859, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3286059738083276e-05, + "loss": 3.3637, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3277673790572753e-05, + "loss": 3.3925, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3269287843062234e-05, + "loss": 3.3788, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3260918274355447e-05, + "loss": 3.3602, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3252532326844925e-05, + "loss": 3.386, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3244146379334405e-05, + "loss": 3.3702, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3235760431823885e-05, + "loss": 3.3761, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3227390863117097e-05, + "loss": 3.3684, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3219004915606576e-05, + "loss": 3.3801, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3210618968096056e-05, + "loss": 3.3659, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3202233020585536e-05, + "loss": 3.3818, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.319386345187875e-05, + "loss": 3.3646, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3185477504368226e-05, + "loss": 3.3699, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3177091556857706e-05, + "loss": 3.3756, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3168705609347188e-05, + "loss": 3.3854, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.3160336040640397e-05, + "loss": 3.3767, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3151950093129877e-05, + "loss": 3.3779, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3143564145619359e-05, + "loss": 3.3926, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.3135178198108839e-05, + "loss": 3.3744, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.312680862940205e-05, + "loss": 3.3852, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.311842268189153e-05, + "loss": 3.3771, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.311003673438101e-05, + "loss": 3.3765, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3101667165674222e-05, + "loss": 3.3768, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.30932812181637e-05, + "loss": 3.3791, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.308489527065318e-05, + "loss": 3.3824, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.307650932314266e-05, + "loss": 3.3844, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3068123375632142e-05, + "loss": 3.376, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3059737428121622e-05, + "loss": 3.3612, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3051351480611102e-05, + "loss": 3.3769, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.304296553310058e-05, + "loss": 3.3826, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3034595964393792e-05, + "loss": 3.38, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3026210016883272e-05, + "loss": 3.3829, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3017824069372752e-05, + "loss": 3.3749, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.300943812186223e-05, + "loss": 3.3689, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.3001068553155443e-05, + "loss": 3.3754, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2992682605644923e-05, + "loss": 3.3715, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2984296658134401e-05, + "loss": 3.3864, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2975910710623881e-05, + "loss": 3.3837, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2967541141917095e-05, + "loss": 3.3924, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2959155194406575e-05, + "loss": 3.3696, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2950769246896052e-05, + "loss": 3.3767, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2942383299385533e-05, + "loss": 3.3776, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2934013730678746e-05, + "loss": 3.3776, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2925627783168226e-05, + "loss": 3.3845, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2917241835657704e-05, + "loss": 3.3776, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2908855888147184e-05, + "loss": 3.376, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2900486319440397e-05, + "loss": 3.3719, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2892100371929875e-05, + "loss": 3.3845, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2883714424419355e-05, + "loss": 3.3604, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2875344855712567e-05, + "loss": 3.3711, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2866958908202047e-05, + "loss": 3.3772, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2858572960691526e-05, + "loss": 3.3805, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2850187013181005e-05, + "loss": 3.368, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.284181744447422e-05, + "loss": 3.379, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.28334314969637e-05, + "loss": 3.3586, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2825045549453176e-05, + "loss": 3.3832, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2816659601942658e-05, + "loss": 3.373, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.280829003323587e-05, + "loss": 3.3782, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2799904085725349e-05, + "loss": 3.3901, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2791518138214829e-05, + "loss": 3.3874, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2783148569508041e-05, + "loss": 3.374, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2774762621997521e-05, + "loss": 3.3755, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2766376674487e-05, + "loss": 3.3801, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.275799072697648e-05, + "loss": 3.3719, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2749604779465959e-05, + "loss": 3.3745, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2741218831955439e-05, + "loss": 3.3691, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.273283288444492e-05, + "loss": 3.377, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.27244469369344e-05, + "loss": 3.3687, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.2716077368227611e-05, + "loss": 3.3722, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2707691420717091e-05, + "loss": 3.3731, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2699305473206571e-05, + "loss": 3.3733, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2690919525696051e-05, + "loss": 3.3678, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2682549956989262e-05, + "loss": 3.3876, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2674164009478742e-05, + "loss": 3.3764, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2665778061968222e-05, + "loss": 3.391, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2657392114457704e-05, + "loss": 3.3709, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2649022545750913e-05, + "loss": 3.3833, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2640636598240393e-05, + "loss": 3.3802, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2632250650729874e-05, + "loss": 3.3779, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2623864703219354e-05, + "loss": 3.3778, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.2615495134512565e-05, + "loss": 3.3731, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2607109187002045e-05, + "loss": 3.382, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2598723239491525e-05, + "loss": 3.3848, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2590353670784736e-05, + "loss": 3.3738, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2581967723274216e-05, + "loss": 3.3775, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2573581775763696e-05, + "loss": 3.3818, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2565195828253176e-05, + "loss": 3.3772, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2556826259546387e-05, + "loss": 3.3727, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2548440312035866e-05, + "loss": 3.3803, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2540054364525346e-05, + "loss": 3.3739, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.2531668417014828e-05, + "loss": 3.3814, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2523298848308037e-05, + "loss": 3.367, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.859243392944336, + "eval_runtime": 307.3518, + "eval_samples_per_second": 1241.545, + "eval_steps_per_second": 38.799, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2514912900797519e-05, + "loss": 3.3851, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2506526953286999e-05, + "loss": 3.3672, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2498141005776477e-05, + "loss": 3.3693, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2489755058265957e-05, + "loss": 3.3859, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2481385489559168e-05, + "loss": 3.3851, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2472999542048648e-05, + "loss": 3.3774, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2464613594538128e-05, + "loss": 3.3729, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2456227647027608e-05, + "loss": 3.3694, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2447858078320818e-05, + "loss": 3.3664, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.24394721308103e-05, + "loss": 3.3834, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.243108618329978e-05, + "loss": 3.3726, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2422700235789258e-05, + "loss": 3.3781, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.241433066708247e-05, + "loss": 3.3766, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.240594471957195e-05, + "loss": 3.3625, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.239755877206143e-05, + "loss": 3.3679, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2389172824550909e-05, + "loss": 3.3608, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2380803255844121e-05, + "loss": 3.3756, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2372417308333601e-05, + "loss": 3.3657, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2364031360823081e-05, + "loss": 3.3687, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2355645413312561e-05, + "loss": 3.3705, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2347275844605772e-05, + "loss": 3.3793, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2338889897095254e-05, + "loss": 3.3813, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2330503949584732e-05, + "loss": 3.378, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2322118002074212e-05, + "loss": 3.3733, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2313748433367424e-05, + "loss": 3.3818, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2305362485856904e-05, + "loss": 3.3695, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2296976538346383e-05, + "loss": 3.3677, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2288590590835863e-05, + "loss": 3.379, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2280221022129075e-05, + "loss": 3.3616, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2271835074618553e-05, + "loss": 3.3602, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2263449127108035e-05, + "loss": 3.3681, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2255063179597515e-05, + "loss": 3.371, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2246693610890726e-05, + "loss": 3.3793, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2238307663380206e-05, + "loss": 3.3801, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2229921715869686e-05, + "loss": 3.3654, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2221535768359166e-05, + "loss": 3.377, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2213166199652378e-05, + "loss": 3.3803, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2204780252141856e-05, + "loss": 3.3599, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2196394304631336e-05, + "loss": 3.3683, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2188008357120816e-05, + "loss": 3.3666, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2179638788414027e-05, + "loss": 3.3623, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2171252840903507e-05, + "loss": 3.3703, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2162866893392989e-05, + "loss": 3.3767, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.2154480945882469e-05, + "loss": 3.3698, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2146111377175678e-05, + "loss": 3.368, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.213772542966516e-05, + "loss": 3.3769, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.212933948215464e-05, + "loss": 3.3681, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2120953534644118e-05, + "loss": 3.3642, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.211258396593733e-05, + "loss": 3.3471, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.210419801842681e-05, + "loss": 3.3751, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.209581207091629e-05, + "loss": 3.3666, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.208742612340577e-05, + "loss": 3.3751, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2079072933502712e-05, + "loss": 3.3659, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2070686985992193e-05, + "loss": 3.3589, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2062301038481673e-05, + "loss": 3.3595, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2053915090971151e-05, + "loss": 3.3632, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2045529143460631e-05, + "loss": 3.3752, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2037143195950113e-05, + "loss": 3.3523, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2028757248439591e-05, + "loss": 3.3832, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2020371300929071e-05, + "loss": 3.3688, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2012001732222284e-05, + "loss": 3.3547, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2003615784711764e-05, + "loss": 3.3762, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1995229837201242e-05, + "loss": 3.3628, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1986843889690724e-05, + "loss": 3.3654, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1978474320983934e-05, + "loss": 3.3581, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1970088373473414e-05, + "loss": 3.3691, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1961702425962894e-05, + "loss": 3.3609, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1953316478452374e-05, + "loss": 3.363, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1944946909745585e-05, + "loss": 3.3608, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1936560962235065e-05, + "loss": 3.3606, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1928175014724545e-05, + "loss": 3.3646, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1919789067214025e-05, + "loss": 3.3811, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1911419498507237e-05, + "loss": 3.366, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1903033550996716e-05, + "loss": 3.3666, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1894647603486196e-05, + "loss": 3.3823, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1886261655975677e-05, + "loss": 3.3655, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1877892087268888e-05, + "loss": 3.3719, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1869506139758366e-05, + "loss": 3.3716, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1861120192247848e-05, + "loss": 3.3707, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.1852734244737328e-05, + "loss": 3.3645, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.1844364676030539e-05, + "loss": 3.3673, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1835978728520019e-05, + "loss": 3.3746, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1827592781009499e-05, + "loss": 3.3786, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.181922321230271e-05, + "loss": 3.3681, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.181083726479219e-05, + "loss": 3.3506, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.180245131728167e-05, + "loss": 3.3665, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.179406536977115e-05, + "loss": 3.3761, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.178569580106436e-05, + "loss": 3.3743, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.177730985355384e-05, + "loss": 3.371, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.176892390604332e-05, + "loss": 3.366, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1760537958532802e-05, + "loss": 3.3602, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.175216838982601e-05, + "loss": 3.3646, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1743782442315492e-05, + "loss": 3.3652, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1735396494804972e-05, + "loss": 3.3733, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.172701054729445e-05, + "loss": 3.3709, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1718640978587663e-05, + "loss": 3.3862, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1710255031077143e-05, + "loss": 3.3587, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1701869083566623e-05, + "loss": 3.3671, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1693483136056101e-05, + "loss": 3.37, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1685113567349314e-05, + "loss": 3.3701, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1676727619838794e-05, + "loss": 3.3714, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1668341672328274e-05, + "loss": 3.3715, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1659955724817754e-05, + "loss": 3.3662, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1651586156110964e-05, + "loss": 3.3614, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1643200208600444e-05, + "loss": 3.3744, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1634814261089924e-05, + "loss": 3.3506, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1626428313579404e-05, + "loss": 3.3618, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1618058744872617e-05, + "loss": 3.3674, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1609672797362097e-05, + "loss": 3.3699, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1601286849851575e-05, + "loss": 3.3613, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1592900902341055e-05, + "loss": 3.3647, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1584531333634267e-05, + "loss": 3.3561, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1576145386123747e-05, + "loss": 3.3669, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1567759438613227e-05, + "loss": 3.3649, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1559373491102707e-05, + "loss": 3.3709, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1551003922395918e-05, + "loss": 3.38, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1542617974885398e-05, + "loss": 3.3786, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1534248406178609e-05, + "loss": 3.3613, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1525862458668089e-05, + "loss": 3.3665, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.151747651115757e-05, + "loss": 3.3745, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1509090563647049e-05, + "loss": 3.3636, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1500704616136529e-05, + "loss": 3.3634, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1492318668626009e-05, + "loss": 3.3631, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1483932721115489e-05, + "loss": 3.3649, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1475546773604969e-05, + "loss": 3.3636, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.146717720489818e-05, + "loss": 3.3603, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1458791257387661e-05, + "loss": 3.3646, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.145040530987714e-05, + "loss": 3.3643, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.144201936236662e-05, + "loss": 3.359, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1433649793659832e-05, + "loss": 3.3733, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1425263846149312e-05, + "loss": 3.3702, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.141687789863879e-05, + "loss": 3.3784, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1408491951128272e-05, + "loss": 3.3656, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1400122382421482e-05, + "loss": 3.3699, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1391736434910962e-05, + "loss": 3.3747, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1383350487400442e-05, + "loss": 3.3646, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1374964539889922e-05, + "loss": 3.3694, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1366594971183133e-05, + "loss": 3.3655, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1358209023672613e-05, + "loss": 3.3726, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1349823076162093e-05, + "loss": 3.3715, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1341437128651573e-05, + "loss": 3.3671, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1333067559944785e-05, + "loss": 3.3687, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1324681612434264e-05, + "loss": 3.3728, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1316295664923744e-05, + "loss": 3.3641, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1307909717413225e-05, + "loss": 3.3655, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1299540148706434e-05, + "loss": 3.3732, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1291154201195916e-05, + "loss": 3.3611, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1282768253685396e-05, + "loss": 3.3776, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1274398684978607e-05, + "loss": 3.3558, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8610892295837402, + "eval_runtime": 303.2817, + "eval_samples_per_second": 1258.206, + "eval_steps_per_second": 39.32, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1266012737468087e-05, + "loss": 3.3642, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1257626789957567e-05, + "loss": 3.3636, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1249240842447047e-05, + "loss": 3.3596, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1240854894936525e-05, + "loss": 3.3724, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1232468947426006e-05, + "loss": 3.3736, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1224082999915486e-05, + "loss": 3.3696, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1215697052404966e-05, + "loss": 3.3601, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1207327483698177e-05, + "loss": 3.3579, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1198941536187657e-05, + "loss": 3.3622, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1190555588677137e-05, + "loss": 3.3706, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1182169641166617e-05, + "loss": 3.3649, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1173800072459828e-05, + "loss": 3.3682, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1165414124949308e-05, + "loss": 3.3669, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1157028177438788e-05, + "loss": 3.354, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1148642229928268e-05, + "loss": 3.3579, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1140272661221478e-05, + "loss": 3.3519, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.113188671371096e-05, + "loss": 3.3667, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1123500766200438e-05, + "loss": 3.3566, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1115114818689918e-05, + "loss": 3.3595, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.110674524998313e-05, + "loss": 3.3622, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.109835930247261e-05, + "loss": 3.3724, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1089973354962089e-05, + "loss": 3.3691, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.108158740745157e-05, + "loss": 3.366, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1073217838744781e-05, + "loss": 3.3653, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1064831891234261e-05, + "loss": 3.3697, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1056445943723741e-05, + "loss": 3.3636, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1048059996213221e-05, + "loss": 3.3556, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1039690427506432e-05, + "loss": 3.3699, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1031304479995912e-05, + "loss": 3.35, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.1022918532485392e-05, + "loss": 3.3515, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1014532584974872e-05, + "loss": 3.3575, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1006163016268085e-05, + "loss": 3.364, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0997777068757563e-05, + "loss": 3.3673, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0989391121247043e-05, + "loss": 3.3676, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0981005173736524e-05, + "loss": 3.3618, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0972635605029735e-05, + "loss": 3.3656, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0964249657519213e-05, + "loss": 3.3723, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0955863710008695e-05, + "loss": 3.3507, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0947477762498175e-05, + "loss": 3.3633, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0939108193791386e-05, + "loss": 3.3504, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0930722246280866e-05, + "loss": 3.3572, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0922336298770346e-05, + "loss": 3.3591, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0913966730063557e-05, + "loss": 3.3683, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0905580782553036e-05, + "loss": 3.3603, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0897194835042516e-05, + "loss": 3.3577, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0888808887531996e-05, + "loss": 3.3694, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0880439318825209e-05, + "loss": 3.3583, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0872053371314687e-05, + "loss": 3.3531, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0863667423804167e-05, + "loss": 3.3359, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0855281476293649e-05, + "loss": 3.3663, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0846911907586858e-05, + "loss": 3.3615, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0838525960076338e-05, + "loss": 3.3633, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.083015639136955e-05, + "loss": 3.3563, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.082177044385903e-05, + "loss": 3.3495, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.081338449634851e-05, + "loss": 3.3478, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.080499854883799e-05, + "loss": 3.3479, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.079661260132747e-05, + "loss": 3.3682, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0788226653816948e-05, + "loss": 3.348, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.077984070630643e-05, + "loss": 3.3672, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.077145475879591e-05, + "loss": 3.3569, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.076308519008912e-05, + "loss": 3.3488, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.07546992425786e-05, + "loss": 3.3638, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.074631329506808e-05, + "loss": 3.3553, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.073792734755756e-05, + "loss": 3.3535, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0729557778850773e-05, + "loss": 3.348, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0721171831340251e-05, + "loss": 3.3614, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0712785883829731e-05, + "loss": 3.3514, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0704399936319211e-05, + "loss": 3.3566, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0696030367612422e-05, + "loss": 3.3476, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0687644420101902e-05, + "loss": 3.355, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0679258472591384e-05, + "loss": 3.3538, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0670872525080864e-05, + "loss": 3.3683, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0662502956374074e-05, + "loss": 3.3556, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0654117008863554e-05, + "loss": 3.3624, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0645731061353034e-05, + "loss": 3.3686, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0637345113842513e-05, + "loss": 3.3623, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0628975545135725e-05, + "loss": 3.3583, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0620589597625205e-05, + "loss": 3.3651, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0612203650114685e-05, + "loss": 3.3618, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.0603817702604165e-05, + "loss": 3.3572, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0595448133897376e-05, + "loss": 3.3574, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0587062186386856e-05, + "loss": 3.3687, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.0578676238876337e-05, + "loss": 3.3673, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0570290291365816e-05, + "loss": 3.3575, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.0561920722659026e-05, + "loss": 3.3418, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.0553534775148508e-05, + "loss": 3.3554, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.0545148827637986e-05, + "loss": 3.367, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.0536762880127466e-05, + "loss": 3.3628, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.0528393311420679e-05, + "loss": 3.3639, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.0520007363910159e-05, + "loss": 3.3589, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0511621416399637e-05, + "loss": 3.3528, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.050325184769285e-05, + "loss": 3.3525, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.049486590018233e-05, + "loss": 3.3539, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.048647995267181e-05, + "loss": 3.3645, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.047809400516129e-05, + "loss": 3.3616, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.04697244364545e-05, + "loss": 3.3756, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.046133848894398e-05, + "loss": 3.3537, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.045295254143346e-05, + "loss": 3.3557, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.044456659392294e-05, + "loss": 3.36, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0436197025216152e-05, + "loss": 3.3609, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0427811077705632e-05, + "loss": 3.3616, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.041942513019511e-05, + "loss": 3.3616, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.041103918268459e-05, + "loss": 3.3564, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0402669613977803e-05, + "loss": 3.3537, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0394283666467281e-05, + "loss": 3.3658, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0385897718956761e-05, + "loss": 3.3444, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0377511771446243e-05, + "loss": 3.3538, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0369142202739454e-05, + "loss": 3.3612, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0360756255228934e-05, + "loss": 3.3585, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0352370307718414e-05, + "loss": 3.3497, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0343984360207894e-05, + "loss": 3.3593, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0335614791501106e-05, + "loss": 3.3433, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0327228843990584e-05, + "loss": 3.3601, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0318842896480064e-05, + "loss": 3.3569, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.0310456948969544e-05, + "loss": 3.36, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0302087380262755e-05, + "loss": 3.3698, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0293701432752235e-05, + "loss": 3.3672, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0285331864045448e-05, + "loss": 3.3548, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0276945916534927e-05, + "loss": 3.3586, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0268559969024406e-05, + "loss": 3.3628, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0260174021513887e-05, + "loss": 3.3511, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0251788074003367e-05, + "loss": 3.3564, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0243402126492846e-05, + "loss": 3.35, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0235016178982326e-05, + "loss": 3.3564, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0226630231471807e-05, + "loss": 3.3537, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0218260662765018e-05, + "loss": 3.3529, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0209874715254498e-05, + "loss": 3.3537, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0201488767743978e-05, + "loss": 3.3539, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0193102820233458e-05, + "loss": 3.3524, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0184733251526669e-05, + "loss": 3.3582, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0176347304016149e-05, + "loss": 3.3617, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0167961356505629e-05, + "loss": 3.3718, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.0159575408995109e-05, + "loss": 3.3526, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.015120584028832e-05, + "loss": 3.3597, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.01428198927778e-05, + "loss": 3.3653, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.013443394526728e-05, + "loss": 3.359, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0126047997756761e-05, + "loss": 3.3595, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.011767842904997e-05, + "loss": 3.3586, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.010929248153945e-05, + "loss": 3.3643, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0100906534028932e-05, + "loss": 3.3556, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.009252058651841e-05, + "loss": 3.3613, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0084151017811622e-05, + "loss": 3.3592, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0075765070301102e-05, + "loss": 3.3573, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0067379122790582e-05, + "loss": 3.3562, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0059009554083793e-05, + "loss": 3.3559, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0050623606573273e-05, + "loss": 3.3605, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0042237659062753e-05, + "loss": 3.3538, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0033851711552233e-05, + "loss": 3.3677, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0025482142845444e-05, + "loss": 3.3463, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0017096195334924e-05, + "loss": 3.3561, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.8599190711975098, + "eval_runtime": 303.5821, + "eval_samples_per_second": 1256.961, + "eval_steps_per_second": 39.281, + "step": 2442240 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.7030488587588403e+18, + "trial_name": null, + "trial_params": null +}