diff --git "a/checkpoint-2900160/trainer_state.json" "b/checkpoint-2900160/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2900160/trainer_state.json" @@ -0,0 +1,34313 @@ +{ + "best_metric": 3.844698667526245, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/3/checkpoints/checkpoint-992160", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2900160, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 11.0178, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8227, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.2018, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.991, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8204, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7126, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6098, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5458, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4575, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4132, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3638, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3233, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2691, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.223, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.179, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1459, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1159, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0987, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.98490857024181e-05, + "loss": 5.0575, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984069975490758e-05, + "loss": 5.0359, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 5.0237, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9769, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9529, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9361, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.928, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8923, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8706, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8656, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.843, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8161, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8007, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.7962, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.783, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7802, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7556, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7412, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7429, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.707, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.7, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6859, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6867, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6639, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6757, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6457, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6488, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6392, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6307, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6281, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.603, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5898, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6045, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5896, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5713, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5602, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5677, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5515, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5627, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.536, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5356, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5381, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949702331620985e-05, + "loss": 4.5188, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5021, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5087, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4917, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4926, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5017, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.495, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4803, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4683, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4622, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4741, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 4.4678, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4597, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4592, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4625, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4559, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4277, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4401, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4349, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4217, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4344, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4227, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4289, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4187, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3921, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4026, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4023, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4021, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3947, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3876, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3896, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3783, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.371, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3736, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3673, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3798, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3578, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3519, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3506, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3598, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3563, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3427, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3421, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3246, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3386, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3246, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3231, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3273, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3273, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3191, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3168, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3095, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3168, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3049, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3045, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3107, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3071, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019237232558704e-05, + "loss": 4.3041, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.2971, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.3012, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2966, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2822, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2993, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2849, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2913, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2746, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2683, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2681, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2703, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2606, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2781, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2749, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2576, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2603, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.267, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2625, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2668, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.264, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2505, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2545, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2509, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2432, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2525, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2403, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2296, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.252, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2324, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2305, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2326, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2255, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.19805908203125, + "eval_runtime": 317.5316, + "eval_samples_per_second": 1201.742, + "eval_steps_per_second": 37.555, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.209, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2221, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2381, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2144, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.23, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2034, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2141, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.1993, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2106, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2068, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2115, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2093, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1932, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1863, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1869, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1893, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1986, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.184, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1919, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.2064, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1819, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1742, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1802, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1882, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.169, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1727, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1739, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.17, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850787460125802e-05, + "loss": 4.1528, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.84994886537475e-05, + "loss": 4.1601, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1575, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1678, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1753, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1573, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.1535, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1657, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1408, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1489, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1392, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.1462, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1374, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1558, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1394, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1409, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.139, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1428, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1354, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1274, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1192, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1407, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.13, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1183, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1169, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.126, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1152, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.132, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.1153, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.117, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825637806996108e-05, + "loss": 4.1285, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.1038, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823960617494004e-05, + "loss": 4.1023, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823122022742952e-05, + "loss": 4.1105, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222834279919e-05, + "loss": 4.0951, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821444833240848e-05, + "loss": 4.1015, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.112, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.116, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.1034, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818092092117013e-05, + "loss": 4.0978, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.0885, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.1073, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.1047, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.1024, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.1037, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.106, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.1058, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113866098693434e-05, + "loss": 4.0836, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.0968, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.0966, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.0813, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808033868745508e-05, + "loss": 4.1042, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807195273994456e-05, + "loss": 4.0952, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.1, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0982, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.0732, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803842532870622e-05, + "loss": 4.0868, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803005575999943e-05, + "loss": 4.0855, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802166981248891e-05, + "loss": 4.0891, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.0852, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0774, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996528348761076e-05, + "loss": 4.0869, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988142401250556e-05, + "loss": 4.0798, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979756453740036e-05, + "loss": 4.0666, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971370506229516e-05, + "loss": 4.0752, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.0786, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795461499001221e-05, + "loss": 4.0877, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794622904250169e-05, + "loss": 4.0721, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793784309499117e-05, + "loss": 4.0577, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792945714748065e-05, + "loss": 4.0671, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792107119997013e-05, + "loss": 4.0757, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912685252459605e-05, + "loss": 4.0729, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904299304949085e-05, + "loss": 4.0673, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895913357438565e-05, + "loss": 4.0628, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.0517, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.0678, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.0519, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862385946200214e-05, + "loss": 4.0573, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785401637749343e-05, + "loss": 4.0599, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784563042998291e-05, + "loss": 4.0607, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783724448247239e-05, + "loss": 4.0567, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782885853496187e-05, + "loss": 4.0595, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782047258745135e-05, + "loss": 4.0506, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781208663994083e-05, + "loss": 4.0562, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780370069243031e-05, + "loss": 4.0485, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779531474491979e-05, + "loss": 4.0477, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786945176213e-05, + "loss": 4.0604, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777855922870248e-05, + "loss": 4.0574, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777018965999569e-05, + "loss": 4.0546, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776180371248517e-05, + "loss": 4.0494, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775341776497465e-05, + "loss": 4.0543, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7745031817464134e-05, + "loss": 4.0511, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736645869953614e-05, + "loss": 4.0405, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728259922443094e-05, + "loss": 4.0581, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719873974932574e-05, + "loss": 4.0445, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711488027422054e-05, + "loss": 4.0518, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770311845871526e-05, + "loss": 4.037, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769473251120474e-05, + "loss": 4.0374, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768634656369422e-05, + "loss": 4.0339, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76779606161837e-05, + "loss": 4.0342, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766959104747691e-05, + "loss": 4.0334, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766120509996639e-05, + "loss": 4.047, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765281915245587e-05, + "loss": 4.0504, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764443320494535e-05, + "loss": 4.0365, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763606363623857e-05, + "loss": 4.029, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762767768872805e-05, + "loss": 4.0417, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761929174121753e-05, + "loss": 4.0405, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761090579370701e-05, + "loss": 4.0481, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760253622500022e-05, + "loss": 4.0424, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941502774897e-05, + "loss": 4.0344, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758576432997918e-05, + "loss": 4.0289, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757737838246866e-05, + "loss": 4.0387, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569008813761866e-05, + "loss": 4.0287, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560622866251346e-05, + "loss": 4.0326, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552236918740826e-05, + "loss": 4.0296, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543850971230306e-05, + "loss": 4.0211, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753548140252352e-05, + "loss": 4.0428, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527095455013e-05, + "loss": 4.0248, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751870950750248e-05, + "loss": 4.0194, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751032355999196e-05, + "loss": 4.0238, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501937612481435e-05, + "loss": 4.0196, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.028687477111816, + "eval_runtime": 316.7625, + "eval_samples_per_second": 1204.659, + "eval_steps_per_second": 37.646, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493551664970914e-05, + "loss": 4.0026, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485165717460394e-05, + "loss": 4.0197, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476779769949874e-05, + "loss": 4.0343, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468393822439354e-05, + "loss": 4.0155, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460007874928834e-05, + "loss": 4.0303, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451621927418314e-05, + "loss": 4.0075, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443235979907794e-05, + "loss": 4.0202, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434850032397274e-05, + "loss": 4.0016, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0181, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741809451617997e-05, + "loss": 4.0157, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.0133, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740132262115893e-05, + "loss": 4.0229, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 4.0027, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 3.999, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 3.9968, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 4.0049, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735940926241006e-05, + "loss": 4.0108, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735102331489954e-05, + "loss": 4.003, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734263736738902e-05, + "loss": 4.0059, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.73342514198785e-05, + "loss": 4.0252, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732586547236797e-05, + "loss": 4.0018, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731747952485746e-05, + "loss": 3.9946, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730909357734694e-05, + "loss": 4.0034, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300724008640154e-05, + "loss": 4.0092, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729233806112963e-05, + "loss": 3.9923, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728395211361911e-05, + "loss": 3.9975, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727556616610859e-05, + "loss": 3.9983, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.72671965974018e-05, + "loss": 3.9958, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258810649891277e-05, + "loss": 3.9806, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250424702380757e-05, + "loss": 3.9881, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724205513367397e-05, + "loss": 3.9886, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233669186163446e-05, + "loss": 3.9948, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225283238652926e-05, + "loss": 4.009, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721689729114241e-05, + "loss": 3.9861, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720851134363189e-05, + "loss": 3.9868, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720012539612137e-05, + "loss": 3.9968, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719173944861085e-05, + "loss": 3.98, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718335350110033e-05, + "loss": 3.9807, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717498393239354e-05, + "loss": 3.9748, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716659798488302e-05, + "loss": 3.9847, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.71582120373725e-05, + "loss": 3.9734, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714982608986198e-05, + "loss": 3.9955, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714145652115519e-05, + "loss": 3.9755, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713307057364467e-05, + "loss": 3.9858, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712468462613415e-05, + "loss": 3.9816, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711629867862363e-05, + "loss": 3.9791, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107929109916846e-05, + "loss": 3.9808, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099543162406326e-05, + "loss": 3.9669, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091157214895806e-05, + "loss": 3.9627, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082787646189015e-05, + "loss": 3.9833, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074401698678495e-05, + "loss": 3.9771, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7066015751167975e-05, + "loss": 3.964, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057629803657455e-05, + "loss": 3.9665, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049260234950664e-05, + "loss": 3.9755, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040874287440144e-05, + "loss": 3.9563, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032488339929624e-05, + "loss": 3.9778, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024102392419104e-05, + "loss": 3.9652, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015716444908584e-05, + "loss": 3.9656, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007330497398064e-05, + "loss": 3.9822, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998944549887544e-05, + "loss": 3.9584, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699055860237703e-05, + "loss": 3.9537, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698218903367024e-05, + "loss": 3.9649, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697380308615972e-05, + "loss": 3.9497, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.69654171386492e-05, + "loss": 3.9542, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695703119113868e-05, + "loss": 3.9682, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694864524362816e-05, + "loss": 3.9698, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694025929611763e-05, + "loss": 3.9549, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693187334860711e-05, + "loss": 3.9553, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692352015870406e-05, + "loss": 3.9432, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691513421119354e-05, + "loss": 3.965, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690674826368302e-05, + "loss": 3.9591, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.68983623161725e-05, + "loss": 3.966, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6889976368661984e-05, + "loss": 3.9608, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688159042115146e-05, + "loss": 3.9639, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687320447364094e-05, + "loss": 3.9711, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686481852613042e-05, + "loss": 3.9452, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685644895742363e-05, + "loss": 3.9571, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848063009913106e-05, + "loss": 3.9611, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839677062402586e-05, + "loss": 3.9442, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831291114892066e-05, + "loss": 3.965, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822905167381546e-05, + "loss": 3.96, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814519219871026e-05, + "loss": 3.9638, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806133272360506e-05, + "loss": 3.9623, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797747324849986e-05, + "loss": 3.9405, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.67893777561432e-05, + "loss": 3.9523, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678100818743641e-05, + "loss": 3.9507, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677262223992589e-05, + "loss": 3.9584, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676423629241537e-05, + "loss": 3.9495, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675585034490485e-05, + "loss": 3.9466, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674748077619806e-05, + "loss": 3.9544, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673909482868754e-05, + "loss": 3.9495, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673070888117702e-05, + "loss": 3.9355, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.67223229336665e-05, + "loss": 3.9432, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671393698615598e-05, + "loss": 3.9496, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670556741744919e-05, + "loss": 3.9572, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697181469938675e-05, + "loss": 3.947, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688795522428155e-05, + "loss": 3.9273, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680409574917635e-05, + "loss": 3.9413, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672023627407115e-05, + "loss": 3.9476, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663654058700324e-05, + "loss": 3.9447, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655268111189804e-05, + "loss": 3.9425, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.6646882163679284e-05, + "loss": 3.9384, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.6638496216168764e-05, + "loss": 3.9258, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.6630110268658244e-05, + "loss": 3.9469, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662174069995145e-05, + "loss": 3.9216, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661335475244093e-05, + "loss": 3.9356, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660496880493041e-05, + "loss": 3.9306, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659658285741989e-05, + "loss": 3.9442, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658821328871311e-05, + "loss": 3.9275, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657982734120259e-05, + "loss": 3.9399, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657144139369207e-05, + "loss": 3.9293, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656305544618155e-05, + "loss": 3.9298, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655466949867103e-05, + "loss": 3.9333, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654629992996424e-05, + "loss": 3.925, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653791398245372e-05, + "loss": 3.9418, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.65295280349432e-05, + "loss": 3.9386, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652114208743268e-05, + "loss": 3.9352, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651275613992216e-05, + "loss": 3.9295, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650437019241164e-05, + "loss": 3.9345, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649598424490112e-05, + "loss": 3.9369, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648761467619433e-05, + "loss": 3.9178, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647922872868381e-05, + "loss": 3.9402, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470842781173294e-05, + "loss": 3.9288, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646245683366277e-05, + "loss": 3.9349, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645407088615225e-05, + "loss": 3.9228, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644568493864173e-05, + "loss": 3.926, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437298991131207e-05, + "loss": 3.9137, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428913043620687e-05, + "loss": 3.9212, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420543474913896e-05, + "loss": 3.9176, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412157527403376e-05, + "loss": 3.9337, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640378795869659e-05, + "loss": 3.9375, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395402011186065e-05, + "loss": 3.9249, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387016063675545e-05, + "loss": 3.9167, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637863011616503e-05, + "loss": 3.9275, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637026054745824e-05, + "loss": 3.9288, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636187459994772e-05, + "loss": 3.9335, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.63534886524372e-05, + "loss": 3.9295, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634510270492668e-05, + "loss": 3.9196, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633673313621989e-05, + "loss": 3.9244, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632834718870937e-05, + "loss": 3.9295, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631996124119885e-05, + "loss": 3.9163, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631157529368833e-05, + "loss": 3.9222, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630318934617781e-05, + "loss": 3.9183, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629481977747102e-05, + "loss": 3.9106, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.62864338299605e-05, + "loss": 3.9329, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278047882449985e-05, + "loss": 3.9173, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269661934939465e-05, + "loss": 3.9117, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261275987428945e-05, + "loss": 3.9142, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252906418722154e-05, + "loss": 3.9092, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9539332389831543, + "eval_runtime": 304.2645, + "eval_samples_per_second": 1254.142, + "eval_steps_per_second": 39.193, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244520471211634e-05, + "loss": 3.9042, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236134523701114e-05, + "loss": 3.9108, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227748576190594e-05, + "loss": 3.9291, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219362628680074e-05, + "loss": 3.9105, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621099305997328e-05, + "loss": 3.9311, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620260711246276e-05, + "loss": 3.899, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619422116495224e-05, + "loss": 3.9167, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618583521744172e-05, + "loss": 3.8947, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617746564873494e-05, + "loss": 3.9135, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616907970122442e-05, + "loss": 3.9139, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.61606937537139e-05, + "loss": 3.9084, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615230780620338e-05, + "loss": 3.9171, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614393823749659e-05, + "loss": 3.8983, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613555228998607e-05, + "loss": 3.8984, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612716634247555e-05, + "loss": 3.8972, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611878039496503e-05, + "loss": 3.9011, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611039444745451e-05, + "loss": 3.9085, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610200849994399e-05, + "loss": 3.9005, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609362255243347e-05, + "loss": 3.9062, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608523660492295e-05, + "loss": 3.9236, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076867036216156e-05, + "loss": 3.9031, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068481088705636e-05, + "loss": 3.8997, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606009514119512e-05, + "loss": 3.9026, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.60517091936846e-05, + "loss": 3.9071, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604333962497781e-05, + "loss": 3.8922, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603495367746729e-05, + "loss": 3.9025, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602656772995677e-05, + "loss": 3.9018, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601818178244625e-05, + "loss": 3.8927, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009795834935725e-05, + "loss": 3.8873, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600142626622894e-05, + "loss": 3.887, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599304031871842e-05, + "loss": 3.8966, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984654371207894e-05, + "loss": 3.8968, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976268423697374e-05, + "loss": 3.9111, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596788247618686e-05, + "loss": 3.896, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595951290748008e-05, + "loss": 3.8849, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595112695996955e-05, + "loss": 3.8989, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594274101245903e-05, + "loss": 3.89, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593435506494851e-05, + "loss": 3.8811, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925985496241726e-05, + "loss": 3.8836, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.59175995487312e-05, + "loss": 3.8887, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590921360122068e-05, + "loss": 3.8837, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590082765371016e-05, + "loss": 3.8999, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589244170619964e-05, + "loss": 3.885, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588405575868912e-05, + "loss": 3.8906, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587568618998233e-05, + "loss": 3.8922, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867300242471815e-05, + "loss": 3.8838, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858914294961295e-05, + "loss": 3.8902, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850528347450774e-05, + "loss": 3.8732, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842158778743984e-05, + "loss": 3.8654, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833772831233464e-05, + "loss": 3.896, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825386883722943e-05, + "loss": 3.8857, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817000936212423e-05, + "loss": 3.8786, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580863136750563e-05, + "loss": 3.8742, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580024541999511e-05, + "loss": 3.8813, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579185947248459e-05, + "loss": 3.868, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578347352497407e-05, + "loss": 3.8857, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577510395626728e-05, + "loss": 3.8789, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576671800875677e-05, + "loss": 3.8776, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575833206124625e-05, + "loss": 3.8909, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574994611373573e-05, + "loss": 3.8681, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574157654502894e-05, + "loss": 3.8656, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573319059751842e-05, + "loss": 3.8816, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.57248046500079e-05, + "loss": 3.8581, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571641870249738e-05, + "loss": 3.8628, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708049133790586e-05, + "loss": 3.8826, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699663186280066e-05, + "loss": 3.8833, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691277238769546e-05, + "loss": 3.8629, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682891291259026e-05, + "loss": 3.8743, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674505343748506e-05, + "loss": 3.8541, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666135775041715e-05, + "loss": 3.8799, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.56577498275312e-05, + "loss": 3.8729, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564936388002068e-05, + "loss": 3.8793, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564097793251016e-05, + "loss": 3.8728, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563259198499964e-05, + "loss": 3.8792, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562422241629285e-05, + "loss": 3.8847, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561583646878233e-05, + "loss": 3.8576, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560745052127181e-05, + "loss": 3.8756, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559906457376129e-05, + "loss": 3.8762, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559067862625077e-05, + "loss": 3.8556, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558230905754398e-05, + "loss": 3.8846, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557392311003346e-05, + "loss": 3.8772, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556553716252294e-05, + "loss": 3.8762, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555715121501242e-05, + "loss": 3.8817, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548781646305635e-05, + "loss": 3.86, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540395698795115e-05, + "loss": 3.8619, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.5532009751284595e-05, + "loss": 3.87, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523623803774075e-05, + "loss": 3.8766, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515254235067284e-05, + "loss": 3.8668, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506868287556764e-05, + "loss": 3.8662, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498482340046244e-05, + "loss": 3.8654, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5490096392535724e-05, + "loss": 3.8743, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481726823828933e-05, + "loss": 3.8529, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547334087631841e-05, + "loss": 3.8613, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546495492880789e-05, + "loss": 3.869, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545658536010111e-05, + "loss": 3.8772, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544819941259059e-05, + "loss": 3.8669, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543981346508007e-05, + "loss": 3.8485, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543142751756955e-05, + "loss": 3.8593, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542304157005903e-05, + "loss": 3.8641, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.54146556225485e-05, + "loss": 3.8662, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540626967503798e-05, + "loss": 3.8645, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539788372752746e-05, + "loss": 3.8574, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538949778001694e-05, + "loss": 3.8463, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538112821131015e-05, + "loss": 3.8647, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537274226379963e-05, + "loss": 3.8465, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536435631628911e-05, + "loss": 3.8554, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535597036877859e-05, + "loss": 3.8488, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534760080007181e-05, + "loss": 3.8659, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533921485256129e-05, + "loss": 3.8497, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533082890505077e-05, + "loss": 3.8661, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532244295754025e-05, + "loss": 3.8464, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314073388833456e-05, + "loss": 3.8534, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305687441322936e-05, + "loss": 3.8541, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297301493812416e-05, + "loss": 3.8517, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288915546301896e-05, + "loss": 3.8584, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280545977595105e-05, + "loss": 3.8637, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272160030084585e-05, + "loss": 3.8561, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263774082574065e-05, + "loss": 3.8529, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255388135063545e-05, + "loss": 3.8585, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524700218755303e-05, + "loss": 3.8605, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523863261884624e-05, + "loss": 3.8412, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523024667133572e-05, + "loss": 3.8625, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.52218607238252e-05, + "loss": 3.8501, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521349115511841e-05, + "loss": 3.8615, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520510520760789e-05, + "loss": 3.8496, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519671926009737e-05, + "loss": 3.8517, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518833331258685e-05, + "loss": 3.8376, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517994736507633e-05, + "loss": 3.8504, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517157779636954e-05, + "loss": 3.8448, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516319184885902e-05, + "loss": 3.8536, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.51548059013485e-05, + "loss": 3.859, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146419953837985e-05, + "loss": 3.8546, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5138050385131194e-05, + "loss": 3.8391, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129664437620674e-05, + "loss": 3.8543, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121278490110154e-05, + "loss": 3.8548, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112892542599634e-05, + "loss": 3.8562, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510452297389284e-05, + "loss": 3.8549, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509613702638232e-05, + "loss": 3.8459, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.50877510788718e-05, + "loss": 3.8502, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507936513136128e-05, + "loss": 3.8566, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507099556265449e-05, + "loss": 3.8423, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506260961514397e-05, + "loss": 3.8518, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505422366763345e-05, + "loss": 3.8403, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504583772012293e-05, + "loss": 3.8428, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503746815141615e-05, + "loss": 3.8603, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502908220390563e-05, + "loss": 3.846, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502069625639511e-05, + "loss": 3.8373, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501231030888459e-05, + "loss": 3.8375, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.50039407401778e-05, + "loss": 3.8408, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9129159450531006, + "eval_runtime": 304.8315, + "eval_samples_per_second": 1251.81, + "eval_steps_per_second": 39.12, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499555479266728e-05, + "loss": 3.8262, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498716884515676e-05, + "loss": 3.8399, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497878289764624e-05, + "loss": 3.852, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497039695013572e-05, + "loss": 3.8418, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962011002625197e-05, + "loss": 3.8567, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953625055114677e-05, + "loss": 3.8364, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945239107604156e-05, + "loss": 3.8406, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936853160093636e-05, + "loss": 3.8314, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492849997019058e-05, + "loss": 3.8384, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492011402268006e-05, + "loss": 3.8441, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491172807516954e-05, + "loss": 3.8403, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490334212765902e-05, + "loss": 3.8472, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.48949561801485e-05, + "loss": 3.8282, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488657023263798e-05, + "loss": 3.831, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487818428512746e-05, + "loss": 3.8297, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869798337616934e-05, + "loss": 3.8301, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486142876891015e-05, + "loss": 3.8402, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485304282139963e-05, + "loss": 3.8324, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484465687388911e-05, + "loss": 3.8384, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483627092637859e-05, + "loss": 3.8553, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482788497886807e-05, + "loss": 3.8374, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819515410161286e-05, + "loss": 3.8328, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481112946265076e-05, + "loss": 3.8335, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480274351514024e-05, + "loss": 3.8361, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479435756762972e-05, + "loss": 3.8245, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.4785987998922935e-05, + "loss": 3.8357, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477760205141241e-05, + "loss": 3.8323, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476921610390189e-05, + "loss": 3.8275, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476083015639137e-05, + "loss": 3.8211, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475246058768458e-05, + "loss": 3.8236, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744074640174064e-05, + "loss": 3.8263, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735688692663544e-05, + "loss": 3.8317, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727302745153024e-05, + "loss": 3.8418, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718916797642504e-05, + "loss": 3.8304, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471054722893571e-05, + "loss": 3.8174, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470216128142519e-05, + "loss": 3.8323, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469377533391467e-05, + "loss": 3.8304, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468538938640415e-05, + "loss": 3.8111, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467701981769736e-05, + "loss": 3.8149, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466863387018684e-05, + "loss": 3.8258, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466024792267632e-05, + "loss": 3.8158, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46518619751658e-05, + "loss": 3.8351, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464349240645902e-05, + "loss": 3.821, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.46351064589485e-05, + "loss": 3.8227, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462672051143798e-05, + "loss": 3.8271, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461833456392746e-05, + "loss": 3.8241, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609964995220666e-05, + "loss": 3.824, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601579047710146e-05, + "loss": 3.8098, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593193100199626e-05, + "loss": 3.7978, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584807152689106e-05, + "loss": 3.8361, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576437583982315e-05, + "loss": 3.8175, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568051636471795e-05, + "loss": 3.8187, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559665688961275e-05, + "loss": 3.8122, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551279741450755e-05, + "loss": 3.8118, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454291017274397e-05, + "loss": 3.8074, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453452422523345e-05, + "loss": 3.8193, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452613827772293e-05, + "loss": 3.8163, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451775233021241e-05, + "loss": 3.815, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450938276150562e-05, + "loss": 3.8322, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.45009968139951e-05, + "loss": 3.8026, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449261086648458e-05, + "loss": 3.8, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448422491897406e-05, + "loss": 3.8231, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447585535026727e-05, + "loss": 3.7929, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446746940275675e-05, + "loss": 3.7997, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445908345524623e-05, + "loss": 3.8228, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445069750773571e-05, + "loss": 3.822, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442327939028925e-05, + "loss": 3.8015, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433941991518405e-05, + "loss": 3.8133, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425556044007885e-05, + "loss": 3.796, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417170096497365e-05, + "loss": 3.8164, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408800527790574e-05, + "loss": 3.8098, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400414580280054e-05, + "loss": 3.8179, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392028632769534e-05, + "loss": 3.811, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383642685259014e-05, + "loss": 3.8173, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437527311655222e-05, + "loss": 3.824, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43668871690417e-05, + "loss": 3.8009, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435850122153118e-05, + "loss": 3.8093, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435011527402066e-05, + "loss": 3.8162, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434172932651014e-05, + "loss": 3.795, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433337613660709e-05, + "loss": 3.8215, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432499018909657e-05, + "loss": 3.8197, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431660424158605e-05, + "loss": 3.8156, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430821829407553e-05, + "loss": 3.8204, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429983234656501e-05, + "loss": 3.8014, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429144639905449e-05, + "loss": 3.7993, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428306045154397e-05, + "loss": 3.8076, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427467450403345e-05, + "loss": 3.8174, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266304935326656e-05, + "loss": 3.8086, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257918987816136e-05, + "loss": 3.8049, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249533040305616e-05, + "loss": 3.8035, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241147092795096e-05, + "loss": 3.8145, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423277752408831e-05, + "loss": 3.7983, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422439157657779e-05, + "loss": 3.801, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421600562906727e-05, + "loss": 3.8065, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420763606036048e-05, + "loss": 3.8188, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419925011284996e-05, + "loss": 3.8079, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419086416533944e-05, + "loss": 3.7917, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418247821782892e-05, + "loss": 3.7989, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.41740922703184e-05, + "loss": 3.8029, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416570632280788e-05, + "loss": 3.8094, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415732037529736e-05, + "loss": 3.8036, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148934427786834e-05, + "loss": 3.8036, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414056485908005e-05, + "loss": 3.7902, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413217891156953e-05, + "loss": 3.8011, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412379296405901e-05, + "loss": 3.789, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411540701654849e-05, + "loss": 3.8005, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107037447841706e-05, + "loss": 3.7854, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098651500331186e-05, + "loss": 3.8141, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409026555282066e-05, + "loss": 3.7921, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408187960531014e-05, + "loss": 3.8014, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073510036603355e-05, + "loss": 3.7933, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065124089092835e-05, + "loss": 3.7943, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405673814158231e-05, + "loss": 3.7966, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404835219407179e-05, + "loss": 3.7954, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039982625365004e-05, + "loss": 3.8013, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031596677854484e-05, + "loss": 3.8057, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023210730343963e-05, + "loss": 3.7985, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014824782833443e-05, + "loss": 3.7987, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400645521412666e-05, + "loss": 3.7994, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399806926661613e-05, + "loss": 3.806, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398968331910561e-05, + "loss": 3.7818, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398129737159509e-05, + "loss": 3.8064, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397292780288831e-05, + "loss": 3.7923, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396454185537778e-05, + "loss": 3.8055, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395615590786726e-05, + "loss": 3.7919, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394776996035674e-05, + "loss": 3.7958, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393940039164996e-05, + "loss": 3.7839, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393101444413944e-05, + "loss": 3.7909, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392262849662892e-05, + "loss": 3.7928, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.39142425491184e-05, + "loss": 3.7974, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905872980411606e-05, + "loss": 3.799, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897487032901086e-05, + "loss": 3.8028, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889101085390566e-05, + "loss": 3.7831, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880715137880046e-05, + "loss": 3.7974, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872329190369526e-05, + "loss": 3.8031, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863959621662735e-05, + "loss": 3.8006, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855573674152215e-05, + "loss": 3.7967, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847187726641695e-05, + "loss": 3.7971, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383881815793491e-05, + "loss": 3.7911, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383043221042439e-05, + "loss": 3.8038, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382204626291387e-05, + "loss": 3.7864, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381366031540335e-05, + "loss": 3.7974, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380529074669656e-05, + "loss": 3.7869, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379690479918604e-05, + "loss": 3.7885, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378851885167552e-05, + "loss": 3.8036, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780132904165e-05, + "loss": 3.7942, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377176333545821e-05, + "loss": 3.7886, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376337738794769e-05, + "loss": 3.7797, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375499144043717e-05, + "loss": 3.7902, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8884897232055664, + "eval_runtime": 304.7482, + "eval_samples_per_second": 1252.152, + "eval_steps_per_second": 39.131, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374660549292665e-05, + "loss": 3.7811, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738235924219865e-05, + "loss": 3.782, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729849976709345e-05, + "loss": 3.7999, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721464029198824e-05, + "loss": 3.7901, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3713078081688304e-05, + "loss": 3.8033, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704708512981514e-05, + "loss": 3.7855, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.3696322565470993e-05, + "loss": 3.7842, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.3687936617960473e-05, + "loss": 3.7802, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679550670449953e-05, + "loss": 3.7824, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367118110174316e-05, + "loss": 3.7918, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366279515423264e-05, + "loss": 3.7903, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365440920672212e-05, + "loss": 3.7902, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.36460232592116e-05, + "loss": 3.7809, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363763731170108e-05, + "loss": 3.779, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362925136419056e-05, + "loss": 3.7759, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362086541668005e-05, + "loss": 3.7761, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361247946916953e-05, + "loss": 3.786, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360410990046274e-05, + "loss": 3.7831, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359572395295222e-05, + "loss": 3.7872, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35873380054417e-05, + "loss": 3.8017, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357896843673491e-05, + "loss": 3.7903, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357058248922439e-05, + "loss": 3.776, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356219654171387e-05, + "loss": 3.7828, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355381059420335e-05, + "loss": 3.7836, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354542464669283e-05, + "loss": 3.7737, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537055077986036e-05, + "loss": 3.7869, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528669130475516e-05, + "loss": 3.7806, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520283182964996e-05, + "loss": 3.7782, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351189723545448e-05, + "loss": 3.7748, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350352766674769e-05, + "loss": 3.7677, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349514171923717e-05, + "loss": 3.776, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348675577172665e-05, + "loss": 3.7813, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347836982421613e-05, + "loss": 3.7873, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347000025550934e-05, + "loss": 3.7799, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346161430799882e-05, + "loss": 3.7668, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.34532283604883e-05, + "loss": 3.7846, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344484241297778e-05, + "loss": 3.78, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343647284427099e-05, + "loss": 3.7601, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342808689676047e-05, + "loss": 3.773, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341970094924995e-05, + "loss": 3.772, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411315001739436e-05, + "loss": 3.7691, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402945433032645e-05, + "loss": 3.7828, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394559485522125e-05, + "loss": 3.7736, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3386173538011605e-05, + "loss": 3.7734, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377787590501085e-05, + "loss": 3.7749, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369418021794294e-05, + "loss": 3.7742, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3361032074283774e-05, + "loss": 3.7789, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352646126773254e-05, + "loss": 3.7614, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344260179262734e-05, + "loss": 3.7441, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333589061055594e-05, + "loss": 3.7894, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332750466304542e-05, + "loss": 3.7685, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.33191187155349e-05, + "loss": 3.7766, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331073276802439e-05, + "loss": 3.7615, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7637, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329397725180708e-05, + "loss": 3.7604, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328559130429656e-05, + "loss": 3.7665, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327720535678604e-05, + "loss": 3.7712, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.7614, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.7845, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325206389305821e-05, + "loss": 3.7595, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324367794554768e-05, + "loss": 3.7495, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.32353083768409e-05, + "loss": 3.7753, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322692242933038e-05, + "loss": 3.749, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321853648181986e-05, + "loss": 3.7492, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321015053430934e-05, + "loss": 3.774, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320178096560255e-05, + "loss": 3.7718, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319339501809203e-05, + "loss": 3.7575, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185009070581506e-05, + "loss": 3.7644, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176623123070986e-05, + "loss": 3.7461, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.31682535543642e-05, + "loss": 3.7701, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.7617, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151481659343155e-05, + "loss": 3.7736, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143095711832635e-05, + "loss": 3.763, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313472614312585e-05, + "loss": 3.7691, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.7773, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311795424810481e-05, + "loss": 3.7539, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310956830059429e-05, + "loss": 3.7659, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.7668, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7515, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308442683686646e-05, + "loss": 3.7736, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3076057268159675e-05, + "loss": 3.7755, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067671320649155e-05, + "loss": 3.7656, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305928537313863e-05, + "loss": 3.779, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305089942562811e-05, + "loss": 3.7539, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304251347811759e-05, + "loss": 3.7498, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303412753060707e-05, + "loss": 3.7626, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302574158309655e-05, + "loss": 3.7659, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017372014389764e-05, + "loss": 3.7681, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008986066879244e-05, + "loss": 3.7584, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000600119368724e-05, + "loss": 3.7538, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2992214171858204e-05, + "loss": 3.7681, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298384460315141e-05, + "loss": 3.7547, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297545865564089e-05, + "loss": 3.7542, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296707270813037e-05, + "loss": 3.7607, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295870313942358e-05, + "loss": 3.773, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295031719191306e-05, + "loss": 3.7643, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294193124440254e-05, + "loss": 3.7432, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293354529689202e-05, + "loss": 3.7541, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.29251593493815e-05, + "loss": 3.7603, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291677340187099e-05, + "loss": 3.7628, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290838745436047e-05, + "loss": 3.76, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290000150684995e-05, + "loss": 3.7569, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289163193814316e-05, + "loss": 3.7433, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288324599063264e-05, + "loss": 3.7531, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287486004312212e-05, + "loss": 3.7501, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.28664740956116e-05, + "loss": 3.755, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285810452690481e-05, + "loss": 3.7384, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284971857939429e-05, + "loss": 3.7713, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284133263188377e-05, + "loss": 3.7475, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2832946684373247e-05, + "loss": 3.754, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824577115666456e-05, + "loss": 3.7447, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281619116815594e-05, + "loss": 3.7559, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280780522064542e-05, + "loss": 3.7508, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.27994192731349e-05, + "loss": 3.7485, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279104970442811e-05, + "loss": 3.7574, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278266375691759e-05, + "loss": 3.7621, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277427780940707e-05, + "loss": 3.7484, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276589186189655e-05, + "loss": 3.7611, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275752229318976e-05, + "loss": 3.7494, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274913634567924e-05, + "loss": 3.7629, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274075039816872e-05, + "loss": 3.7431, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.27323644506582e-05, + "loss": 3.761, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272399488195141e-05, + "loss": 3.7465, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715608934440896e-05, + "loss": 3.7596, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707222986930376e-05, + "loss": 3.7502, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698837039419856e-05, + "loss": 3.7515, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690467470713065e-05, + "loss": 3.7383, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2682081523202545e-05, + "loss": 3.7503, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673695575692025e-05, + "loss": 3.7505, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2665309628181505e-05, + "loss": 3.7581, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656940059474714e-05, + "loss": 3.7497, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648554111964194e-05, + "loss": 3.7599, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640168164453674e-05, + "loss": 3.7421, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631782216943154e-05, + "loss": 3.7538, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262341264823636e-05, + "loss": 3.7572, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261502670072584e-05, + "loss": 3.7586, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260664075321533e-05, + "loss": 3.7522, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259825480570481e-05, + "loss": 3.7527, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258988523699802e-05, + "loss": 3.7475, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.25814992894875e-05, + "loss": 3.7649, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257311334197698e-05, + "loss": 3.7406, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256472739446646e-05, + "loss": 3.7558, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255635782575967e-05, + "loss": 3.7443, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254797187824915e-05, + "loss": 3.7464, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253958593073863e-05, + "loss": 3.7581, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253119998322811e-05, + "loss": 3.747, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252283041452132e-05, + "loss": 3.7498, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.25144444670108e-05, + "loss": 3.7342, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250605851950028e-05, + "loss": 3.7501, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8713021278381348, + "eval_runtime": 305.0615, + "eval_samples_per_second": 1250.866, + "eval_steps_per_second": 39.09, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249767257198976e-05, + "loss": 3.7391, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489286624479237e-05, + "loss": 3.7373, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480900676968716e-05, + "loss": 3.7539, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472514729458196e-05, + "loss": 3.7501, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464128781947676e-05, + "loss": 3.7586, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455742834437156e-05, + "loss": 3.7434, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447356886926636e-05, + "loss": 3.7402, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438970939416116e-05, + "loss": 3.7415, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430601370709325e-05, + "loss": 3.741, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422215423198805e-05, + "loss": 3.7508, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413829475688285e-05, + "loss": 3.7426, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405443528177765e-05, + "loss": 3.7481, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239709033827471e-05, + "loss": 3.7387, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238870439076419e-05, + "loss": 3.7371, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238031844325367e-05, + "loss": 3.7362, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237193249574315e-05, + "loss": 3.7322, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236354654823263e-05, + "loss": 3.7459, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235516060072211e-05, + "loss": 3.7425, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234677465321159e-05, + "loss": 3.7414, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233838870570107e-05, + "loss": 3.7576, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233001913699428e-05, + "loss": 3.7535, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232163318948376e-05, + "loss": 3.7357, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231324724197324e-05, + "loss": 3.7373, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230486129446272e-05, + "loss": 3.7427, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296491725755935e-05, + "loss": 3.7382, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288105778245415e-05, + "loss": 3.7434, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279719830734895e-05, + "loss": 3.7426, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271333883224375e-05, + "loss": 3.7394, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262964314517584e-05, + "loss": 3.7314, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254578367007064e-05, + "loss": 3.7306, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246192419496544e-05, + "loss": 3.7279, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237806471986024e-05, + "loss": 3.7401, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222943690327923e-05, + "loss": 3.7469, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222105095576871e-05, + "loss": 3.7423, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221266500825819e-05, + "loss": 3.728, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220427906074767e-05, + "loss": 3.7409, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219590949204089e-05, + "loss": 3.7411, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218752354453037e-05, + "loss": 3.7219, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217913759701985e-05, + "loss": 3.7308, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217075164950933e-05, + "loss": 3.7309, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216238208080254e-05, + "loss": 3.7258, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215399613329202e-05, + "loss": 3.7416, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.21456101857815e-05, + "loss": 3.7331, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137240617074706e-05, + "loss": 3.7343, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128854669564186e-05, + "loss": 3.7346, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120468722053666e-05, + "loss": 3.7329, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112082774543146e-05, + "loss": 3.7391, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103696827032626e-05, + "loss": 3.7225, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209532725832584e-05, + "loss": 3.7019, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208694131081532e-05, + "loss": 3.7478, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.20785553633048e-05, + "loss": 3.7298, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207016941579428e-05, + "loss": 3.7372, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206179984708749e-05, + "loss": 3.7233, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205341389957697e-05, + "loss": 3.7245, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204502795206645e-05, + "loss": 3.7156, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203664200455593e-05, + "loss": 3.7278, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202827243584914e-05, + "loss": 3.7357, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201988648833862e-05, + "loss": 3.72, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.20115005408281e-05, + "loss": 3.7424, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200311459331758e-05, + "loss": 3.7235, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994745024610796e-05, + "loss": 3.7122, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986359077100276e-05, + "loss": 3.7295, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977973129589756e-05, + "loss": 3.7156, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969587182079236e-05, + "loss": 3.7085, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961217613372445e-05, + "loss": 3.7361, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952831665861925e-05, + "loss": 3.7339, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944445718351405e-05, + "loss": 3.7193, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936076149644614e-05, + "loss": 3.7231, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927690202134094e-05, + "loss": 3.7118, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919304254623574e-05, + "loss": 3.7304, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910918307113054e-05, + "loss": 3.726, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190254873840627e-05, + "loss": 3.7292, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189416279089575e-05, + "loss": 3.7259, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188577684338523e-05, + "loss": 3.7287, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187739089587471e-05, + "loss": 3.7399, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186902132716792e-05, + "loss": 3.7159, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.18606353796574e-05, + "loss": 3.7306, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185224943214688e-05, + "loss": 3.7245, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184386348463636e-05, + "loss": 3.7148, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183549391592957e-05, + "loss": 3.7322, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827124347222776e-05, + "loss": 3.7389, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818738399712256e-05, + "loss": 3.7269, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181035245220174e-05, + "loss": 3.7408, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180196650469122e-05, + "loss": 3.7164, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17935805571807e-05, + "loss": 3.7131, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178519460967018e-05, + "loss": 3.7242, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177680866215966e-05, + "loss": 3.7327, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176843909345287e-05, + "loss": 3.7238, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176005314594235e-05, + "loss": 3.7235, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175166719843183e-05, + "loss": 3.721, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174328125092131e-05, + "loss": 3.7281, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173491168221452e-05, + "loss": 3.7164, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726525734704e-05, + "loss": 3.7164, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171813978719348e-05, + "loss": 3.7235, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170977021848669e-05, + "loss": 3.7357, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170138427097618e-05, + "loss": 3.7256, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169299832346566e-05, + "loss": 3.7052, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168461237595514e-05, + "loss": 3.7206, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167622642844461e-05, + "loss": 3.7206, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166784048093409e-05, + "loss": 3.729, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165945453342357e-05, + "loss": 3.7218, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651084964716786e-05, + "loss": 3.7187, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164269901720626e-05, + "loss": 3.7097, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163431306969574e-05, + "loss": 3.7108, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162592712218522e-05, + "loss": 3.7186, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.16175411746747e-05, + "loss": 3.7146, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160915522716418e-05, + "loss": 3.7032, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160076927965366e-05, + "loss": 3.735, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592383332143145e-05, + "loss": 3.7119, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1584013763436354e-05, + "loss": 3.7138, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575627815925834e-05, + "loss": 3.7068, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567241868415314e-05, + "loss": 3.718, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558872299708523e-05, + "loss": 3.718, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1550486352198003e-05, + "loss": 3.7113, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154210040468748e-05, + "loss": 3.7227, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153371445717696e-05, + "loss": 3.7223, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152534488847017e-05, + "loss": 3.7156, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151695894095965e-05, + "loss": 3.7242, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150857299344913e-05, + "loss": 3.7123, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150018704593861e-05, + "loss": 3.7241, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.14918010984281e-05, + "loss": 3.7097, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148341515091758e-05, + "loss": 3.7208, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147502920340706e-05, + "loss": 3.7117, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146664325589654e-05, + "loss": 3.7215, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145827368718975e-05, + "loss": 3.7178, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144988773967923e-05, + "loss": 3.7144, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144150179216871e-05, + "loss": 3.7049, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143311584465819e-05, + "loss": 3.712, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.14247462759514e-05, + "loss": 3.7091, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141636032844088e-05, + "loss": 3.7257, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140797438093036e-05, + "loss": 3.7122, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139958843341984e-05, + "loss": 3.7267, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139121886471305e-05, + "loss": 3.7036, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138283291720253e-05, + "loss": 3.7184, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137444696969201e-05, + "loss": 3.7198, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136606102218149e-05, + "loss": 3.7225, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.13576914534747e-05, + "loss": 3.7177, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134930550596418e-05, + "loss": 3.7163, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134091955845366e-05, + "loss": 3.7104, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133254998974687e-05, + "loss": 3.7302, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132416404223635e-05, + "loss": 3.7039, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131577809472583e-05, + "loss": 3.7187, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130739214721531e-05, + "loss": 3.7117, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129900619970479e-05, + "loss": 3.7171, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129062025219427e-05, + "loss": 3.7151, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128223430468375e-05, + "loss": 3.7128, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273864735976966e-05, + "loss": 3.7147, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265478788466446e-05, + "loss": 3.7004, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125709284095592e-05, + "loss": 3.7154, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8613688945770264, + "eval_runtime": 303.0312, + "eval_samples_per_second": 1259.247, + "eval_steps_per_second": 39.352, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.12487068934454e-05, + "loss": 3.7045, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240337324738615e-05, + "loss": 3.7015, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231951377228095e-05, + "loss": 3.7155, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122356542971757e-05, + "loss": 3.7145, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121517948220705e-05, + "loss": 3.7235, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206809913500264e-05, + "loss": 3.7125, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1198423965989744e-05, + "loss": 3.7061, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1190038018479224e-05, + "loss": 3.7083, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1181652070968704e-05, + "loss": 3.7059, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117328250226192e-05, + "loss": 3.7174, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116489655475139e-05, + "loss": 3.7069, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115651060724087e-05, + "loss": 3.7133, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114814103853409e-05, + "loss": 3.707, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113975509102357e-05, + "loss": 3.7031, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113136914351304e-05, + "loss": 3.6964, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112298319600252e-05, + "loss": 3.6976, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111461362729574e-05, + "loss": 3.7141, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110622767978521e-05, + "loss": 3.7079, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.10978417322747e-05, + "loss": 3.7031, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108945578476418e-05, + "loss": 3.7239, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108106983725366e-05, + "loss": 3.7185, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107268388974314e-05, + "loss": 3.7066, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106429794223262e-05, + "loss": 3.7069, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.10559119947221e-05, + "loss": 3.7004, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104754242601531e-05, + "loss": 3.7052, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103915647850479e-05, + "loss": 3.7079, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103077053099427e-05, + "loss": 3.7083, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1022384583483747e-05, + "loss": 3.7066, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1014015014776956e-05, + "loss": 3.6963, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005629067266436e-05, + "loss": 3.6972, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997243119755916e-05, + "loss": 3.6909, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988857172245396e-05, + "loss": 3.7091, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098048760353861e-05, + "loss": 3.7113, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097210165602809e-05, + "loss": 3.7103, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096371570851757e-05, + "loss": 3.6995, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095532976100705e-05, + "loss": 3.6988, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094696019230026e-05, + "loss": 3.7085, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093857424478974e-05, + "loss": 3.6952, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093018829727922e-05, + "loss": 3.6915, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.09218023497687e-05, + "loss": 3.7007, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091343278106191e-05, + "loss": 3.6951, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090504683355139e-05, + "loss": 3.7029, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089666088604087e-05, + "loss": 3.7008, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888291317334085e-05, + "loss": 3.7028, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879905369823565e-05, + "loss": 3.6988, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871519422313045e-05, + "loss": 3.7012, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.0863133474802525e-05, + "loss": 3.7055, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.0854763906095734e-05, + "loss": 3.6906, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.0846377958585214e-05, + "loss": 3.6692, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0837992011074694e-05, + "loss": 3.7124, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829606063564174e-05, + "loss": 3.6969, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082123649485738e-05, + "loss": 3.7053, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081285054734686e-05, + "loss": 3.6904, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080446459983634e-05, + "loss": 3.6927, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079609503112955e-05, + "loss": 3.6814, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078770908361904e-05, + "loss": 3.6946, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077932313610852e-05, + "loss": 3.7056, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770937188598e-05, + "loss": 3.6837, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076255124108748e-05, + "loss": 3.7121, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075416529357696e-05, + "loss": 3.6913, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074577934606644e-05, + "loss": 3.6784, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073739339855592e-05, + "loss": 3.6944, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072902382984913e-05, + "loss": 3.6838, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072063788233861e-05, + "loss": 3.6764, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071225193482809e-05, + "loss": 3.7026, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070386598731757e-05, + "loss": 3.7014, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695496418610777e-05, + "loss": 3.6862, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0687110471100257e-05, + "loss": 3.6939, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678724523589736e-05, + "loss": 3.677, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067035495488295e-05, + "loss": 3.6982, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066196900737243e-05, + "loss": 3.6888, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065358305986191e-05, + "loss": 3.6967, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064519711235139e-05, + "loss": 3.7006, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.06368275436446e-05, + "loss": 3.6911, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062844159613408e-05, + "loss": 3.7118, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062005564862356e-05, + "loss": 3.6831, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061166970111304e-05, + "loss": 3.6979, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060330013240625e-05, + "loss": 3.6909, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059491418489573e-05, + "loss": 3.6853, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058652823738521e-05, + "loss": 3.699, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578158668678426e-05, + "loss": 3.7062, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569772721167906e-05, + "loss": 3.6971, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561386773657386e-05, + "loss": 3.71, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553000826146866e-05, + "loss": 3.6839, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544614878636346e-05, + "loss": 3.6819, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053622893112582e-05, + "loss": 3.6919, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.05278429836153e-05, + "loss": 3.7025, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0519473414908515e-05, + "loss": 3.6889, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0511087467397995e-05, + "loss": 3.694, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050270151988747e-05, + "loss": 3.6878, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.0494331951180684e-05, + "loss": 3.6948, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.0485946003670164e-05, + "loss": 3.6887, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0477560056159644e-05, + "loss": 3.6827, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469174108649124e-05, + "loss": 3.6924, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046080453994234e-05, + "loss": 3.7042, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045241859243182e-05, + "loss": 3.6943, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044403264492129e-05, + "loss": 3.6737, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043564669741077e-05, + "loss": 3.6873, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042726074990025e-05, + "loss": 3.6881, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041887480238973e-05, + "loss": 3.6992, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041048885487921e-05, + "loss": 3.6929, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040210290736869e-05, + "loss": 3.6855, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.03937333386619e-05, + "loss": 3.6795, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038534739115138e-05, + "loss": 3.678, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037696144364087e-05, + "loss": 3.6874, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036857549613035e-05, + "loss": 3.684, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036020592742356e-05, + "loss": 3.6723, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035181997991304e-05, + "loss": 3.6997, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034343403240252e-05, + "loss": 3.6852, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335048084892e-05, + "loss": 3.6798, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326678516185206e-05, + "loss": 3.6818, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318308947478415e-05, + "loss": 3.6809, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309922999967895e-05, + "loss": 3.6883, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301537052457375e-05, + "loss": 3.6797, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293151104946855e-05, + "loss": 3.6914, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284765157436335e-05, + "loss": 3.693, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276379209925815e-05, + "loss": 3.6817, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.02679932624153e-05, + "loss": 3.6921, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025960731490478e-05, + "loss": 3.6831, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025123774619799e-05, + "loss": 3.695, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024285179868747e-05, + "loss": 3.6808, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023446585117695e-05, + "loss": 3.6852, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022607990366643e-05, + "loss": 3.6821, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021771033495964e-05, + "loss": 3.693, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020932438744912e-05, + "loss": 3.6897, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.02009384399386e-05, + "loss": 3.6815, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019255249242808e-05, + "loss": 3.668, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018418292372129e-05, + "loss": 3.6858, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017579697621077e-05, + "loss": 3.6792, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167411028700256e-05, + "loss": 3.6905, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159025081189736e-05, + "loss": 3.6835, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150655512482945e-05, + "loss": 3.6945, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0142269564972425e-05, + "loss": 3.672, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133883617461905e-05, + "loss": 3.6928, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0125514048755114e-05, + "loss": 3.6871, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011714448004832e-05, + "loss": 3.6958, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.01087585325378e-05, + "loss": 3.6878, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010037258502728e-05, + "loss": 3.6825, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009198663751676e-05, + "loss": 3.6822, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008361706880998e-05, + "loss": 3.6986, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007523112129946e-05, + "loss": 3.6734, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006684517378894e-05, + "loss": 3.6898, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005845922627842e-05, + "loss": 3.6835, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.00500732787679e-05, + "loss": 3.6831, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004170371006111e-05, + "loss": 3.6844, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003331776255059e-05, + "loss": 3.6847, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002493181504007e-05, + "loss": 3.6826, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001654586752955e-05, + "loss": 3.6734, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000815992001903e-05, + "loss": 3.6838, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8546175956726074, + "eval_runtime": 303.766, + "eval_samples_per_second": 1256.201, + "eval_steps_per_second": 39.257, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999977397250851e-05, + "loss": 3.672, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999138802499799e-05, + "loss": 3.6731, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998300207748747e-05, + "loss": 3.6863, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997461612997695e-05, + "loss": 3.6843, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996624656127016e-05, + "loss": 3.6962, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995786061375964e-05, + "loss": 3.6769, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994947466624912e-05, + "loss": 3.6804, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.99410887187386e-05, + "loss": 3.6784, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932702771228076e-05, + "loss": 3.6735, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992433320252129e-05, + "loss": 3.6881, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991594725501077e-05, + "loss": 3.6771, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990756130750025e-05, + "loss": 3.6819, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989919173879346e-05, + "loss": 3.686, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989080579128294e-05, + "loss": 3.6646, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988241984377242e-05, + "loss": 3.6694, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.98740338962619e-05, + "loss": 3.6669, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986564794875138e-05, + "loss": 3.6876, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985726200124086e-05, + "loss": 3.6782, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984887605373034e-05, + "loss": 3.6745, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984049010621982e-05, + "loss": 3.692, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.98321041587093e-05, + "loss": 3.6898, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982371821119878e-05, + "loss": 3.6756, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981533226368826e-05, + "loss": 3.6774, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980696269498147e-05, + "loss": 3.6747, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979857674747095e-05, + "loss": 3.6781, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979019079996043e-05, + "loss": 3.6755, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978180485244991e-05, + "loss": 3.6758, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977341890493939e-05, + "loss": 3.6834, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976503295742887e-05, + "loss": 3.666, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975664700991835e-05, + "loss": 3.6659, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974826106240783e-05, + "loss": 3.6673, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739891493701045e-05, + "loss": 3.6751, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731505546190525e-05, + "loss": 3.6792, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723119598680005e-05, + "loss": 3.6859, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714733651169485e-05, + "loss": 3.6692, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706364082462694e-05, + "loss": 3.6724, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9697978134952174e-05, + "loss": 3.6828, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689592187441654e-05, + "loss": 3.6642, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9681206239931134e-05, + "loss": 3.6644, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967283667122434e-05, + "loss": 3.6758, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966445072371382e-05, + "loss": 3.6626, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.96560647762033e-05, + "loss": 3.6707, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964767882869278e-05, + "loss": 3.6764, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639309259986e-05, + "loss": 3.676, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963092331247548e-05, + "loss": 3.6655, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962253736496496e-05, + "loss": 3.6774, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961415141745444e-05, + "loss": 3.675, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960578184874765e-05, + "loss": 3.6654, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959739590123713e-05, + "loss": 3.6422, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958900995372661e-05, + "loss": 3.6789, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958062400621609e-05, + "loss": 3.6684, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95722544375093e-05, + "loss": 3.6731, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956386848999878e-05, + "loss": 3.6651, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955548254248826e-05, + "loss": 3.6597, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547096594977737e-05, + "loss": 3.6572, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953872702627095e-05, + "loss": 3.6641, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953034107876043e-05, + "loss": 3.6799, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952197151005364e-05, + "loss": 3.653, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951358556254312e-05, + "loss": 3.6873, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.95051996150326e-05, + "loss": 3.6648, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949681366752208e-05, + "loss": 3.6496, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948842772001156e-05, + "loss": 3.6677, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480041772501035e-05, + "loss": 3.6554, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471655824990514e-05, + "loss": 3.6533, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463269877479994e-05, + "loss": 3.669, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945490030877321e-05, + "loss": 3.6742, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446530740066426e-05, + "loss": 3.6546, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438144792555906e-05, + "loss": 3.6702, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429758845045386e-05, + "loss": 3.6483, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942137289753486e-05, + "loss": 3.6689, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941298695002434e-05, + "loss": 3.666, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940460100251382e-05, + "loss": 3.665, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939623143380703e-05, + "loss": 3.6728, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938784548629651e-05, + "loss": 3.6666, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937945953878599e-05, + "loss": 3.6812, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937107359127547e-05, + "loss": 3.6589, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936268764376495e-05, + "loss": 3.669, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935430169625443e-05, + "loss": 3.6602, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934591574874391e-05, + "loss": 3.6574, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337529801233395e-05, + "loss": 3.6739, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329160232526604e-05, + "loss": 3.6723, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320774285016084e-05, + "loss": 3.6717, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312388337505564e-05, + "loss": 3.6812, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304002389995044e-05, + "loss": 3.6584, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295616442484524e-05, + "loss": 3.6537, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287230494974004e-05, + "loss": 3.6617, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9278844547463484e-05, + "loss": 3.6759, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270458599952964e-05, + "loss": 3.6617, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926208903124617e-05, + "loss": 3.6654, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925370308373565e-05, + "loss": 3.6653, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924533351502886e-05, + "loss": 3.6635, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923694756751835e-05, + "loss": 3.6625, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922856162000783e-05, + "loss": 3.6558, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922017567249731e-05, + "loss": 3.6659, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921180610379052e-05, + "loss": 3.6753, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920342015628e-05, + "loss": 3.6669, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919503420876948e-05, + "loss": 3.6498, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918664826125896e-05, + "loss": 3.6594, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917826231374844e-05, + "loss": 3.6603, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916987636623792e-05, + "loss": 3.6677, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916149041872739e-05, + "loss": 3.6677, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915310447121687e-05, + "loss": 3.6574, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144734902510086e-05, + "loss": 3.656, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136348954999566e-05, + "loss": 3.6494, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912797938629278e-05, + "loss": 3.6618, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911959343878226e-05, + "loss": 3.6592, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911120749127174e-05, + "loss": 3.6492, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910282154376122e-05, + "loss": 3.6696, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094435596250695e-05, + "loss": 3.6552, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086049648740175e-05, + "loss": 3.6553, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077663701229655e-05, + "loss": 3.6503, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069294132522864e-05, + "loss": 3.6553, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060908185012344e-05, + "loss": 3.6634, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052522237501824e-05, + "loss": 3.6509, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044136289991304e-05, + "loss": 3.6657, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035750342480784e-05, + "loss": 3.6656, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027364394970264e-05, + "loss": 3.6557, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901899482626348e-05, + "loss": 3.6657, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901060887875296e-05, + "loss": 3.6571, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900222293124244e-05, + "loss": 3.6674, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899383698373192e-05, + "loss": 3.6556, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.89854510362214e-05, + "loss": 3.6592, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897706508871088e-05, + "loss": 3.655, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896867914120036e-05, + "loss": 3.6638, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896029319368984e-05, + "loss": 3.6663, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895192362498305e-05, + "loss": 3.651, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894353767747253e-05, + "loss": 3.6476, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893516810876574e-05, + "loss": 3.6532, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892678216125522e-05, + "loss": 3.6562, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918396213744704e-05, + "loss": 3.6637, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910010266234184e-05, + "loss": 3.658, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901624318723664e-05, + "loss": 3.6658, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889325475001687e-05, + "loss": 3.6469, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888486880250635e-05, + "loss": 3.6716, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887648285499583e-05, + "loss": 3.6585, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886809690748531e-05, + "loss": 3.6631, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885972733877852e-05, + "loss": 3.6607, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851341391268e-05, + "loss": 3.655, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884295544375748e-05, + "loss": 3.6557, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883456949624696e-05, + "loss": 3.6726, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882618354873644e-05, + "loss": 3.6485, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881781398002966e-05, + "loss": 3.6623, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880942803251914e-05, + "loss": 3.658, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880104208500862e-05, + "loss": 3.6571, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.87926561374981e-05, + "loss": 3.6579, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878428656879131e-05, + "loss": 3.6597, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877590062128079e-05, + "loss": 3.653, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876751467377027e-05, + "loss": 3.6543, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875912872625975e-05, + "loss": 3.6538, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8501596450805664, + "eval_runtime": 307.5866, + "eval_samples_per_second": 1240.597, + "eval_steps_per_second": 38.77, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875074277874923e-05, + "loss": 3.6462, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.87423568312387e-05, + "loss": 3.6452, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8733987262531916e-05, + "loss": 3.6576, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725601315021396e-05, + "loss": 3.6612, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8717215367510876e-05, + "loss": 3.6706, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708829420000356e-05, + "loss": 3.6483, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870045985129357e-05, + "loss": 3.6561, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869207390378305e-05, + "loss": 3.6546, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683687956272525e-05, + "loss": 3.6444, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675302008762005e-05, + "loss": 3.6636, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8666916061251485e-05, + "loss": 3.649, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8658530113740964e-05, + "loss": 3.6573, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8650160545034174e-05, + "loss": 3.6615, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641774597523654e-05, + "loss": 3.64, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633388650013133e-05, + "loss": 3.6412, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625002702502613e-05, + "loss": 3.6414, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861663313379583e-05, + "loss": 3.6594, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860824718628531e-05, + "loss": 3.6587, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859986123877479e-05, + "loss": 3.6433, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859147529126427e-05, + "loss": 3.6664, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858308934375375e-05, + "loss": 3.6641, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857470339624323e-05, + "loss": 3.6497, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856633382753644e-05, + "loss": 3.6513, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855794788002592e-05, + "loss": 3.6503, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.85495619325154e-05, + "loss": 3.6506, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854117598500488e-05, + "loss": 3.6514, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853279003749436e-05, + "loss": 3.6492, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852442046878757e-05, + "loss": 3.6574, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851603452127705e-05, + "loss": 3.6431, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507648573766534e-05, + "loss": 3.6394, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499262626256014e-05, + "loss": 3.6435, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8490876678745494e-05, + "loss": 3.6502, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482490731234974e-05, + "loss": 3.6498, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474104783724454e-05, + "loss": 3.6618, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846573521501766e-05, + "loss": 3.6447, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845734926750714e-05, + "loss": 3.644, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844896331999662e-05, + "loss": 3.6589, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.84405773724861e-05, + "loss": 3.6358, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843219142497558e-05, + "loss": 3.644, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842380547746506e-05, + "loss": 3.6498, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415419529954536e-05, + "loss": 3.6398, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407033582444016e-05, + "loss": 3.6425, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839866401373723e-05, + "loss": 3.6508, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839027806622671e-05, + "loss": 3.6532, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838189211871619e-05, + "loss": 3.6396, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837350617120567e-05, + "loss": 3.6516, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836513660249889e-05, + "loss": 3.6469, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356767033792096e-05, + "loss": 3.641, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348381086281576e-05, + "loss": 3.6222, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339995138771056e-05, + "loss": 3.6527, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331609191260536e-05, + "loss": 3.643, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832322324375001e-05, + "loss": 3.6528, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314853675043225e-05, + "loss": 3.6362, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306467727532705e-05, + "loss": 3.6377, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298081780022185e-05, + "loss": 3.6314, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289695832511665e-05, + "loss": 3.6382, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828132626380488e-05, + "loss": 3.6568, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827294031629436e-05, + "loss": 3.6301, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8264554368783834e-05, + "loss": 3.658, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8256168421273314e-05, + "loss": 3.6422, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247782473762794e-05, + "loss": 3.6247, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.8239396526252274e-05, + "loss": 3.6371, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8231010578741754e-05, + "loss": 3.6289, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.8222624631231234e-05, + "loss": 3.6341, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821425506252444e-05, + "loss": 3.6422, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820588549381766e-05, + "loss": 3.6493, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819749954630714e-05, + "loss": 3.6296, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818911359879662e-05, + "loss": 3.645, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.81807276512861e-05, + "loss": 3.6235, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817234170377558e-05, + "loss": 3.6439, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816395575626506e-05, + "loss": 3.6411, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815556980875454e-05, + "loss": 3.6418, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814718386124402e-05, + "loss": 3.6436, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813881429253723e-05, + "loss": 3.6408, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813044472383044e-05, + "loss": 3.658, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812205877631992e-05, + "loss": 3.6353, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.81136728288094e-05, + "loss": 3.6471, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810528688129888e-05, + "loss": 3.6377, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809691731259209e-05, + "loss": 3.6315, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808853136508157e-05, + "loss": 3.6453, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808014541757105e-05, + "loss": 3.6495, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807175947006053e-05, + "loss": 3.6464, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806337352255001e-05, + "loss": 3.6591, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805498757503949e-05, + "loss": 3.6373, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.80466180063327e-05, + "loss": 3.627, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803823205882218e-05, + "loss": 3.6376, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802984611131166e-05, + "loss": 3.6482, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802146016380114e-05, + "loss": 3.6389, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801307421629062e-05, + "loss": 3.6418, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.80046882687801e-05, + "loss": 3.638, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799631870007331e-05, + "loss": 3.6419, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.79879327525628e-05, + "loss": 3.6388, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797954680505228e-05, + "loss": 3.6315, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797116085754176e-05, + "loss": 3.6412, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962791288834966e-05, + "loss": 3.6522, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954405341324446e-05, + "loss": 3.6453, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946019393813926e-05, + "loss": 3.6219, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937633446303406e-05, + "loss": 3.6357, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929247498792886e-05, + "loss": 3.6373, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920877930086095e-05, + "loss": 3.6444, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912491982575575e-05, + "loss": 3.6421, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904106035065055e-05, + "loss": 3.6324, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895720087554535e-05, + "loss": 3.6319, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7887334140044015e-05, + "loss": 3.6261, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787896457133723e-05, + "loss": 3.6378, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787057862382671e-05, + "loss": 3.6321, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786219267631619e-05, + "loss": 3.629, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785380672880567e-05, + "loss": 3.6382, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845420781295144e-05, + "loss": 3.6379, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7837034833784624e-05, + "loss": 3.629, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782866526507784e-05, + "loss": 3.6295, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782027931756732e-05, + "loss": 3.6283, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781189337005679e-05, + "loss": 3.6427, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780350742254627e-05, + "loss": 3.6222, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779513785383949e-05, + "loss": 3.6434, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778675190632897e-05, + "loss": 3.643, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777836595881845e-05, + "loss": 3.631, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776998001130793e-05, + "loss": 3.6421, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761610442601144e-05, + "loss": 3.6353, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775322449509062e-05, + "loss": 3.6434, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.77448385475801e-05, + "loss": 3.636, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773645260006958e-05, + "loss": 3.6336, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772806665255906e-05, + "loss": 3.6333, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719697083852266e-05, + "loss": 3.6368, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711311136341746e-05, + "loss": 3.6393, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7702925188831226e-05, + "loss": 3.6328, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7694539241320706e-05, + "loss": 3.6218, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768616967261392e-05, + "loss": 3.6344, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.76777837251034e-05, + "loss": 3.6266, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766939777759288e-05, + "loss": 3.6428, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766101183008236e-05, + "loss": 3.6329, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765262588257184e-05, + "loss": 3.6425, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764425631386505e-05, + "loss": 3.623, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763587036635453e-05, + "loss": 3.6455, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762748441884401e-05, + "loss": 3.6335, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761909847133349e-05, + "loss": 3.6473, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.76107289026267e-05, + "loss": 3.6347, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760234295511618e-05, + "loss": 3.634, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759395700760566e-05, + "loss": 3.6269, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758557106009514e-05, + "loss": 3.6522, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757718511258462e-05, + "loss": 3.6223, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568815543877836e-05, + "loss": 3.6411, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7560429596367316e-05, + "loss": 3.6313, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7552043648856796e-05, + "loss": 3.6332, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543657701346276e-05, + "loss": 3.6372, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535288132639485e-05, + "loss": 3.6325, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526902185128965e-05, + "loss": 3.6327, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518516237618445e-05, + "loss": 3.6312, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510130290107924e-05, + "loss": 3.627, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8467867374420166, + "eval_runtime": 308.0391, + "eval_samples_per_second": 1238.774, + "eval_steps_per_second": 38.713, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501744342597404e-05, + "loss": 3.6166, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493358395086884e-05, + "loss": 3.6219, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484972447576364e-05, + "loss": 3.6334, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476586500065844e-05, + "loss": 3.641, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746821693135906e-05, + "loss": 3.6479, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745983098384854e-05, + "loss": 3.6281, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745144503633802e-05, + "loss": 3.6308, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.74430590888275e-05, + "loss": 3.6352, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743467314131698e-05, + "loss": 3.6211, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742630357261019e-05, + "loss": 3.6334, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741791762509967e-05, + "loss": 3.634, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740953167758915e-05, + "loss": 3.6353, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740116210888236e-05, + "loss": 3.6369, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739277616137184e-05, + "loss": 3.619, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738439021386132e-05, + "loss": 3.617, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.73760042663508e-05, + "loss": 3.6165, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736761831884028e-05, + "loss": 3.6419, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735923237132976e-05, + "loss": 3.6308, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735084642381924e-05, + "loss": 3.6213, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734246047630872e-05, + "loss": 3.6389, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733409090760193e-05, + "loss": 3.6441, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732570496009141e-05, + "loss": 3.6281, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731731901258089e-05, + "loss": 3.6286, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730893306507037e-05, + "loss": 3.6262, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730054711755985e-05, + "loss": 3.6331, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292177548853056e-05, + "loss": 3.6265, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283791601342536e-05, + "loss": 3.6209, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275405653832016e-05, + "loss": 3.6362, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267019706321496e-05, + "loss": 3.6176, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725863375881098e-05, + "loss": 3.614, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725026419010419e-05, + "loss": 3.6245, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724187824259367e-05, + "loss": 3.6238, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723349229508315e-05, + "loss": 3.6281, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722510634757263e-05, + "loss": 3.6404, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721672040006211e-05, + "loss": 3.619, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720833445255159e-05, + "loss": 3.6247, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719994850504107e-05, + "loss": 3.6365, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719157893633428e-05, + "loss": 3.6116, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718319298882376e-05, + "loss": 3.6188, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717480704131324e-05, + "loss": 3.6263, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716642109380272e-05, + "loss": 3.6153, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715805152509593e-05, + "loss": 3.6219, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149665577585416e-05, + "loss": 3.6279, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141279630074896e-05, + "loss": 3.6308, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132910061368105e-05, + "loss": 3.6199, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124524113857585e-05, + "loss": 3.6251, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116138166347065e-05, + "loss": 3.6248, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107752218836545e-05, + "loss": 3.6194, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7099366271326025e-05, + "loss": 3.5999, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7090996702619234e-05, + "loss": 3.6279, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7082610755108714e-05, + "loss": 3.6235, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074224807598194e-05, + "loss": 3.6288, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065838860087674e-05, + "loss": 3.6195, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705746929138088e-05, + "loss": 3.6097, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704908334387037e-05, + "loss": 3.6105, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704069739635985e-05, + "loss": 3.6152, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703231144884933e-05, + "loss": 3.6324, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702394188014254e-05, + "loss": 3.6091, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701555593263202e-05, + "loss": 3.6345, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.70071699851215e-05, + "loss": 3.6239, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699878403761098e-05, + "loss": 3.6053, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699039809010046e-05, + "loss": 3.6203, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698201214258993e-05, + "loss": 3.6057, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697362619507941e-05, + "loss": 3.6102, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696525662637263e-05, + "loss": 3.6155, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695687067886211e-05, + "loss": 3.6307, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694848473135159e-05, + "loss": 3.6092, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694009878384107e-05, + "loss": 3.6205, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693171283633055e-05, + "loss": 3.6043, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692332688882003e-05, + "loss": 3.6192, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691494094130951e-05, + "loss": 3.6201, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906571372602716e-05, + "loss": 3.6234, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898185425092196e-05, + "loss": 3.6202, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889799477581676e-05, + "loss": 3.6177, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881413530071156e-05, + "loss": 3.6363, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873027582560636e-05, + "loss": 3.6136, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864658013853845e-05, + "loss": 3.6225, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856272066343325e-05, + "loss": 3.6137, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847886118832805e-05, + "loss": 3.6157, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683950017132229e-05, + "loss": 3.6241, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.68311306026155e-05, + "loss": 3.6215, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682274465510498e-05, + "loss": 3.626, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681435870759446e-05, + "loss": 3.6346, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680597276008394e-05, + "loss": 3.6221, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679758681257342e-05, + "loss": 3.6019, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.67892008650629e-05, + "loss": 3.6145, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678083129635611e-05, + "loss": 3.6274, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677244534884559e-05, + "loss": 3.6192, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676405940133507e-05, + "loss": 3.6193, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675567345382455e-05, + "loss": 3.6164, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674730388511776e-05, + "loss": 3.6187, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738917937607246e-05, + "loss": 3.6172, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730531990096726e-05, + "loss": 3.6089, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722146042586206e-05, + "loss": 3.6218, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713776473879415e-05, + "loss": 3.6291, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6705390526368895e-05, + "loss": 3.6216, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6697004578858375e-05, + "loss": 3.6007, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6688618631347854e-05, + "loss": 3.6165, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680232683837334e-05, + "loss": 3.6186, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6671846736326814e-05, + "loss": 3.6196, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663460788816294e-05, + "loss": 3.6212, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665507484130577e-05, + "loss": 3.6095, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664670527259898e-05, + "loss": 3.6095, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.66383357038922e-05, + "loss": 3.6061, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662994975638168e-05, + "loss": 3.6149, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662156380887116e-05, + "loss": 3.6119, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661317786136064e-05, + "loss": 3.6065, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660480829265385e-05, + "loss": 3.6206, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659642234514333e-05, + "loss": 3.6122, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658803639763281e-05, + "loss": 3.6085, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657965045012229e-05, + "loss": 3.6092, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657126450261177e-05, + "loss": 3.6045, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656287855510124e-05, + "loss": 3.6193, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655450898639446e-05, + "loss": 3.606, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654612303888394e-05, + "loss": 3.6155, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653773709137342e-05, + "loss": 3.6199, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.65293511438629e-05, + "loss": 3.6122, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652098157515611e-05, + "loss": 3.6178, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651259562764559e-05, + "loss": 3.616, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504209680135066e-05, + "loss": 3.6204, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495823732624546e-05, + "loss": 3.6193, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487437785114026e-05, + "loss": 3.6119, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479051837603506e-05, + "loss": 3.6108, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470682268896715e-05, + "loss": 3.6157, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462296321386195e-05, + "loss": 3.6197, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453910373875675e-05, + "loss": 3.6087, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445524426365155e-05, + "loss": 3.602, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643715485765837e-05, + "loss": 3.6096, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642876891014785e-05, + "loss": 3.6073, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642038296263733e-05, + "loss": 3.6218, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641199701512681e-05, + "loss": 3.6117, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640361106761629e-05, + "loss": 3.6209, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.63952414989095e-05, + "loss": 3.6054, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638685555139898e-05, + "loss": 3.6194, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637846960388846e-05, + "loss": 3.612, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637008365637794e-05, + "loss": 3.6265, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636171408767115e-05, + "loss": 3.6161, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635332814016063e-05, + "loss": 3.6136, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634494219265011e-05, + "loss": 3.6078, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633655624513959e-05, + "loss": 3.6291, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328186676432804e-05, + "loss": 3.6049, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319800728922284e-05, + "loss": 3.6147, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311414781411764e-05, + "loss": 3.6145, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303028833901244e-05, + "loss": 3.6103, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629465926519445e-05, + "loss": 3.6156, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628627331768393e-05, + "loss": 3.6129, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627788737017341e-05, + "loss": 3.6105, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626950142266289e-05, + "loss": 3.6123, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.62611318539561e-05, + "loss": 3.6059, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8452212810516357, + "eval_runtime": 337.6, + "eval_samples_per_second": 1130.305, + "eval_steps_per_second": 35.323, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625274590644558e-05, + "loss": 3.6017, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624435995893506e-05, + "loss": 3.6008, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623597401142454e-05, + "loss": 3.6115, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622758806391402e-05, + "loss": 3.6197, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621921849520724e-05, + "loss": 3.6253, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621083254769672e-05, + "loss": 3.6044, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.62024466001862e-05, + "loss": 3.6119, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619406065267568e-05, + "loss": 3.6144, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618569108396889e-05, + "loss": 3.6014, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617730513645837e-05, + "loss": 3.6067, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616891918894785e-05, + "loss": 3.6178, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616053324143733e-05, + "loss": 3.6122, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152180051534265e-05, + "loss": 3.6176, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6143794104023745e-05, + "loss": 3.5975, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613540815651323e-05, + "loss": 3.5966, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612702220900271e-05, + "loss": 3.5956, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611863626149219e-05, + "loss": 3.6175, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611025031398167e-05, + "loss": 3.6142, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610186436647115e-05, + "loss": 3.6004, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609347841896063e-05, + "loss": 3.6164, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608510885025384e-05, + "loss": 3.6255, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607672290274332e-05, + "loss": 3.6047, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.60683369552328e-05, + "loss": 3.6089, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605995100772228e-05, + "loss": 3.6052, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605156506021176e-05, + "loss": 3.6154, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604319549150497e-05, + "loss": 3.6025, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603480954399445e-05, + "loss": 3.6003, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602642359648393e-05, + "loss": 3.6198, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6018037648973416e-05, + "loss": 3.5959, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009651701462896e-05, + "loss": 3.5966, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001282132756105e-05, + "loss": 3.6012, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992896185245585e-05, + "loss": 3.6021, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5984510237735065e-05, + "loss": 3.6099, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5976124290224545e-05, + "loss": 3.6197, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.5967738342714025e-05, + "loss": 3.5962, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.5959368774007234e-05, + "loss": 3.6067, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5950982826496714e-05, + "loss": 3.6141, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942596878986194e-05, + "loss": 3.5897, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593421093147567e-05, + "loss": 3.5986, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592584136276888e-05, + "loss": 3.6086, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591745541525837e-05, + "loss": 3.5925, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590906946774785e-05, + "loss": 3.6056, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590068352023732e-05, + "loss": 3.6111, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.58922975727268e-05, + "loss": 3.6076, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588392800402002e-05, + "loss": 3.5999, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.58755420565095e-05, + "loss": 3.6067, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586715610899897e-05, + "loss": 3.6015, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585877016148845e-05, + "loss": 3.6025, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585038421397793e-05, + "loss": 3.5806, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584201464527114e-05, + "loss": 3.6069, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583362869776062e-05, + "loss": 3.6048, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582524275025011e-05, + "loss": 3.6072, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581685680273959e-05, + "loss": 3.5965, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.58084872340328e-05, + "loss": 3.5921, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800101286522277e-05, + "loss": 3.5908, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791715339011757e-05, + "loss": 3.5941, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783329391501236e-05, + "loss": 3.6139, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5774959822794446e-05, + "loss": 3.5905, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766573875283926e-05, + "loss": 3.6063, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758187927773405e-05, + "loss": 3.6056, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5749801980262885e-05, + "loss": 3.5901, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741416032752365e-05, + "loss": 3.5944, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733046464045575e-05, + "loss": 3.5877, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572466051653506e-05, + "loss": 3.594, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571627456902454e-05, + "loss": 3.5901, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570788862151402e-05, + "loss": 3.6126, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569951905280723e-05, + "loss": 3.5927, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569113310529671e-05, + "loss": 3.5926, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568274715778619e-05, + "loss": 3.5878, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567436121027567e-05, + "loss": 3.5985, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566597526276515e-05, + "loss": 3.6002, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565760569405836e-05, + "loss": 3.6008, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564921974654784e-05, + "loss": 3.6031, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564083379903732e-05, + "loss": 3.5993, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.56324478515268e-05, + "loss": 3.6121, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562406190401628e-05, + "loss": 3.595, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615692335309495e-05, + "loss": 3.6015, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607306387798975e-05, + "loss": 3.5981, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598920440288455e-05, + "loss": 3.5948, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590534492777935e-05, + "loss": 3.6041, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582164924071144e-05, + "loss": 3.6013, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573778976560624e-05, + "loss": 3.6096, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565393029050104e-05, + "loss": 3.6132, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557007081539584e-05, + "loss": 3.6066, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5548621134029064e-05, + "loss": 3.5831, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5540235186518544e-05, + "loss": 3.5951, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553186561781175e-05, + "loss": 3.6047, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552347967030123e-05, + "loss": 3.6019, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551509372279071e-05, + "loss": 3.5956, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550670777528019e-05, + "loss": 3.5983, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549833820657341e-05, + "loss": 3.5988, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548995225906289e-05, + "loss": 3.5932, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548156631155237e-05, + "loss": 3.5924, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547318036404185e-05, + "loss": 3.6023, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546481079533506e-05, + "loss": 3.6055, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545642484782454e-05, + "loss": 3.6067, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544803890031402e-05, + "loss": 3.5809, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.54396529528035e-05, + "loss": 3.5964, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543126700529298e-05, + "loss": 3.5977, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422897436586186e-05, + "loss": 3.6051, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414511489075666e-05, + "loss": 3.6004, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406125541565146e-05, + "loss": 3.5896, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539773959405463e-05, + "loss": 3.5924, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538937002534784e-05, + "loss": 3.5824, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538098407783732e-05, + "loss": 3.5999, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.53725981303268e-05, + "loss": 3.5885, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364212182816275e-05, + "loss": 3.5865, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355826235305755e-05, + "loss": 3.6006, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534745666659897e-05, + "loss": 3.5965, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533907071908845e-05, + "loss": 3.5866, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330684771577924e-05, + "loss": 3.5917, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322298824067404e-05, + "loss": 3.583, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313912876556884e-05, + "loss": 3.6032, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530552692904637e-05, + "loss": 3.5835, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529715736033958e-05, + "loss": 3.6003, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528877141282906e-05, + "loss": 3.5929, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528038546531854e-05, + "loss": 3.5975, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527199951780802e-05, + "loss": 3.5974, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526362994910123e-05, + "loss": 3.5951, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525524400159071e-05, + "loss": 3.6031, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524685805408019e-05, + "loss": 3.5986, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523847210656967e-05, + "loss": 3.5913, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523008615905915e-05, + "loss": 3.5912, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522171659035236e-05, + "loss": 3.5947, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521333064284184e-05, + "loss": 3.5988, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5204944695331324e-05, + "loss": 3.5881, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196558747820804e-05, + "loss": 3.5871, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188189179114013e-05, + "loss": 3.5878, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5179803231603493e-05, + "loss": 3.5902, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5171417284092973e-05, + "loss": 3.5986, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516303133658245e-05, + "loss": 3.5928, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515464538907193e-05, + "loss": 3.6057, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514627582036514e-05, + "loss": 3.5822, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513788987285462e-05, + "loss": 3.6024, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.51295039253441e-05, + "loss": 3.596, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512111797783358e-05, + "loss": 3.6012, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511274840912679e-05, + "loss": 3.5981, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510436246161628e-05, + "loss": 3.593, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509597651410576e-05, + "loss": 3.5925, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508759056659524e-05, + "loss": 3.6073, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507922099788845e-05, + "loss": 3.59, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507083505037793e-05, + "loss": 3.5922, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506244910286741e-05, + "loss": 3.5974, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505406315535689e-05, + "loss": 3.5912, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5045693586650096e-05, + "loss": 3.5916, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037307639139576e-05, + "loss": 3.5999, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028921691629056e-05, + "loss": 3.5873, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020535744118536e-05, + "loss": 3.5918, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012166175411745e-05, + "loss": 3.5882, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.844944477081299, + "eval_runtime": 337.4942, + "eval_samples_per_second": 1130.659, + "eval_steps_per_second": 35.334, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003780227901225e-05, + "loss": 3.5925, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499539428039071e-05, + "loss": 3.5767, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498700833288019e-05, + "loss": 3.5942, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497862238536967e-05, + "loss": 3.6002, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497025281666288e-05, + "loss": 3.6016, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496186686915236e-05, + "loss": 3.5906, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495348092164184e-05, + "loss": 3.5916, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494509497413132e-05, + "loss": 3.5946, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.49367090266208e-05, + "loss": 3.5837, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492833945791401e-05, + "loss": 3.5883, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491995351040349e-05, + "loss": 3.5949, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491156756289297e-05, + "loss": 3.5942, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490319799418618e-05, + "loss": 3.6025, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894812046675665e-05, + "loss": 3.5792, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886426099165145e-05, + "loss": 3.5757, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878040151654625e-05, + "loss": 3.5766, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869654204144105e-05, + "loss": 3.6032, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861268256633585e-05, + "loss": 3.5911, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485288230912306e-05, + "loss": 3.5835, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484449636161254e-05, + "loss": 3.5973, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4836126792905754e-05, + "loss": 3.6046, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4827740845395234e-05, + "loss": 3.5893, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481935489788471e-05, + "loss": 3.5893, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481096895037419e-05, + "loss": 3.587, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480258300286367e-05, + "loss": 3.5971, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479421343415688e-05, + "loss": 3.5833, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478582748664636e-05, + "loss": 3.5821, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477744153913584e-05, + "loss": 3.6026, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476905559162532e-05, + "loss": 3.5731, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.47606696441148e-05, + "loss": 3.5782, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475230007540801e-05, + "loss": 3.5811, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474391412789749e-05, + "loss": 3.5835, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473552818038697e-05, + "loss": 3.5939, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472714223287645e-05, + "loss": 3.5978, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471877266416966e-05, + "loss": 3.5831, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471038671665914e-05, + "loss": 3.5828, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470200076914862e-05, + "loss": 3.5951, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.46936148216381e-05, + "loss": 3.5745, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468524525293132e-05, + "loss": 3.5852, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.46768593054208e-05, + "loss": 3.5867, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466847335791028e-05, + "loss": 3.5746, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466008741039976e-05, + "loss": 3.5825, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4651701462889237e-05, + "loss": 3.5956, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4643315515378717e-05, + "loss": 3.5857, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4634945946671926e-05, + "loss": 3.5804, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626559999161406e-05, + "loss": 3.5926, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618174051650886e-05, + "loss": 3.5819, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609788104140365e-05, + "loss": 3.5852, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601402156629845e-05, + "loss": 3.5569, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593032587923055e-05, + "loss": 3.5832, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458464664041254e-05, + "loss": 3.5937, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457626069290202e-05, + "loss": 3.5863, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.45678747453915e-05, + "loss": 3.5771, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455950517668471e-05, + "loss": 3.577, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455111922917419e-05, + "loss": 3.5706, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454273328166367e-05, + "loss": 3.5719, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453434733415315e-05, + "loss": 3.6003, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452597776544636e-05, + "loss": 3.5732, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451759181793584e-05, + "loss": 3.5862, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450920587042532e-05, + "loss": 3.5873, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.45008199229148e-05, + "loss": 3.5714, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449243397540428e-05, + "loss": 3.5756, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484064406697495e-05, + "loss": 3.5713, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475678459186975e-05, + "loss": 3.5731, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467292511676455e-05, + "loss": 3.575, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458906564165935e-05, + "loss": 3.5915, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450536995459144e-05, + "loss": 3.5812, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442151047948624e-05, + "loss": 3.5736, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433765100438104e-05, + "loss": 3.5678, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425379152927584e-05, + "loss": 3.5785, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416993205417064e-05, + "loss": 3.5812, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440862363671027e-05, + "loss": 3.5847, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440023768919975e-05, + "loss": 3.5814, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439185174168923e-05, + "loss": 3.5829, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438346579417871e-05, + "loss": 3.5944, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437507984666819e-05, + "loss": 3.5767, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436671027796141e-05, + "loss": 3.5793, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435832433045089e-05, + "loss": 3.5832, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434993838294037e-05, + "loss": 3.5787, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434155243542984e-05, + "loss": 3.5829, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433318286672306e-05, + "loss": 3.584, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432479691921254e-05, + "loss": 3.588, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431641097170201e-05, + "loss": 3.5983, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430802502419149e-05, + "loss": 3.5871, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429963907668097e-05, + "loss": 3.5638, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291269507974186e-05, + "loss": 3.5739, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282883560463666e-05, + "loss": 3.5887, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274497612953146e-05, + "loss": 3.5843, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266111665442626e-05, + "loss": 3.576, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425774209673584e-05, + "loss": 3.5847, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249356149225315e-05, + "loss": 3.5827, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4240970201714795e-05, + "loss": 3.5735, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232584254204275e-05, + "loss": 3.5743, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224214685497484e-05, + "loss": 3.5835, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4215828737986964e-05, + "loss": 3.5823, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207442790476444e-05, + "loss": 3.5891, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199056842965924e-05, + "loss": 3.5697, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419068727425913e-05, + "loss": 3.5747, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418230132674862e-05, + "loss": 3.5842, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.41739153792381e-05, + "loss": 3.5831, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416552943172758e-05, + "loss": 3.5835, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415714348421706e-05, + "loss": 3.5717, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414875753670654e-05, + "loss": 3.5729, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414038796799975e-05, + "loss": 3.5672, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413200202048923e-05, + "loss": 3.5816, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412361607297871e-05, + "loss": 3.5681, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411523012546819e-05, + "loss": 3.5709, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.41068605567614e-05, + "loss": 3.5813, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409847460925088e-05, + "loss": 3.5757, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409008866174036e-05, + "loss": 3.5728, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408170271422984e-05, + "loss": 3.5746, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073333145523054e-05, + "loss": 3.5607, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4064947198012534e-05, + "loss": 3.5826, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056561250502014e-05, + "loss": 3.5698, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048175302991494e-05, + "loss": 3.578, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.40398057342847e-05, + "loss": 3.5801, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403141978677418e-05, + "loss": 3.5821, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402303383926366e-05, + "loss": 3.5778, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401464789175314e-05, + "loss": 3.5778, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400627832304635e-05, + "loss": 3.5849, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399789237553583e-05, + "loss": 3.5785, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398950642802531e-05, + "loss": 3.5743, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398112048051479e-05, + "loss": 3.577, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397275091180801e-05, + "loss": 3.5738, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396436496429749e-05, + "loss": 3.583, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395597901678697e-05, + "loss": 3.5662, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394759306927645e-05, + "loss": 3.5705, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939223500569656e-05, + "loss": 3.5684, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3930837553059136e-05, + "loss": 3.5745, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922451605548616e-05, + "loss": 3.5838, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914065658038096e-05, + "loss": 3.5737, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905679710527576e-05, + "loss": 3.5857, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897310141820785e-05, + "loss": 3.5704, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888924194310265e-05, + "loss": 3.5799, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880538246799745e-05, + "loss": 3.5773, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872152299289225e-05, + "loss": 3.5847, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386378273058244e-05, + "loss": 3.5773, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385539678307192e-05, + "loss": 3.5785, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.38470108355614e-05, + "loss": 3.575, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383862488805088e-05, + "loss": 3.5908, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383025531934409e-05, + "loss": 3.573, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382186937183357e-05, + "loss": 3.5728, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381348342432305e-05, + "loss": 3.5816, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380509747681253e-05, + "loss": 3.572, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379672790810574e-05, + "loss": 3.573, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378834196059522e-05, + "loss": 3.5837, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.37799560130847e-05, + "loss": 3.5676, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377157006557418e-05, + "loss": 3.5734, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763200496867395e-05, + "loss": 3.571, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.844698667526245, + "eval_runtime": 302.5494, + "eval_samples_per_second": 1261.252, + "eval_steps_per_second": 39.415, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3754814549356875e-05, + "loss": 3.5692, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746428601846355e-05, + "loss": 3.5609, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738042654335834e-05, + "loss": 3.574, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3729656706825314e-05, + "loss": 3.5875, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721287138118524e-05, + "loss": 3.5798, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3712901190608003e-05, + "loss": 3.578, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704515243097483e-05, + "loss": 3.5673, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696129295586963e-05, + "loss": 3.5772, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368775972688017e-05, + "loss": 3.5654, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367937377936965e-05, + "loss": 3.5761, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367098783185913e-05, + "loss": 3.5744, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366260188434861e-05, + "loss": 3.5769, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365424869444556e-05, + "loss": 3.5829, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364586274693504e-05, + "loss": 3.5613, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363747679942452e-05, + "loss": 3.5598, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629090851914e-05, + "loss": 3.5611, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362070490440348e-05, + "loss": 3.5843, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361231895689296e-05, + "loss": 3.5699, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360393300938244e-05, + "loss": 3.5683, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359554706187192e-05, + "loss": 3.5804, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587177493165126e-05, + "loss": 3.5883, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3578791545654606e-05, + "loss": 3.5705, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3570405598144086e-05, + "loss": 3.5697, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3562019650633566e-05, + "loss": 3.5704, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355365008192678e-05, + "loss": 3.5809, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354526413441626e-05, + "loss": 3.5661, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353687818690574e-05, + "loss": 3.5636, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528492239395215e-05, + "loss": 3.5852, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352012267068843e-05, + "loss": 3.5551, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351173672317791e-05, + "loss": 3.5619, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350335077566739e-05, + "loss": 3.5627, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3494964828156864e-05, + "loss": 3.5669, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348659525945008e-05, + "loss": 3.5734, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347820931193956e-05, + "loss": 3.5816, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346982336442904e-05, + "loss": 3.5677, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346143741691852e-05, + "loss": 3.5652, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453051469408e-05, + "loss": 3.577, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444681900701216e-05, + "loss": 3.5584, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343629595319069e-05, + "loss": 3.5669, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342791000568017e-05, + "loss": 3.5672, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341952405816965e-05, + "loss": 3.5645, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411154489462864e-05, + "loss": 3.5597, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340276854195234e-05, + "loss": 3.5813, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339438259444182e-05, + "loss": 3.5663, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.33859966469313e-05, + "loss": 3.5677, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3377627078224513e-05, + "loss": 3.5739, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3369241130713993e-05, + "loss": 3.5663, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336085518320347e-05, + "loss": 3.5667, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335246923569295e-05, + "loss": 3.5446, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334408328818243e-05, + "loss": 3.5635, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333571371947564e-05, + "loss": 3.5762, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332732777196512e-05, + "loss": 3.572, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.33189418244546e-05, + "loss": 3.5567, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331055587694408e-05, + "loss": 3.5551, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330218630823729e-05, + "loss": 3.5611, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329380036072677e-05, + "loss": 3.5515, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328541441321625e-05, + "loss": 3.5855, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327704484450947e-05, + "loss": 3.5539, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326865889699895e-05, + "loss": 3.5727, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326027294948843e-05, + "loss": 3.5691, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325188700197791e-05, + "loss": 3.5511, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324350105446739e-05, + "loss": 3.5608, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3235131485760596e-05, + "loss": 3.5535, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3226745538250076e-05, + "loss": 3.556, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3218359590739556e-05, + "loss": 3.5551, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3209973643229036e-05, + "loss": 3.5753, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3201604074522245e-05, + "loss": 3.565, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193218127011725e-05, + "loss": 3.5589, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3184832179501205e-05, + "loss": 3.551, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176446231990685e-05, + "loss": 3.5601, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3168060284480165e-05, + "loss": 3.5656, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315969071577338e-05, + "loss": 3.5686, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315130476826286e-05, + "loss": 3.562, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314291882075234e-05, + "loss": 3.566, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313453287324182e-05, + "loss": 3.5777, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.31261469257313e-05, + "loss": 3.5616, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311777735702451e-05, + "loss": 3.5616, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310939140951399e-05, + "loss": 3.5632, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310100546200347e-05, + "loss": 3.5644, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309261951449295e-05, + "loss": 3.5671, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308423356698243e-05, + "loss": 3.567, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307586399827564e-05, + "loss": 3.571, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306747805076512e-05, + "loss": 3.5775, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059092103254605e-05, + "loss": 3.5714, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050706155744085e-05, + "loss": 3.5481, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042320208233565e-05, + "loss": 3.5567, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3033950639526774e-05, + "loss": 3.5722, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025564692016254e-05, + "loss": 3.5685, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017178744505734e-05, + "loss": 3.5628, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3008792796995214e-05, + "loss": 3.5627, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300042322828842e-05, + "loss": 3.571, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.29920372807779e-05, + "loss": 3.5552, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298365133326738e-05, + "loss": 3.5578, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297526538575686e-05, + "loss": 3.5672, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296689581705007e-05, + "loss": 3.5627, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295850986953956e-05, + "loss": 3.5767, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295012392202904e-05, + "loss": 3.5507, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294173797451852e-05, + "loss": 3.5528, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2933352027008e-05, + "loss": 3.5691, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292498245830121e-05, + "loss": 3.5694, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291659651079069e-05, + "loss": 3.5667, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290821056328017e-05, + "loss": 3.5578, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289982461576964e-05, + "loss": 3.5552, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289145504706286e-05, + "loss": 3.5489, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288306909955234e-05, + "loss": 3.5668, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287468315204182e-05, + "loss": 3.5527, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.28662972045313e-05, + "loss": 3.5546, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285792763582451e-05, + "loss": 3.5657, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284954168831399e-05, + "loss": 3.5612, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284115574080347e-05, + "loss": 3.5489, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2832769793292946e-05, + "loss": 3.5609, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282440022458616e-05, + "loss": 3.5464, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281601427707564e-05, + "loss": 3.5646, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2807628329565115e-05, + "loss": 3.5549, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799242382054595e-05, + "loss": 3.559, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279087281334781e-05, + "loss": 3.5639, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278248686583729e-05, + "loss": 3.562, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774100918326764e-05, + "loss": 3.559, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276571497081625e-05, + "loss": 3.5637, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275734540210946e-05, + "loss": 3.5716, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2748959454598946e-05, + "loss": 3.5569, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274057350708842e-05, + "loss": 3.5561, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.27321875595779e-05, + "loss": 3.5592, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272380161206738e-05, + "loss": 3.5612, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271543204336059e-05, + "loss": 3.5639, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270704609585007e-05, + "loss": 3.5521, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269866014833955e-05, + "loss": 3.5536, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269027420082903e-05, + "loss": 3.5524, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268190463212224e-05, + "loss": 3.5543, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267351868461172e-05, + "loss": 3.5651, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.26651327371012e-05, + "loss": 3.5634, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2656746789590684e-05, + "loss": 3.5665, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264837722088389e-05, + "loss": 3.554, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263999127337337e-05, + "loss": 3.5636, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263160532586285e-05, + "loss": 3.5594, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262321937835233e-05, + "loss": 3.5713, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261484980964554e-05, + "loss": 3.5567, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260646386213502e-05, + "loss": 3.5615, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.25980779146245e-05, + "loss": 3.5591, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258969196711398e-05, + "loss": 3.5723, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258132239840719e-05, + "loss": 3.5585, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257293645089667e-05, + "loss": 3.5552, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256455050338615e-05, + "loss": 3.5657, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255616455587564e-05, + "loss": 3.5564, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254779498716885e-05, + "loss": 3.5541, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253940903965833e-05, + "loss": 3.5696, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253102309214781e-05, + "loss": 3.5453, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522637144637287e-05, + "loss": 3.5632, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514267575930496e-05, + "loss": 3.5498, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.844769239425659, + "eval_runtime": 302.9283, + "eval_samples_per_second": 1259.674, + "eval_steps_per_second": 39.366, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2505881628419976e-05, + "loss": 3.5537, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497495680909456e-05, + "loss": 3.5461, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489109733398936e-05, + "loss": 3.5551, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480723785888416e-05, + "loss": 3.571, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472354217181625e-05, + "loss": 3.5656, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2463968269671105e-05, + "loss": 3.5617, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245558232216059e-05, + "loss": 3.5475, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244719637465007e-05, + "loss": 3.5619, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243881042713955e-05, + "loss": 3.5531, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243044085843276e-05, + "loss": 3.5567, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242205491092224e-05, + "loss": 3.5596, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241366896341172e-05, + "loss": 3.561, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240529939470493e-05, + "loss": 3.5677, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239691344719441e-05, + "loss": 3.5455, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238852749968389e-05, + "loss": 3.5418, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238014155217337e-05, + "loss": 3.5457, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237175560466285e-05, + "loss": 3.5654, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236336965715233e-05, + "loss": 3.5572, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235498370964181e-05, + "loss": 3.5517, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234659776213129e-05, + "loss": 3.5613, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338228193424505e-05, + "loss": 3.5744, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2329842245913985e-05, + "loss": 3.5528, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321456298403465e-05, + "loss": 3.5518, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313070350892945e-05, + "loss": 3.5568, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304684403382425e-05, + "loss": 3.5658, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296314834675634e-05, + "loss": 3.547, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2287928887165114e-05, + "loss": 3.5513, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2279542939654594e-05, + "loss": 3.5652, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271156992144074e-05, + "loss": 3.5435, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226278742343728e-05, + "loss": 3.544, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225440147592676e-05, + "loss": 3.5445, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224601552841624e-05, + "loss": 3.5529, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223762958090572e-05, + "loss": 3.5589, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222926001219894e-05, + "loss": 3.5617, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222087406468842e-05, + "loss": 3.5551, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.22124881171779e-05, + "loss": 3.5492, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220410216966737e-05, + "loss": 3.5606, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219573260096059e-05, + "loss": 3.5406, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218734665345007e-05, + "loss": 3.5523, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217896070593955e-05, + "loss": 3.5506, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217057475842902e-05, + "loss": 3.5516, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.21621888109185e-05, + "loss": 3.5415, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2153819242211716e-05, + "loss": 3.565, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145433294701196e-05, + "loss": 3.5497, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2137047347190676e-05, + "loss": 3.5544, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2128661399680156e-05, + "loss": 3.5566, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212029183097337e-05, + "loss": 3.5499, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2111905883462845e-05, + "loss": 3.5502, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103519935952325e-05, + "loss": 3.5314, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095133988441805e-05, + "loss": 3.5495, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208676441973502e-05, + "loss": 3.5579, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078378472224494e-05, + "loss": 3.5526, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2069992524713974e-05, + "loss": 3.5423, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061606577203454e-05, + "loss": 3.538, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205323700849667e-05, + "loss": 3.5478, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204485106098615e-05, + "loss": 3.5351, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203646511347563e-05, + "loss": 3.5682, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202807916596511e-05, + "loss": 3.5416, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201970959725832e-05, + "loss": 3.5528, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.20113236497478e-05, + "loss": 3.557, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200293770223728e-05, + "loss": 3.5374, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199455175472676e-05, + "loss": 3.5428, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198616580721624e-05, + "loss": 3.5412, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197779623850945e-05, + "loss": 3.5375, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196941029099893e-05, + "loss": 3.5354, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196102434348841e-05, + "loss": 3.5611, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195263839597789e-05, + "loss": 3.5493, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944268827271104e-05, + "loss": 3.5425, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1935882879760584e-05, + "loss": 3.5357, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927496932250064e-05, + "loss": 3.5419, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919110984739544e-05, + "loss": 3.5493, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191074141603275e-05, + "loss": 3.5513, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190235546852223e-05, + "loss": 3.5463, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189396952101171e-05, + "loss": 3.5515, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188558357350119e-05, + "loss": 3.5572, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.18772140047944e-05, + "loss": 3.5508, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186882805728388e-05, + "loss": 3.5426, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186044210977336e-05, + "loss": 3.55, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185205616226284e-05, + "loss": 3.5478, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184368659355606e-05, + "loss": 3.5495, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183530064604554e-05, + "loss": 3.5541, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182691469853502e-05, + "loss": 3.5557, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.18185287510245e-05, + "loss": 3.5623, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181014280351398e-05, + "loss": 3.5508, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801773234807186e-05, + "loss": 3.5361, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793387287296666e-05, + "loss": 3.5436, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785001339786146e-05, + "loss": 3.5576, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776615392275626e-05, + "loss": 3.5521, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768245823568835e-05, + "loss": 3.5467, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1759859876058315e-05, + "loss": 3.5457, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1751473928547795e-05, + "loss": 3.5532, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1743087981037275e-05, + "loss": 3.5403, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173471841233049e-05, + "loss": 3.5484, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172633246481997e-05, + "loss": 3.5423, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171794651730945e-05, + "loss": 3.551, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170956056979893e-05, + "loss": 3.5536, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170119100109214e-05, + "loss": 3.5467, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169280505358162e-05, + "loss": 3.5326, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.16844191060711e-05, + "loss": 3.5536, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167603315856058e-05, + "loss": 3.5508, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166766358985379e-05, + "loss": 3.5496, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165927764234327e-05, + "loss": 3.5445, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165089169483275e-05, + "loss": 3.5378, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164250574732223e-05, + "loss": 3.5372, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634136178615445e-05, + "loss": 3.5487, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625750231104925e-05, + "loss": 3.5375, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617364283594405e-05, + "loss": 3.5372, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1608978336083884e-05, + "loss": 3.5495, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600608767377094e-05, + "loss": 3.5496, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592222819866574e-05, + "loss": 3.5363, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1583836872356054e-05, + "loss": 3.544, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575450924845533e-05, + "loss": 3.5337, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567064977335013e-05, + "loss": 3.5477, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155869540862822e-05, + "loss": 3.5396, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.15503094611177e-05, + "loss": 3.5439, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154192351360718e-05, + "loss": 3.5478, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153353756609667e-05, + "loss": 3.5504, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152516799738988e-05, + "loss": 3.5432, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151678204987936e-05, + "loss": 3.5464, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150839610236884e-05, + "loss": 3.5542, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150001015485832e-05, + "loss": 3.5445, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149164058615153e-05, + "loss": 3.5372, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148325463864101e-05, + "loss": 3.5471, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147486869113049e-05, + "loss": 3.5436, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146648274361997e-05, + "loss": 3.5514, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458113174913176e-05, + "loss": 3.5373, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1449727227402656e-05, + "loss": 3.5359, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441341279892136e-05, + "loss": 3.5385, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143295533238162e-05, + "loss": 3.5448, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142458576367483e-05, + "loss": 3.5401, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141619981616431e-05, + "loss": 3.5498, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140781386865379e-05, + "loss": 3.5502, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139942792114327e-05, + "loss": 3.5396, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139105835243648e-05, + "loss": 3.5472, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138267240492596e-05, + "loss": 3.5456, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137428645741544e-05, + "loss": 3.5546, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136590050990492e-05, + "loss": 3.5403, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135753094119813e-05, + "loss": 3.5453, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134914499368761e-05, + "loss": 3.5481, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134075904617709e-05, + "loss": 3.5527, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133237309866657e-05, + "loss": 3.5423, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324003529959786e-05, + "loss": 3.5398, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315617582449266e-05, + "loss": 3.5488, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307231634938745e-05, + "loss": 3.5395, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129884568742822e-05, + "loss": 3.5388, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290476118721435e-05, + "loss": 3.5545, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282090171210915e-05, + "loss": 3.5364, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273704223700394e-05, + "loss": 3.5455, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126531827618987e-05, + "loss": 3.5367, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.845672845840454, + "eval_runtime": 303.1832, + "eval_samples_per_second": 1258.615, + "eval_steps_per_second": 39.333, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1256948707483084e-05, + "loss": 3.5361, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248562759972563e-05, + "loss": 3.5332, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240176812462043e-05, + "loss": 3.5389, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123179086495152e-05, + "loss": 3.5549, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122342129624474e-05, + "loss": 3.5486, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121503534873422e-05, + "loss": 3.5495, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120664940122369e-05, + "loss": 3.5366, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119826345371317e-05, + "loss": 3.546, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118989388500639e-05, + "loss": 3.5357, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118150793749587e-05, + "loss": 3.5438, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117312198998534e-05, + "loss": 3.5409, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116473604247482e-05, + "loss": 3.5491, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156382852571766e-05, + "loss": 3.5576, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114799690506125e-05, + "loss": 3.5317, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113961095755073e-05, + "loss": 3.5259, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113122501004021e-05, + "loss": 3.5265, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112283906252969e-05, + "loss": 3.5451, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114453115019166e-05, + "loss": 3.5427, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106067167508646e-05, + "loss": 3.5394, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1097681219998126e-05, + "loss": 3.5416, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108931165129134e-05, + "loss": 3.5656, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1080925703780815e-05, + "loss": 3.5378, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072539756270295e-05, + "loss": 3.5356, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064153808759775e-05, + "loss": 3.5418, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1055767861249255e-05, + "loss": 3.5506, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104739829254247e-05, + "loss": 3.5294, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103901234503195e-05, + "loss": 3.5385, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103062639752143e-05, + "loss": 3.5483, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102224045001091e-05, + "loss": 3.5356, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101387088130412e-05, + "loss": 3.5293, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.10054849337936e-05, + "loss": 3.5257, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099709898628308e-05, + "loss": 3.5368, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098871303877256e-05, + "loss": 3.5463, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098034347006577e-05, + "loss": 3.5448, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097195752255525e-05, + "loss": 3.5406, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096357157504473e-05, + "loss": 3.5329, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095518562753421e-05, + "loss": 3.5434, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0946816058827424e-05, + "loss": 3.5285, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938430111316904e-05, + "loss": 3.5358, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930044163806384e-05, + "loss": 3.5355, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921658216295864e-05, + "loss": 3.5346, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913272268785344e-05, + "loss": 3.5266, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090490270007855e-05, + "loss": 3.5497, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089651675256803e-05, + "loss": 3.534, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088813080505751e-05, + "loss": 3.5389, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087974485754699e-05, + "loss": 3.5459, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.08713752888402e-05, + "loss": 3.5333, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086298934132968e-05, + "loss": 3.5348, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085460339381916e-05, + "loss": 3.5168, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084621744630864e-05, + "loss": 3.5324, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083784787760186e-05, + "loss": 3.5429, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082946193009134e-05, + "loss": 3.5392, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082107598258082e-05, + "loss": 3.5288, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.08126900350703e-05, + "loss": 3.525, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080432046636351e-05, + "loss": 3.5324, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079593451885299e-05, + "loss": 3.5234, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078754857134247e-05, + "loss": 3.5481, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077916262383195e-05, + "loss": 3.5277, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0770793055125156e-05, + "loss": 3.5375, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762407107614636e-05, + "loss": 3.5446, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754021160104116e-05, + "loss": 3.5198, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0745635212593596e-05, + "loss": 3.5258, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073726564388681e-05, + "loss": 3.527, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072887969637629e-05, + "loss": 3.521, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072049374886577e-05, + "loss": 3.5226, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071210780135525e-05, + "loss": 3.5395, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070373823264846e-05, + "loss": 3.5373, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069535228513794e-05, + "loss": 3.5292, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068696633762742e-05, + "loss": 3.5187, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.06785803901169e-05, + "loss": 3.5279, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067021082141011e-05, + "loss": 3.5344, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066182487389959e-05, + "loss": 3.5361, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065343892638907e-05, + "loss": 3.5352, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064505297887855e-05, + "loss": 3.5349, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636683410171765e-05, + "loss": 3.54, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628297462661245e-05, + "loss": 3.537, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0619911515150725e-05, + "loss": 3.5241, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611525567640205e-05, + "loss": 3.5388, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603155998933414e-05, + "loss": 3.5335, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0594770051422894e-05, + "loss": 3.53, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586384103912374e-05, + "loss": 3.5428, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0577998156401854e-05, + "loss": 3.5372, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056962858769506e-05, + "loss": 3.5485, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056124264018454e-05, + "loss": 3.5386, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055285669267402e-05, + "loss": 3.5223, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.05444707451635e-05, + "loss": 3.5257, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053608479765298e-05, + "loss": 3.5376, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.05277152289462e-05, + "loss": 3.5401, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051932928143568e-05, + "loss": 3.5334, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0510943333925156e-05, + "loss": 3.5291, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050255738641464e-05, + "loss": 3.5383, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494187817707848e-05, + "loss": 3.5267, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485801870197328e-05, + "loss": 3.5313, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477415922686808e-05, + "loss": 3.528, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469029975176288e-05, + "loss": 3.5354, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.04606604064695e-05, + "loss": 3.543, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045227445895898e-05, + "loss": 3.531, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044388851144846e-05, + "loss": 3.5208, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043550256393794e-05, + "loss": 3.535, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042713299523115e-05, + "loss": 3.5381, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041874704772063e-05, + "loss": 3.5366, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.041036110021011e-05, + "loss": 3.5266, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0401975152699593e-05, + "loss": 3.5252, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.03936055839928e-05, + "loss": 3.5194, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038521963648228e-05, + "loss": 3.537, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037683368897176e-05, + "loss": 3.5206, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036844774146124e-05, + "loss": 3.5293, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360078172754454e-05, + "loss": 3.5326, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351692225243934e-05, + "loss": 3.5299, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343306277733414e-05, + "loss": 3.5216, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334920330222894e-05, + "loss": 3.5265, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326550761516103e-05, + "loss": 3.5225, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318164814005583e-05, + "loss": 3.5334, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309778866495063e-05, + "loss": 3.5243, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030139291898454e-05, + "loss": 3.5291, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293023350277755e-05, + "loss": 3.5292, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284637402767235e-05, + "loss": 3.5355, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276251455256715e-05, + "loss": 3.5281, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267865507746192e-05, + "loss": 3.5333, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259495939039408e-05, + "loss": 3.5377, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251109991528888e-05, + "loss": 3.533, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242724044018368e-05, + "loss": 3.517, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023433809650784e-05, + "loss": 3.535, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0225968527801057e-05, + "loss": 3.5302, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217582580290537e-05, + "loss": 3.5384, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209196632780013e-05, + "loss": 3.5234, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200810685269493e-05, + "loss": 3.5233, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019244111656271e-05, + "loss": 3.5252, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018405516905219e-05, + "loss": 3.5282, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175669221541662e-05, + "loss": 3.5261, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167283274031145e-05, + "loss": 3.536, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015891370532436e-05, + "loss": 3.5379, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015052775781384e-05, + "loss": 3.5282, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142141810303314e-05, + "loss": 3.5286, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133755862792794e-05, + "loss": 3.5314, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125369915282274e-05, + "loss": 3.537, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117000346575487e-05, + "loss": 3.5342, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108614399064967e-05, + "loss": 3.5309, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100228451554447e-05, + "loss": 3.5355, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091842504043927e-05, + "loss": 3.5334, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083472935337136e-05, + "loss": 3.5295, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075086987826616e-05, + "loss": 3.5256, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.00667010403161e-05, + "loss": 3.5338, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005831509280558e-05, + "loss": 3.525, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049945524098788e-05, + "loss": 3.5205, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041559576588268e-05, + "loss": 3.5421, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033173629077748e-05, + "loss": 3.5249, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024787681567228e-05, + "loss": 3.5274, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001641811286044e-05, + "loss": 3.5228, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000803216534992e-05, + "loss": 3.524, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8458034992218018, + "eval_runtime": 303.1829, + "eval_samples_per_second": 1258.616, + "eval_steps_per_second": 39.333, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.99996462178394e-05, + "loss": 3.5149, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999126027032888e-05, + "loss": 3.526, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998287432281836e-05, + "loss": 3.54, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997448837530784e-05, + "loss": 3.5332, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966118806601053e-05, + "loss": 3.5358, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957732859090533e-05, + "loss": 3.5211, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949346911580013e-05, + "loss": 3.5289, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940960964069493e-05, + "loss": 3.521, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932591395362702e-05, + "loss": 3.5318, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924205447852182e-05, + "loss": 3.5277, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915819500341662e-05, + "loss": 3.5332, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990743355283114e-05, + "loss": 3.534, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899063984124354e-05, + "loss": 3.5253, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890678036613834e-05, + "loss": 3.5111, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882292089103314e-05, + "loss": 3.5171, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9873906141592794e-05, + "loss": 3.5215, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865536572886006e-05, + "loss": 3.5307, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857150625375486e-05, + "loss": 3.5225, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848764677864966e-05, + "loss": 3.5292, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840378730354446e-05, + "loss": 3.5528, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832009161647655e-05, + "loss": 3.5232, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823623214137135e-05, + "loss": 3.5218, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815237266626615e-05, + "loss": 3.5272, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806851319116095e-05, + "loss": 3.535, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798481750409308e-05, + "loss": 3.5154, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790095802898788e-05, + "loss": 3.5221, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781709855388268e-05, + "loss": 3.5355, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773323907877748e-05, + "loss": 3.521, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9764954339170957e-05, + "loss": 3.511, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975656839166044e-05, + "loss": 3.513, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974818244414992e-05, + "loss": 3.524, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.97397964966394e-05, + "loss": 3.53, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.973142692793261e-05, + "loss": 3.5358, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972304098042209e-05, + "loss": 3.5206, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971465503291157e-05, + "loss": 3.5162, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970626908540105e-05, + "loss": 3.5312, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969789951669426e-05, + "loss": 3.5117, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.968951356918374e-05, + "loss": 3.5247, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968112762167322e-05, + "loss": 3.5169, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.96727416741627e-05, + "loss": 3.5231, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966437210545591e-05, + "loss": 3.5105, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655986157945394e-05, + "loss": 3.5356, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647600210434874e-05, + "loss": 3.5191, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639214262924354e-05, + "loss": 3.5216, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630828315413834e-05, + "loss": 3.5295, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622458746707043e-05, + "loss": 3.5239, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614072799196523e-05, + "loss": 3.5196, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605686851686003e-05, + "loss": 3.5065, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597300904175486e-05, + "loss": 3.5134, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588931335468695e-05, + "loss": 3.5299, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580545387958175e-05, + "loss": 3.525, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572159440447655e-05, + "loss": 3.5124, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563773492937135e-05, + "loss": 3.5119, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555403924230347e-05, + "loss": 3.5193, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547017976719827e-05, + "loss": 3.5101, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538632029209307e-05, + "loss": 3.5301, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530246081698787e-05, + "loss": 3.5156, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521860134188267e-05, + "loss": 3.5222, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513490565481476e-05, + "loss": 3.527, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505104617970956e-05, + "loss": 3.5144, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949671867046044e-05, + "loss": 3.5074, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948833272294992e-05, + "loss": 3.5155, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.947996315424313e-05, + "loss": 3.5087, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.947157720673261e-05, + "loss": 3.5107, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946319125922209e-05, + "loss": 3.5262, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454805311711565e-05, + "loss": 3.5259, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944643574300478e-05, + "loss": 3.5135, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943804979549426e-05, + "loss": 3.5098, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942966384798374e-05, + "loss": 3.5092, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421277900473214e-05, + "loss": 3.5192, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941290833176643e-05, + "loss": 3.5209, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940452238425591e-05, + "loss": 3.522, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396136436745387e-05, + "loss": 3.5209, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387750489234867e-05, + "loss": 3.5259, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379364541724346e-05, + "loss": 3.5277, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9370994973017562e-05, + "loss": 3.5076, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936260902550704e-05, + "loss": 3.5209, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935422307799652e-05, + "loss": 3.5218, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345837130486e-05, + "loss": 3.5131, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337467561779215e-05, + "loss": 3.5284, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329081614268688e-05, + "loss": 3.5241, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320695666758168e-05, + "loss": 3.5317, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312309719247648e-05, + "loss": 3.5259, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930394015054086e-05, + "loss": 3.5062, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929555420303034e-05, + "loss": 3.5151, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928716825551982e-05, + "loss": 3.5234, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.92787823080093e-05, + "loss": 3.5247, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.927041273930251e-05, + "loss": 3.5206, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262026791791993e-05, + "loss": 3.5167, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253640844281473e-05, + "loss": 3.5213, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245254896770952e-05, + "loss": 3.5144, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923688532806416e-05, + "loss": 3.5142, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.922849938055364e-05, + "loss": 3.5147, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922011343304312e-05, + "loss": 3.5225, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.92117274855326e-05, + "loss": 3.5346, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203357916825814e-05, + "loss": 3.5124, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194971969315294e-05, + "loss": 3.5068, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186586021804774e-05, + "loss": 3.518, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178200074294254e-05, + "loss": 3.5226, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169830505587463e-05, + "loss": 3.5243, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161444558076946e-05, + "loss": 3.5128, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153058610566426e-05, + "loss": 3.5165, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144672663055906e-05, + "loss": 3.501, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136303094349115e-05, + "loss": 3.5218, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127917146838595e-05, + "loss": 3.5115, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119531199328075e-05, + "loss": 3.5103, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111145251817555e-05, + "loss": 3.5174, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102775683110768e-05, + "loss": 3.5191, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094389735600248e-05, + "loss": 3.5084, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086003788089728e-05, + "loss": 3.5154, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077617840579207e-05, + "loss": 3.5093, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069231893068687e-05, + "loss": 3.5188, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.90608623243619e-05, + "loss": 3.5082, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905247637685138e-05, + "loss": 3.5157, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904409042934086e-05, + "loss": 3.5192, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903570448183034e-05, + "loss": 3.5193, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902733491312355e-05, + "loss": 3.5163, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901894896561303e-05, + "loss": 3.5191, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901056301810251e-05, + "loss": 3.5243, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900217707059199e-05, + "loss": 3.5186, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.89938075018852e-05, + "loss": 3.505, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898542155437468e-05, + "loss": 3.5236, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897703560686416e-05, + "loss": 3.5156, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896864965935364e-05, + "loss": 3.5209, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896028009064685e-05, + "loss": 3.5125, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951894143136334e-05, + "loss": 3.5097, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943508195625813e-05, + "loss": 3.5069, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935122248115293e-05, + "loss": 3.5137, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926752679408503e-05, + "loss": 3.5142, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918366731897982e-05, + "loss": 3.5244, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8909980784387462e-05, + "loss": 3.5238, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901594836876942e-05, + "loss": 3.5114, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893225268170155e-05, + "loss": 3.5126, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8884839320659635e-05, + "loss": 3.5188, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876453373149115e-05, + "loss": 3.5218, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868067425638595e-05, + "loss": 3.5222, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859697856931804e-05, + "loss": 3.5215, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851311909421287e-05, + "loss": 3.5165, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8842925961910767e-05, + "loss": 3.5189, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834540014400247e-05, + "loss": 3.5167, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826170445693456e-05, + "loss": 3.5131, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817784498182936e-05, + "loss": 3.5223, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809398550672416e-05, + "loss": 3.5147, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801012603161896e-05, + "loss": 3.5029, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.879264303445511e-05, + "loss": 3.5314, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878425708694459e-05, + "loss": 3.5126, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877587113943407e-05, + "loss": 3.5139, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876748519192355e-05, + "loss": 3.5089, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759115623216758e-05, + "loss": 3.51, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8483121395111084, + "eval_runtime": 306.7781, + "eval_samples_per_second": 1243.867, + "eval_steps_per_second": 38.872, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.875072967570624e-05, + "loss": 3.5006, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874234372819572e-05, + "loss": 3.5164, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.87339577806852e-05, + "loss": 3.5286, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872558821197841e-05, + "loss": 3.5127, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871720226446789e-05, + "loss": 3.5296, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870881631695737e-05, + "loss": 3.5038, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870043036944685e-05, + "loss": 3.5165, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692060800740062e-05, + "loss": 3.5059, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683674853229542e-05, + "loss": 3.519, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675288905719022e-05, + "loss": 3.5156, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8666902958208502e-05, + "loss": 3.5161, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865853338950171e-05, + "loss": 3.5178, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650163820794924e-05, + "loss": 3.5104, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641777873284404e-05, + "loss": 3.5025, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633391925773884e-05, + "loss": 3.5038, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625005978263364e-05, + "loss": 3.5094, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616620030752843e-05, + "loss": 3.5172, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608234083242323e-05, + "loss": 3.5082, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599848135731803e-05, + "loss": 3.5141, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591462188221287e-05, + "loss": 3.5383, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583092619514496e-05, + "loss": 3.5107, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574706672003976e-05, + "loss": 3.5056, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566320724493456e-05, + "loss": 3.5132, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557934776982936e-05, + "loss": 3.5179, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549565208276148e-05, + "loss": 3.5019, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541179260765628e-05, + "loss": 3.5131, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532793313255108e-05, + "loss": 3.5155, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524407365744588e-05, + "loss": 3.5101, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516037797037797e-05, + "loss": 3.4946, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507651849527277e-05, + "loss": 3.5032, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499265902016757e-05, + "loss": 3.5078, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849087995450624e-05, + "loss": 3.5173, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482494006995714e-05, + "loss": 3.5234, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847412443828893e-05, + "loss": 3.5089, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.846573849077841e-05, + "loss": 3.5041, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457352543267886e-05, + "loss": 3.5171, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8448966595757366e-05, + "loss": 3.4994, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440597027050582e-05, + "loss": 3.512, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432211079540062e-05, + "loss": 3.5012, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423825132029535e-05, + "loss": 3.5075, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415439184519015e-05, + "loss": 3.4998, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840706961581223e-05, + "loss": 3.5221, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.839868366830171e-05, + "loss": 3.5107, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390297720791187e-05, + "loss": 3.5071, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381911773280667e-05, + "loss": 3.5132, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373542204573883e-05, + "loss": 3.512, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365156257063356e-05, + "loss": 3.5008, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835677030955284e-05, + "loss": 3.4984, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834838436204232e-05, + "loss": 3.4982, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340014793335535e-05, + "loss": 3.5163, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833162884582501e-05, + "loss": 3.5088, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832324289831449e-05, + "loss": 3.4988, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831485695080397e-05, + "loss": 3.499, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306487382097184e-05, + "loss": 3.506, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829810143458666e-05, + "loss": 3.4992, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.828971548707614e-05, + "loss": 3.5146, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.828132953956562e-05, + "loss": 3.504, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827295997085883e-05, + "loss": 3.5066, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826457402334831e-05, + "loss": 3.515, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256188075837793e-05, + "loss": 3.4975, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247802128327273e-05, + "loss": 3.4948, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239432559620482e-05, + "loss": 3.5062, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231046612109962e-05, + "loss": 3.4913, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222660664599442e-05, + "loss": 3.4961, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214274717088922e-05, + "loss": 3.5096, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205905148382135e-05, + "loss": 3.5135, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197519200871615e-05, + "loss": 3.5009, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189133253361095e-05, + "loss": 3.4982, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180747305850575e-05, + "loss": 3.4903, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172377737143784e-05, + "loss": 3.5066, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8163991789633264e-05, + "loss": 3.5079, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155605842122747e-05, + "loss": 3.5076, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147219894612227e-05, + "loss": 3.5102, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138850325905436e-05, + "loss": 3.5113, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130464378394916e-05, + "loss": 3.516, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122078430884396e-05, + "loss": 3.4963, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113692483373876e-05, + "loss": 3.5074, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810532291466709e-05, + "loss": 3.5101, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809693696715657e-05, + "loss": 3.4944, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808855101964605e-05, + "loss": 3.5191, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080165072135528e-05, + "loss": 3.5122, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071795503428737e-05, + "loss": 3.5168, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063409555918217e-05, + "loss": 3.5155, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055023608407697e-05, + "loss": 3.4927, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804663766089718e-05, + "loss": 3.5053, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803826809219039e-05, + "loss": 3.5062, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802988214467987e-05, + "loss": 3.5132, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802149619716935e-05, + "loss": 3.5103, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801311024965883e-05, + "loss": 3.5017, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004740680952042e-05, + "loss": 3.5101, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996354733441522e-05, + "loss": 3.506, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7987968785931002e-05, + "loss": 3.4955, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979582838420482e-05, + "loss": 3.5006, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971196890909962e-05, + "loss": 3.5112, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796282732220317e-05, + "loss": 3.5197, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795444137469265e-05, + "loss": 3.5021, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946055427182134e-05, + "loss": 3.4907, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937669479671614e-05, + "loss": 3.508, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929299910964823e-05, + "loss": 3.5098, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920913963454303e-05, + "loss": 3.508, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912528015943783e-05, + "loss": 3.5025, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904142068433263e-05, + "loss": 3.5011, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895772499726476e-05, + "loss": 3.4917, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887386552215956e-05, + "loss": 3.5054, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879000604705436e-05, + "loss": 3.4956, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870614657194916e-05, + "loss": 3.4985, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862245088488125e-05, + "loss": 3.5023, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853859140977605e-05, + "loss": 3.5073, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845473193467088e-05, + "loss": 3.4931, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837087245956568e-05, + "loss": 3.5041, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828717677249777e-05, + "loss": 3.4987, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820331729739257e-05, + "loss": 3.5016, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811945782228737e-05, + "loss": 3.4968, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803559834718217e-05, + "loss": 3.499, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779519026601143e-05, + "loss": 3.5091, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778680431850091e-05, + "loss": 3.5076, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777841837099039e-05, + "loss": 3.5026, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.777003242347987e-05, + "loss": 3.5047, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776166285477308e-05, + "loss": 3.5101, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753276907262558e-05, + "loss": 3.5053, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774489095975204e-05, + "loss": 3.4921, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773650501224152e-05, + "loss": 3.5114, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728119064731e-05, + "loss": 3.5004, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771974949602421e-05, + "loss": 3.5083, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771136354851369e-05, + "loss": 3.4967, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770297760100317e-05, + "loss": 3.4968, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769459165349265e-05, + "loss": 3.4938, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686222084785863e-05, + "loss": 3.4971, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677836137275343e-05, + "loss": 3.499, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669450189764823e-05, + "loss": 3.5107, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661080621058032e-05, + "loss": 3.514, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652694673547512e-05, + "loss": 3.5033, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644308726036995e-05, + "loss": 3.4947, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635922778526475e-05, + "loss": 3.5059, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627536831015955e-05, + "loss": 3.5074, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619167262309164e-05, + "loss": 3.5113, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610781314798644e-05, + "loss": 3.5054, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602395367288124e-05, + "loss": 3.5061, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594009419777604e-05, + "loss": 3.4991, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585639851070817e-05, + "loss": 3.5091, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577253903560297e-05, + "loss": 3.5026, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568867956049777e-05, + "loss": 3.5036, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560482008539257e-05, + "loss": 3.5055, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552112439832466e-05, + "loss": 3.4931, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754372649232195e-05, + "loss": 3.5174, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753534054481143e-05, + "loss": 3.4998, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.752695459730091e-05, + "loss": 3.4988, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518585028594118e-05, + "loss": 3.4946, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510199081083598e-05, + "loss": 3.4957, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.849315881729126, + "eval_runtime": 305.6421, + "eval_samples_per_second": 1248.49, + "eval_steps_per_second": 39.016, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501813133573078e-05, + "loss": 3.4846, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493427186062558e-05, + "loss": 3.5032, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485041238552034e-05, + "loss": 3.5145, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476655291041514e-05, + "loss": 3.4989, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746828572233473e-05, + "loss": 3.5171, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.745989977482421e-05, + "loss": 3.4949, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451513827313687e-05, + "loss": 3.5047, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443127879803167e-05, + "loss": 3.4891, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434758311096383e-05, + "loss": 3.5053, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426372363585856e-05, + "loss": 3.5033, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417986416075336e-05, + "loss": 3.4998, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409600468564816e-05, + "loss": 3.5123, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401247278661764e-05, + "loss": 3.495, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392861331151244e-05, + "loss": 3.4908, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384475383640724e-05, + "loss": 3.4905, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376089436130204e-05, + "loss": 3.4959, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367703488619677e-05, + "loss": 3.5041, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359317541109157e-05, + "loss": 3.4949, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735093159359864e-05, + "loss": 3.5018, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734254564608812e-05, + "loss": 3.5225, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733417607738133e-05, + "loss": 3.4981, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732579012987081e-05, + "loss": 3.4932, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731740418236029e-05, + "loss": 3.5018, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730901823484977e-05, + "loss": 3.5053, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300648666142982e-05, + "loss": 3.4907, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292262718632462e-05, + "loss": 3.5019, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283876771121942e-05, + "loss": 3.5017, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727549082361142e-05, + "loss": 3.4958, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726712125490463e-05, + "loss": 3.4839, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725873530739411e-05, + "loss": 3.4927, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250349359883594e-05, + "loss": 3.4961, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7241963412373074e-05, + "loss": 3.499, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233593843666283e-05, + "loss": 3.5135, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225207896155763e-05, + "loss": 3.4928, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216821948645243e-05, + "loss": 3.4915, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208436001134723e-05, + "loss": 3.5039, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200066432427935e-05, + "loss": 3.4912, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191680484917415e-05, + "loss": 3.4948, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183294537406895e-05, + "loss": 3.4887, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174908589896375e-05, + "loss": 3.4968, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166539021189584e-05, + "loss": 3.4845, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158153073679064e-05, + "loss": 3.5115, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149767126168544e-05, + "loss": 3.4927, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141381178658028e-05, + "loss": 3.5015, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7132995231147508e-05, + "loss": 3.5009, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124625662440717e-05, + "loss": 3.4958, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116239714930197e-05, + "loss": 3.4934, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107853767419677e-05, + "loss": 3.4829, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099467819909157e-05, + "loss": 3.4828, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709109825120237e-05, + "loss": 3.5039, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708271230369185e-05, + "loss": 3.4969, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707432635618133e-05, + "loss": 3.4871, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706594040867081e-05, + "loss": 3.4883, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057570839964018e-05, + "loss": 3.4958, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049184892453498e-05, + "loss": 3.4787, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704079894494298e-05, + "loss": 3.501, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703241299743246e-05, + "loss": 3.4912, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702404342872567e-05, + "loss": 3.4887, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701565748121515e-05, + "loss": 3.5069, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700727153370463e-05, + "loss": 3.4867, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699888558619411e-05, + "loss": 3.4845, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990516017487323e-05, + "loss": 3.4946, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982130069976803e-05, + "loss": 3.4805, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973744122466283e-05, + "loss": 3.4846, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965358174955763e-05, + "loss": 3.4971, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956988606248972e-05, + "loss": 3.5006, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694860265873845e-05, + "loss": 3.4856, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940216711227935e-05, + "loss": 3.4887, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931830763717415e-05, + "loss": 3.4765, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923461195010624e-05, + "loss": 3.4956, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915075247500104e-05, + "loss": 3.4895, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906689299989584e-05, + "loss": 3.4969, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898303352479064e-05, + "loss": 3.4967, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6889917404968544e-05, + "loss": 3.4979, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881547836261756e-05, + "loss": 3.5091, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873161888751236e-05, + "loss": 3.4831, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864775941240716e-05, + "loss": 3.4966, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856389993730196e-05, + "loss": 3.4988, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848020425023405e-05, + "loss": 3.482, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683963447751289e-05, + "loss": 3.5043, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683124853000237e-05, + "loss": 3.4988, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682286258249185e-05, + "loss": 3.5034, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814493013785058e-05, + "loss": 3.5006, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806107066274538e-05, + "loss": 3.4811, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797721118764018e-05, + "loss": 3.4945, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789335171253498e-05, + "loss": 3.4912, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.678096560254671e-05, + "loss": 3.5005, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677257965503619e-05, + "loss": 3.4941, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676419370752567e-05, + "loss": 3.4901, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.675580776001515e-05, + "loss": 3.4965, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674743819130836e-05, + "loss": 3.493, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739052243797842e-05, + "loss": 3.4823, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730666296287322e-05, + "loss": 3.4882, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722280348776802e-05, + "loss": 3.4978, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671391078007001e-05, + "loss": 3.5051, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670552483255949e-05, + "loss": 3.4944, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669713888504897e-05, + "loss": 3.4773, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668875293753845e-05, + "loss": 3.4932, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680383368831664e-05, + "loss": 3.4978, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6671997421321144e-05, + "loss": 3.4942, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663611473810624e-05, + "loss": 3.4898, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655225526300104e-05, + "loss": 3.4899, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646855957593313e-05, + "loss": 3.4792, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638470010082796e-05, + "loss": 3.4969, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630084062572276e-05, + "loss": 3.4775, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621698115061756e-05, + "loss": 3.4883, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613328546354965e-05, + "loss": 3.4844, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6604942598844445e-05, + "loss": 3.5003, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596556651333925e-05, + "loss": 3.4777, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588170703823405e-05, + "loss": 3.4937, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579801135116617e-05, + "loss": 3.4853, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571415187606097e-05, + "loss": 3.4854, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563029240095577e-05, + "loss": 3.4883, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554643292585057e-05, + "loss": 3.4839, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546273723878266e-05, + "loss": 3.4961, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653788777636775e-05, + "loss": 3.4942, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.652950182885723e-05, + "loss": 3.4904, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521115881346703e-05, + "loss": 3.4908, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.651274631263992e-05, + "loss": 3.4964, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.65043603651294e-05, + "loss": 3.4967, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.649597441761888e-05, + "loss": 3.4761, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487588470108355e-05, + "loss": 3.4973, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647921890140157e-05, + "loss": 3.4908, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.647083295389105e-05, + "loss": 3.4946, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646244700638053e-05, + "loss": 3.4874, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454061058870004e-05, + "loss": 3.4889, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644569149016322e-05, + "loss": 3.4786, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.64373055426527e-05, + "loss": 3.4842, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6428919595142177e-05, + "loss": 3.4864, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420533647631657e-05, + "loss": 3.4979, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412164078924872e-05, + "loss": 3.5015, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403778131414352e-05, + "loss": 3.4908, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639539218390383e-05, + "loss": 3.4811, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638700623639331e-05, + "loss": 3.4924, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378636667686525e-05, + "loss": 3.497, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370250720176005e-05, + "loss": 3.4967, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361864772665478e-05, + "loss": 3.4945, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353478825154958e-05, + "loss": 3.4882, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345109256448174e-05, + "loss": 3.4926, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633672330893765e-05, + "loss": 3.497, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632833736142713e-05, + "loss": 3.4866, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.631995141391661e-05, + "loss": 3.4924, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311581845209826e-05, + "loss": 3.4912, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303195897699303e-05, + "loss": 3.4798, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294809950188783e-05, + "loss": 3.5018, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286424002678263e-05, + "loss": 3.491, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627805443397148e-05, + "loss": 3.4863, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626966848646095e-05, + "loss": 3.4824, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626128253895043e-05, + "loss": 3.481, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8502516746520996, + "eval_runtime": 354.204, + "eval_samples_per_second": 1077.32, + "eval_steps_per_second": 33.667, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625289659143991e-05, + "loss": 3.4754, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244527022733124e-05, + "loss": 3.4887, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236141075222604e-05, + "loss": 3.4999, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227755127712084e-05, + "loss": 3.4894, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219369180201564e-05, + "loss": 3.508, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6210999611494773e-05, + "loss": 3.4776, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202613663984253e-05, + "loss": 3.4957, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194227716473736e-05, + "loss": 3.4764, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6185841768963216e-05, + "loss": 3.4921, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177455821452696e-05, + "loss": 3.4918, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169086252745905e-05, + "loss": 3.4857, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160700305235385e-05, + "loss": 3.499, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152330736528598e-05, + "loss": 3.4827, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143944789018078e-05, + "loss": 3.4794, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135558841507558e-05, + "loss": 3.4778, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127172893997038e-05, + "loss": 3.4839, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118786946486518e-05, + "loss": 3.4899, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110400998975997e-05, + "loss": 3.4819, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102015051465477e-05, + "loss": 3.49, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093629103954957e-05, + "loss": 3.5081, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.608525953524817e-05, + "loss": 3.4878, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.607687358773765e-05, + "loss": 3.4841, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606848764022713e-05, + "loss": 3.4875, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.606010169271661e-05, + "loss": 3.4924, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605173212400982e-05, + "loss": 3.4761, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.60433461764993e-05, + "loss": 3.4906, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6034960228988782e-05, + "loss": 3.4888, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026574281478262e-05, + "loss": 3.4822, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.601820471277147e-05, + "loss": 3.476, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.600981876526095e-05, + "loss": 3.4757, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600143281775043e-05, + "loss": 3.4864, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599304687023991e-05, + "loss": 3.4859, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984677301533124e-05, + "loss": 3.4996, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976291354022603e-05, + "loss": 3.4876, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967905406512083e-05, + "loss": 3.4745, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959519459001563e-05, + "loss": 3.4898, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951149890294772e-05, + "loss": 3.4824, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942763942784252e-05, + "loss": 3.4784, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934377995273736e-05, + "loss": 3.4793, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5925992047763216e-05, + "loss": 3.4825, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917622479056425e-05, + "loss": 3.475, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909236531545905e-05, + "loss": 3.495, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900850584035385e-05, + "loss": 3.4831, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892464636524865e-05, + "loss": 3.4871, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884078689014345e-05, + "loss": 3.4919, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875709120307557e-05, + "loss": 3.4822, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867323172797037e-05, + "loss": 3.4837, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5858937225286517e-05, + "loss": 3.4705, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850551277775997e-05, + "loss": 3.4638, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842181709069206e-05, + "loss": 3.4937, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583379576155869e-05, + "loss": 3.4849, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582540981404817e-05, + "loss": 3.4787, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581702386653765e-05, + "loss": 3.4751, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.580865429783086e-05, + "loss": 3.4805, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.580026835032034e-05, + "loss": 3.469, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.579188240280982e-05, + "loss": 3.4867, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.57834964552993e-05, + "loss": 3.4839, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577512688659251e-05, + "loss": 3.4778, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576674093908199e-05, + "loss": 3.4897, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575835499157147e-05, + "loss": 3.4737, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.574996904406095e-05, + "loss": 3.4695, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.574159947535416e-05, + "loss": 3.488, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733213527843643e-05, + "loss": 3.4643, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724827580333123e-05, + "loss": 3.4691, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716441632822603e-05, + "loss": 3.4884, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708072064115812e-05, + "loss": 3.4888, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699686116605292e-05, + "loss": 3.4698, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691300169094772e-05, + "loss": 3.4825, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682914221584252e-05, + "loss": 3.4613, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674544652877464e-05, + "loss": 3.4835, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666158705366944e-05, + "loss": 3.4786, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657772757856424e-05, + "loss": 3.4866, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649386810345904e-05, + "loss": 3.4797, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641017241639113e-05, + "loss": 3.4886, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632631294128597e-05, + "loss": 3.4961, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624245346618077e-05, + "loss": 3.4684, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615859399107557e-05, + "loss": 3.4856, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607489830400766e-05, + "loss": 3.4865, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599103882890246e-05, + "loss": 3.4659, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590717935379726e-05, + "loss": 3.4953, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582331987869202e-05, + "loss": 3.4881, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5573962419162418e-05, + "loss": 3.488, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565576471651898e-05, + "loss": 3.4913, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557190524141378e-05, + "loss": 3.4719, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554880457663085e-05, + "loss": 3.4735, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540435007924067e-05, + "loss": 3.4818, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532049060413547e-05, + "loss": 3.4886, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552366311290303e-05, + "loss": 3.4822, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515277165392504e-05, + "loss": 3.4807, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550690759668572e-05, + "loss": 3.4781, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.54985216491752e-05, + "loss": 3.4875, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490135701664676e-05, + "loss": 3.4693, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481749754154156e-05, + "loss": 3.476, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473380185447372e-05, + "loss": 3.4872, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5464994237936852e-05, + "loss": 3.4916, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456608290426325e-05, + "loss": 3.4836, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448222342915805e-05, + "loss": 3.4646, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543985277420902e-05, + "loss": 3.4803, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431466826698497e-05, + "loss": 3.484, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423080879187977e-05, + "loss": 3.4823, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414694931677457e-05, + "loss": 3.4807, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406308984166937e-05, + "loss": 3.4782, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397939415460146e-05, + "loss": 3.4671, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538955346794963e-05, + "loss": 3.4808, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538116752043911e-05, + "loss": 3.4683, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537278157292859e-05, + "loss": 3.4756, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.53644120042218e-05, + "loss": 3.4695, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535602605671128e-05, + "loss": 3.4854, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534764010920076e-05, + "loss": 3.4679, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533925416169024e-05, + "loss": 3.4851, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533088459298345e-05, + "loss": 3.4695, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.532249864547293e-05, + "loss": 3.4743, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.531411269796241e-05, + "loss": 3.4751, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530572675045189e-05, + "loss": 3.4755, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.52973571817451e-05, + "loss": 3.4813, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5288971234234583e-05, + "loss": 3.4859, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280585286724063e-05, + "loss": 3.4782, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272199339213543e-05, + "loss": 3.4762, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5263829770506752e-05, + "loss": 3.4816, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255443822996232e-05, + "loss": 3.484, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247057875485712e-05, + "loss": 3.4637, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238671927975192e-05, + "loss": 3.4851, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230302359268405e-05, + "loss": 3.4755, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221916411757885e-05, + "loss": 3.4847, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213530464247365e-05, + "loss": 3.4748, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205144516736845e-05, + "loss": 3.4781, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196774948030054e-05, + "loss": 3.4651, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188389000519537e-05, + "loss": 3.4771, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180003053009017e-05, + "loss": 3.4731, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171617105498497e-05, + "loss": 3.4796, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163247536791706e-05, + "loss": 3.4881, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154861589281186e-05, + "loss": 3.4822, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146475641770666e-05, + "loss": 3.4669, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138089694260146e-05, + "loss": 3.4804, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512972012555336e-05, + "loss": 3.4842, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121334178042838e-05, + "loss": 3.4843, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5112948230532318e-05, + "loss": 3.4811, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104562283021798e-05, + "loss": 3.4781, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096192714315007e-05, + "loss": 3.479, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508780676680449e-05, + "loss": 3.4875, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507942081929397e-05, + "loss": 3.4723, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507103487178345e-05, + "loss": 3.4821, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506266530307666e-05, + "loss": 3.4752, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505427935556614e-05, + "loss": 3.4742, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504589340805562e-05, + "loss": 3.4878, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.50375074605451e-05, + "loss": 3.4813, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029137891838312e-05, + "loss": 3.4739, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020751944327792e-05, + "loss": 3.4671, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012365996817272e-05, + "loss": 3.4717, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8522465229034424, + "eval_runtime": 344.5231, + "eval_samples_per_second": 1107.592, + "eval_steps_per_second": 34.613, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5003980049306752e-05, + "loss": 3.4598, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995594101796232e-05, + "loss": 3.4774, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987208154285712e-05, + "loss": 3.4843, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978822206775192e-05, + "loss": 3.4794, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970452638068404e-05, + "loss": 3.4939, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962066690557884e-05, + "loss": 3.472, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953680743047364e-05, + "loss": 3.4787, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494529479553684e-05, + "loss": 3.4695, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936925226830053e-05, + "loss": 3.4773, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928539279319537e-05, + "loss": 3.4805, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920153331809016e-05, + "loss": 3.475, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911767384298493e-05, + "loss": 3.4866, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903397815591706e-05, + "loss": 3.4674, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895011868081186e-05, + "loss": 3.4688, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886625920570662e-05, + "loss": 3.4667, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878239973060145e-05, + "loss": 3.4694, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869870404353358e-05, + "loss": 3.4799, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861484456842838e-05, + "loss": 3.4676, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853098509332314e-05, + "loss": 3.4787, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844712561821794e-05, + "loss": 3.4947, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836342993115007e-05, + "loss": 3.4782, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4827957045604487e-05, + "loss": 3.4734, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819571098093967e-05, + "loss": 3.4748, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811185150583447e-05, + "loss": 3.4757, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480281558187666e-05, + "loss": 3.4655, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794429634366136e-05, + "loss": 3.4788, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786043686855616e-05, + "loss": 3.4763, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.47776577393451e-05, + "loss": 3.4715, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476928817063831e-05, + "loss": 3.4652, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4760902223127788e-05, + "loss": 3.4676, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752516275617268e-05, + "loss": 3.4702, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744130328106748e-05, + "loss": 3.4759, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.473576075939996e-05, + "loss": 3.4867, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.472737481188944e-05, + "loss": 3.4745, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.471898886437892e-05, + "loss": 3.4625, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.47106029168684e-05, + "loss": 3.4774, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470223334816161e-05, + "loss": 3.4775, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469384740065109e-05, + "loss": 3.4621, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468546145314057e-05, + "loss": 3.4653, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677075505630053e-05, + "loss": 3.4732, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668705936923262e-05, + "loss": 3.4615, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660319989412742e-05, + "loss": 3.485, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651934041902222e-05, + "loss": 3.4714, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643548094391702e-05, + "loss": 3.4704, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635178525684914e-05, + "loss": 3.4784, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626792578174394e-05, + "loss": 3.4751, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618406630663874e-05, + "loss": 3.4721, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610020683153354e-05, + "loss": 3.4599, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601651114446563e-05, + "loss": 3.4485, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593265166936043e-05, + "loss": 3.4877, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584879219425523e-05, + "loss": 3.4687, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576493271915006e-05, + "loss": 3.4699, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568123703208216e-05, + "loss": 3.4656, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559737755697695e-05, + "loss": 3.4616, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551351808187175e-05, + "loss": 3.4585, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542965860676655e-05, + "loss": 3.4719, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534596291969868e-05, + "loss": 3.4722, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526210344459348e-05, + "loss": 3.4661, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517824396948828e-05, + "loss": 3.4833, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509438449438308e-05, + "loss": 3.4594, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501068880731517e-05, + "loss": 3.4543, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492682933220997e-05, + "loss": 3.4809, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484296985710477e-05, + "loss": 3.449, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447591103819996e-05, + "loss": 3.4547, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446754146949317e-05, + "loss": 3.477, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445915552198265e-05, + "loss": 3.4757, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445076957447213e-05, + "loss": 3.4601, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444238362696161e-05, + "loss": 3.47, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.443401405825482e-05, + "loss": 3.453, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.44256281107443e-05, + "loss": 3.471, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441724216323378e-05, + "loss": 3.4662, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440885621572326e-05, + "loss": 3.4739, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440048664701647e-05, + "loss": 3.4685, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439210069950595e-05, + "loss": 3.475, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438371475199543e-05, + "loss": 3.4831, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375328804484914e-05, + "loss": 3.4622, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366959235778123e-05, + "loss": 3.4693, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358573288267603e-05, + "loss": 3.4756, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350187340757083e-05, + "loss": 3.4527, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434180139324656e-05, + "loss": 3.4805, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333431824539775e-05, + "loss": 3.479, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325045877029255e-05, + "loss": 3.4768, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316659929518735e-05, + "loss": 3.48, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.430827398200821e-05, + "loss": 3.4632, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299904413301424e-05, + "loss": 3.461, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291518465790904e-05, + "loss": 3.4686, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283132518280384e-05, + "loss": 3.4793, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274746570769864e-05, + "loss": 3.4718, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266377002063077e-05, + "loss": 3.4676, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257991054552556e-05, + "loss": 3.4664, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249605107042033e-05, + "loss": 3.4755, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241219159531513e-05, + "loss": 3.4624, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232849590824725e-05, + "loss": 3.4623, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422446364331421e-05, + "loss": 3.4708, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216077695803685e-05, + "loss": 3.482, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207691748293165e-05, + "loss": 3.4723, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199322179586378e-05, + "loss": 3.4563, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190936232075854e-05, + "loss": 3.4667, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182550284565338e-05, + "loss": 3.4703, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174164337054818e-05, + "loss": 3.4709, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416579476834803e-05, + "loss": 3.4678, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157408820837507e-05, + "loss": 3.4698, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149022873326987e-05, + "loss": 3.4551, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140636925816467e-05, + "loss": 3.4673, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.413226735710968e-05, + "loss": 3.4592, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412388140959916e-05, + "loss": 3.467, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411549546208864e-05, + "loss": 3.4522, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410710951457812e-05, + "loss": 3.4815, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.40987235670676e-05, + "loss": 3.4597, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090353998360808e-05, + "loss": 3.4663, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408196805085029e-05, + "loss": 3.4603, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.407358210333977e-05, + "loss": 3.4618, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406519615582925e-05, + "loss": 3.4638, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405682658712246e-05, + "loss": 3.4654, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404844063961194e-05, + "loss": 3.4689, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404005469210142e-05, + "loss": 3.4725, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.40316687445909e-05, + "loss": 3.4659, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023299175884113e-05, + "loss": 3.4652, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014913228373593e-05, + "loss": 3.4693, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006527280863073e-05, + "loss": 3.4774, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998141333352553e-05, + "loss": 3.4501, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989771764645762e-05, + "loss": 3.4747, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981385817135245e-05, + "loss": 3.4608, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972999869624725e-05, + "loss": 3.4732, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964613922114205e-05, + "loss": 3.463, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956244353407414e-05, + "loss": 3.4672, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947858405896894e-05, + "loss": 3.455, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939472458386374e-05, + "loss": 3.4614, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931086510875854e-05, + "loss": 3.4672, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922716942169066e-05, + "loss": 3.4664, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914330994658546e-05, + "loss": 3.4714, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905945047148026e-05, + "loss": 3.4745, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897559099637506e-05, + "loss": 3.4565, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889189530930715e-05, + "loss": 3.4691, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.38808035834202e-05, + "loss": 3.4746, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387241763590968e-05, + "loss": 3.4725, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386403168839916e-05, + "loss": 3.4696, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855662119692368e-05, + "loss": 3.47, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847276172181848e-05, + "loss": 3.4627, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838890224671328e-05, + "loss": 3.4765, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830504277160808e-05, + "loss": 3.4587, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382213470845402e-05, + "loss": 3.4691, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.38137487609435e-05, + "loss": 3.4651, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380536281343298e-05, + "loss": 3.4629, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796976865922457e-05, + "loss": 3.4742, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378860729721567e-05, + "loss": 3.4703, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378022134970515e-05, + "loss": 3.4648, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771835402194632e-05, + "loss": 3.4519, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376344945468411e-05, + "loss": 3.462, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8515069484710693, + "eval_runtime": 303.2108, + "eval_samples_per_second": 1258.501, + "eval_steps_per_second": 39.329, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375507988597732e-05, + "loss": 3.455, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.37466939384668e-05, + "loss": 3.4623, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.373830799095628e-05, + "loss": 3.4735, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.372992204344576e-05, + "loss": 3.4683, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721552474738974e-05, + "loss": 3.4813, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713166527228454e-05, + "loss": 3.4622, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370478057971793e-05, + "loss": 3.4636, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369639463220741e-05, + "loss": 3.46, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3688025063500623e-05, + "loss": 3.4604, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679639115990103e-05, + "loss": 3.4705, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671253168479583e-05, + "loss": 3.4654, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662867220969063e-05, + "loss": 3.4712, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654497652262275e-05, + "loss": 3.4623, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646111704751755e-05, + "loss": 3.4577, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363772575724123e-05, + "loss": 3.4553, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629339809730715e-05, + "loss": 3.4568, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620953862220195e-05, + "loss": 3.4654, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612567914709675e-05, + "loss": 3.4605, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604181967199155e-05, + "loss": 3.4665, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595796019688635e-05, + "loss": 3.4827, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587426450981844e-05, + "loss": 3.4712, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579040503471324e-05, + "loss": 3.456, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570654555960807e-05, + "loss": 3.4649, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562268608450287e-05, + "loss": 3.4637, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553899039743496e-05, + "loss": 3.4569, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545513092232976e-05, + "loss": 3.4693, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537127144722456e-05, + "loss": 3.4622, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528741197211933e-05, + "loss": 3.4626, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.352037162850515e-05, + "loss": 3.4572, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.351198568099463e-05, + "loss": 3.454, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.350359973348411e-05, + "loss": 3.4604, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495213785973585e-05, + "loss": 3.4641, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486844217266798e-05, + "loss": 3.4708, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478458269756277e-05, + "loss": 3.465, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470072322245757e-05, + "loss": 3.4521, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461686374735237e-05, + "loss": 3.468, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345331680602845e-05, + "loss": 3.4651, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.344493085851793e-05, + "loss": 3.4453, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436544911007406e-05, + "loss": 3.4603, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428158963496886e-05, + "loss": 3.457, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419789394790102e-05, + "loss": 3.4534, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411403447279582e-05, + "loss": 3.4716, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340301749976906e-05, + "loss": 3.4611, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339463155225854e-05, + "loss": 3.46, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338626198355175e-05, + "loss": 3.4643, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.337787603604123e-05, + "loss": 3.4618, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.336949008853071e-05, + "loss": 3.4623, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.336110414102019e-05, + "loss": 3.4482, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352734572313404e-05, + "loss": 3.4334, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334434862480288e-05, + "loss": 3.4776, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333596267729236e-05, + "loss": 3.4561, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332757672978184e-05, + "loss": 3.4629, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319207161075056e-05, + "loss": 3.4513, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310821213564532e-05, + "loss": 3.4518, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302435266054012e-05, + "loss": 3.4492, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294049318543492e-05, + "loss": 3.4559, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285679749836705e-05, + "loss": 3.4637, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277293802326185e-05, + "loss": 3.4513, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268907854815665e-05, + "loss": 3.4736, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260521907305145e-05, + "loss": 3.4528, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252152338598354e-05, + "loss": 3.4436, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243766391087834e-05, + "loss": 3.468, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235380443577314e-05, + "loss": 3.443, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3226994496066794e-05, + "loss": 3.4416, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3218624927360006e-05, + "loss": 3.4659, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210238979849486e-05, + "loss": 3.4612, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201853032338966e-05, + "loss": 3.4503, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193467084828446e-05, + "loss": 3.4555, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185097516121655e-05, + "loss": 3.4408, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317671156861114e-05, + "loss": 3.4589, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316832562110062e-05, + "loss": 3.4521, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.31599396735901e-05, + "loss": 3.4643, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151570104883308e-05, + "loss": 3.4569, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143184157372787e-05, + "loss": 3.461, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134798209862267e-05, + "loss": 3.4716, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126412262351747e-05, + "loss": 3.4518, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311804269364496e-05, + "loss": 3.4603, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310965674613444e-05, + "loss": 3.4609, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310127079862392e-05, + "loss": 3.4449, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.30928848511134e-05, + "loss": 3.4684, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308451528240661e-05, + "loss": 3.47, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076129334896092e-05, + "loss": 3.4626, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067743387385572e-05, + "loss": 3.4738, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059357439875052e-05, + "loss": 3.4489, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305098787116826e-05, + "loss": 3.4474, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304260192365774e-05, + "loss": 3.4605, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303421597614722e-05, + "loss": 3.4632, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.30258300286367e-05, + "loss": 3.4642, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017460459929914e-05, + "loss": 3.4551, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009074512419393e-05, + "loss": 3.4515, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000688564908873e-05, + "loss": 3.4655, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992302617398353e-05, + "loss": 3.4514, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2983933048691562e-05, + "loss": 3.4508, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2975547101181046e-05, + "loss": 3.4592, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967161153670526e-05, + "loss": 3.4704, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958775206160006e-05, + "loss": 3.4613, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950405637453215e-05, + "loss": 3.4431, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942019689942695e-05, + "loss": 3.4547, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933633742432175e-05, + "loss": 3.4588, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925247794921655e-05, + "loss": 3.4592, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916878226214867e-05, + "loss": 3.4566, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908492278704347e-05, + "loss": 3.457, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900106331193827e-05, + "loss": 3.4404, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891720383683304e-05, + "loss": 3.4523, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883350814976516e-05, + "loss": 3.4523, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2874964867465996e-05, + "loss": 3.4573, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286657891995548e-05, + "loss": 3.4402, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858192972444956e-05, + "loss": 3.4707, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.284982340373817e-05, + "loss": 3.4469, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.284143745622765e-05, + "loss": 3.4549, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.283305150871713e-05, + "loss": 3.4447, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.282466556120661e-05, + "loss": 3.4585, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281627961369609e-05, + "loss": 3.4508, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.28079100449893e-05, + "loss": 3.4508, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799524097478777e-05, + "loss": 3.4587, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2791138149968257e-05, + "loss": 3.4655, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782752202457737e-05, + "loss": 3.45, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277438263375095e-05, + "loss": 3.4622, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276599668624043e-05, + "loss": 3.4515, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275761073872991e-05, + "loss": 3.4649, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274922479121939e-05, + "loss": 3.4442, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740855222512602e-05, + "loss": 3.4622, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.273246927500208e-05, + "loss": 3.4495, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724083327491562e-05, + "loss": 3.4613, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715697379981042e-05, + "loss": 3.4535, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.270732781127425e-05, + "loss": 3.4563, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.269894186376373e-05, + "loss": 3.4417, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.269055591625321e-05, + "loss": 3.4512, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268216996874269e-05, + "loss": 3.4553, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673800400035903e-05, + "loss": 3.4568, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665414452525383e-05, + "loss": 3.4551, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657028505014863e-05, + "loss": 3.4636, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648642557504343e-05, + "loss": 3.4479, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640272988797552e-05, + "loss": 3.458, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631887041287032e-05, + "loss": 3.4612, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623501093776516e-05, + "loss": 3.4637, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615115146265996e-05, + "loss": 3.4542, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606745577559205e-05, + "loss": 3.4575, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598359630048685e-05, + "loss": 3.4503, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589973682538165e-05, + "loss": 3.4695, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581587735027645e-05, + "loss": 3.448, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573218166320857e-05, + "loss": 3.4597, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564832218810337e-05, + "loss": 3.45, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556446271299817e-05, + "loss": 3.4535, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548060323789297e-05, + "loss": 3.4616, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539690755082506e-05, + "loss": 3.4538, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531304807571986e-05, + "loss": 3.4573, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522918860061466e-05, + "loss": 3.4379, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251453291255095e-05, + "loss": 3.4542, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.854020118713379, + "eval_runtime": 303.2259, + "eval_samples_per_second": 1258.438, + "eval_steps_per_second": 39.327, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250616334384416e-05, + "loss": 3.4445, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249777739633364e-05, + "loss": 3.45, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248939144882312e-05, + "loss": 3.4616, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481005501312598e-05, + "loss": 3.4578, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.247263593260581e-05, + "loss": 3.4683, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.246424998509529e-05, + "loss": 3.4501, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245586403758477e-05, + "loss": 3.4509, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244747809007425e-05, + "loss": 3.4503, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243910852136746e-05, + "loss": 3.4495, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243072257385694e-05, + "loss": 3.462, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242233662634642e-05, + "loss": 3.4529, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413950678835903e-05, + "loss": 3.4583, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405597488932845e-05, + "loss": 3.4503, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239721154142232e-05, + "loss": 3.4461, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.23888255939118e-05, + "loss": 3.4464, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.238043964640128e-05, + "loss": 3.4433, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372053698890764e-05, + "loss": 3.456, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363667751380244e-05, + "loss": 3.4493, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355281803869724e-05, + "loss": 3.4518, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346895856359204e-05, + "loss": 3.4684, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338526287652413e-05, + "loss": 3.4648, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330140340141893e-05, + "loss": 3.4486, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321754392631373e-05, + "loss": 3.4476, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313368445120853e-05, + "loss": 3.454, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304998876414066e-05, + "loss": 3.4489, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296612928903546e-05, + "loss": 3.4545, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288226981393026e-05, + "loss": 3.4542, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279841033882502e-05, + "loss": 3.4519, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271471465175718e-05, + "loss": 3.4443, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263085517665198e-05, + "loss": 3.446, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254699570154678e-05, + "loss": 3.4409, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246313622644155e-05, + "loss": 3.4534, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237944053937367e-05, + "loss": 3.4607, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229558106426847e-05, + "loss": 3.4578, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221172158916327e-05, + "loss": 3.4412, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212786211405807e-05, + "loss": 3.4528, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220441664269902e-05, + "loss": 3.4553, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.21960306951885e-05, + "loss": 3.4387, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187644747677976e-05, + "loss": 3.4481, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179258800167456e-05, + "loss": 3.446, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170889231460672e-05, + "loss": 3.4406, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216250328395015e-05, + "loss": 3.4587, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154117336439628e-05, + "loss": 3.4488, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214574776773284e-05, + "loss": 3.4519, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.213736182022232e-05, + "loss": 3.4522, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.21289758727118e-05, + "loss": 3.4498, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.212058992520128e-05, + "loss": 3.4534, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112220356494493e-05, + "loss": 3.4397, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103834408983973e-05, + "loss": 3.4181, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209544846147345e-05, + "loss": 3.4651, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208706251396293e-05, + "loss": 3.4467, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078692945256142e-05, + "loss": 3.4533, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070306997745622e-05, + "loss": 3.4431, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061921050235102e-05, + "loss": 3.4404, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053535102724582e-05, + "loss": 3.4335, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045165534017794e-05, + "loss": 3.4468, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203677958650727e-05, + "loss": 3.4552, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028393638996754e-05, + "loss": 3.4394, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020007691486234e-05, + "loss": 3.4602, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011638122779447e-05, + "loss": 3.4439, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003252175268923e-05, + "loss": 3.4328, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994866227758403e-05, + "loss": 3.4535, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986480280247883e-05, + "loss": 3.4368, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978110711541096e-05, + "loss": 3.4277, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969724764030576e-05, + "loss": 3.4561, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961338816520056e-05, + "loss": 3.4518, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952952869009536e-05, + "loss": 3.4395, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944583300302745e-05, + "loss": 3.4429, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936197352792225e-05, + "loss": 3.4334, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927811405281705e-05, + "loss": 3.4463, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919425457771188e-05, + "loss": 3.444, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911055889064397e-05, + "loss": 3.4479, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902669941553877e-05, + "loss": 3.448, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894283994043357e-05, + "loss": 3.4495, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885898046532837e-05, + "loss": 3.4614, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187752847782605e-05, + "loss": 3.4386, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186914253031553e-05, + "loss": 3.4533, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186075658280501e-05, + "loss": 3.4465, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185237063529449e-05, + "loss": 3.4352, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.184398468778397e-05, + "loss": 3.4545, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.183561511907718e-05, + "loss": 3.4603, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.182722917156666e-05, + "loss": 3.4485, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.181884322405614e-05, + "loss": 3.4608, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181045727654562e-05, + "loss": 3.4377, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180208770783883e-05, + "loss": 3.436, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179370176032831e-05, + "loss": 3.4484, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178531581281779e-05, + "loss": 3.4579, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177692986530727e-05, + "loss": 3.4459, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768560296600483e-05, + "loss": 3.4468, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760174349089963e-05, + "loss": 3.4439, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1751788401579443e-05, + "loss": 3.4509, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743402454068923e-05, + "loss": 3.4401, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1735032885362132e-05, + "loss": 3.4409, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726646937851612e-05, + "loss": 3.449, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718260990341095e-05, + "loss": 3.4595, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709875042830575e-05, + "loss": 3.4483, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701505474123784e-05, + "loss": 3.4292, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693119526613264e-05, + "loss": 3.4476, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684733579102744e-05, + "loss": 3.4456, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676347631592224e-05, + "loss": 3.4515, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1667978062885437e-05, + "loss": 3.4441, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659592115374917e-05, + "loss": 3.4443, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651206167864397e-05, + "loss": 3.4353, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642836599157606e-05, + "loss": 3.4369, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634450651647086e-05, + "loss": 3.447, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626064704136566e-05, + "loss": 3.4443, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161767875662605e-05, + "loss": 3.4293, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609309187919258e-05, + "loss": 3.4602, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600923240408738e-05, + "loss": 3.4368, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592537292898218e-05, + "loss": 3.4409, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584151345387695e-05, + "loss": 3.435, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.157578177668091e-05, + "loss": 3.4453, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156739582917039e-05, + "loss": 3.4436, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155900988165987e-05, + "loss": 3.4396, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550623934149347e-05, + "loss": 3.4481, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.154225436544256e-05, + "loss": 3.4491, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.153386841793204e-05, + "loss": 3.4425, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.152548247042152e-05, + "loss": 3.4507, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517096522911e-05, + "loss": 3.4392, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508726954204212e-05, + "loss": 3.4534, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1500341006693692e-05, + "loss": 3.4347, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1491955059183168e-05, + "loss": 3.4504, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483569111672648e-05, + "loss": 3.4386, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475199542965864e-05, + "loss": 3.4482, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466813595455344e-05, + "loss": 3.4444, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145842764794482e-05, + "loss": 3.4432, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.14500417004343e-05, + "loss": 3.4357, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441672131727513e-05, + "loss": 3.4389, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143328618421699e-05, + "loss": 3.4416, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424900236706473e-05, + "loss": 3.4509, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416514289195953e-05, + "loss": 3.4429, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408144720489165e-05, + "loss": 3.4544, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399758772978642e-05, + "loss": 3.4345, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391372825468122e-05, + "loss": 3.4469, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1382986877957602e-05, + "loss": 3.4497, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374617309250818e-05, + "loss": 3.4532, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366231361740294e-05, + "loss": 3.447, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357845414229774e-05, + "loss": 3.4474, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349459466719254e-05, + "loss": 3.4379, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341089898012463e-05, + "loss": 3.4597, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332703950501943e-05, + "loss": 3.4346, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324318002991427e-05, + "loss": 3.4483, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1315932055480907e-05, + "loss": 3.4405, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307562486774116e-05, + "loss": 3.4484, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299176539263596e-05, + "loss": 3.4444, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290790591753076e-05, + "loss": 3.4455, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282404644242556e-05, + "loss": 3.4452, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274035075535768e-05, + "loss": 3.4305, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265649128025248e-05, + "loss": 3.4453, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.854451894760132, + "eval_runtime": 303.8587, + "eval_samples_per_second": 1255.817, + "eval_steps_per_second": 39.245, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257263180514728e-05, + "loss": 3.4363, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248877233004208e-05, + "loss": 3.4352, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240507664297417e-05, + "loss": 3.4451, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232121716786897e-05, + "loss": 3.4505, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.122373576927638e-05, + "loss": 3.4557, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121534982176586e-05, + "loss": 3.4443, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120698025305907e-05, + "loss": 3.4401, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119859430554855e-05, + "loss": 3.4404, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.119020835803803e-05, + "loss": 3.4381, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.118182241052751e-05, + "loss": 3.4498, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173452841820722e-05, + "loss": 3.4399, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.11650668943102e-05, + "loss": 3.4453, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115669732560341e-05, + "loss": 3.4443, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114831137809289e-05, + "loss": 3.434, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113992543058237e-05, + "loss": 3.4327, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113153948307185e-05, + "loss": 3.4313, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1123153535561334e-05, + "loss": 3.4468, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1114767588050814e-05, + "loss": 3.4425, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1106381640540294e-05, + "loss": 3.4364, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109799569302977e-05, + "loss": 3.4577, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1089626124322983e-05, + "loss": 3.4527, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1081240176812463e-05, + "loss": 3.4399, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1072854229301943e-05, + "loss": 3.4408, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1064468281791423e-05, + "loss": 3.4363, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056098713084635e-05, + "loss": 3.4394, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047712765574115e-05, + "loss": 3.4447, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039326818063592e-05, + "loss": 3.4434, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1030940870553072e-05, + "loss": 3.443, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022571301846288e-05, + "loss": 3.4328, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014185354335768e-05, + "loss": 3.4335, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005799406825244e-05, + "loss": 3.4283, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997413459314724e-05, + "loss": 3.4455, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989043890607937e-05, + "loss": 3.4488, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980657943097417e-05, + "loss": 3.445, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972271995586897e-05, + "loss": 3.4354, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963886048076376e-05, + "loss": 3.4338, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.095551647936959e-05, + "loss": 3.4446, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947130531859066e-05, + "loss": 3.434, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938744584348545e-05, + "loss": 3.4311, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930358636838025e-05, + "loss": 3.437, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.092198906813124e-05, + "loss": 3.4332, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913603120620718e-05, + "loss": 3.4418, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905217173110198e-05, + "loss": 3.4402, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0896831225599678e-05, + "loss": 3.4401, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888461656892887e-05, + "loss": 3.4381, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0880075709382367e-05, + "loss": 3.4422, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.087168976187185e-05, + "loss": 3.4403, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863320193165063e-05, + "loss": 3.4294, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085493424565454e-05, + "loss": 3.4079, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084654829814402e-05, + "loss": 3.4521, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.08381623506335e-05, + "loss": 3.4365, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.082979278192671e-05, + "loss": 3.4442, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.082140683441619e-05, + "loss": 3.4316, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081302088690567e-05, + "loss": 3.4317, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080463493939515e-05, + "loss": 3.4184, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079626537068836e-05, + "loss": 3.434, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078787942317784e-05, + "loss": 3.4463, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.077949347566732e-05, + "loss": 3.4271, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0771107528156804e-05, + "loss": 3.4518, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762737959450013e-05, + "loss": 3.4343, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754352011939493e-05, + "loss": 3.4207, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0745966064428973e-05, + "loss": 3.4374, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0737580116918453e-05, + "loss": 3.426, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729210548211665e-05, + "loss": 3.4201, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0720824600701145e-05, + "loss": 3.4411, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0712438653190625e-05, + "loss": 3.4415, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704052705680105e-05, + "loss": 3.4294, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695683136973314e-05, + "loss": 3.436, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687297189462794e-05, + "loss": 3.4183, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0678911241952274e-05, + "loss": 3.4391, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670525294441758e-05, + "loss": 3.4306, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662155725734967e-05, + "loss": 3.4357, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653769778224447e-05, + "loss": 3.4405, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645383830713927e-05, + "loss": 3.4362, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0636997883203406e-05, + "loss": 3.4525, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.062862831449662e-05, + "loss": 3.4297, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.06202423669861e-05, + "loss": 3.4419, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.061185641947558e-05, + "loss": 3.4347, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.060347047196506e-05, + "loss": 3.4252, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0595100903258268e-05, + "loss": 3.4431, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586714955747748e-05, + "loss": 3.4491, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578329008237228e-05, + "loss": 3.4405, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.056994306072671e-05, + "loss": 3.453, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056157349201992e-05, + "loss": 3.4284, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.05531875445094e-05, + "loss": 3.4248, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.054480159699888e-05, + "loss": 3.4383, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.053641564948836e-05, + "loss": 3.4468, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528046080781573e-05, + "loss": 3.434, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519660133271053e-05, + "loss": 3.4404, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511274185760533e-05, + "loss": 3.4328, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0502888238250013e-05, + "loss": 3.4393, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049451866954322e-05, + "loss": 3.4314, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.04861327220327e-05, + "loss": 3.428, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.047774677452218e-05, + "loss": 3.4362, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469360827011665e-05, + "loss": 3.4478, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460991258304874e-05, + "loss": 3.4388, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452605310794354e-05, + "loss": 3.4186, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444219363283834e-05, + "loss": 3.4364, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0435833415773314e-05, + "loss": 3.4363, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0427463847066526e-05, + "loss": 3.445, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0419077899556006e-05, + "loss": 3.4354, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410691952045486e-05, + "loss": 3.4317, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402306004534963e-05, + "loss": 3.4252, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393936435828175e-05, + "loss": 3.4232, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385550488317655e-05, + "loss": 3.4351, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0377164540807135e-05, + "loss": 3.4321, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0368778593296615e-05, + "loss": 3.4197, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360409024589828e-05, + "loss": 3.4461, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0352023077079308e-05, + "loss": 3.4323, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343637129568788e-05, + "loss": 3.4292, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335251182058264e-05, + "loss": 3.429, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032688161335148e-05, + "loss": 3.43, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031849566584096e-05, + "loss": 3.435, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0310109718330436e-05, + "loss": 3.4294, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301723770819916e-05, + "loss": 3.4394, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.029335420211313e-05, + "loss": 3.4416, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.028496825460261e-05, + "loss": 3.4297, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.027658230709209e-05, + "loss": 3.4393, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026819635958157e-05, + "loss": 3.4282, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025982679087478e-05, + "loss": 3.443, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251440843364258e-05, + "loss": 3.4276, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0243054895853738e-05, + "loss": 3.4339, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234668948343218e-05, + "loss": 3.4295, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226299379636434e-05, + "loss": 3.4391, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021791343212591e-05, + "loss": 3.4371, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020952748461539e-05, + "loss": 3.4297, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020114153710487e-05, + "loss": 3.419, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192771968398083e-05, + "loss": 3.4324, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.018438602088756e-05, + "loss": 3.4303, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0176000073377043e-05, + "loss": 3.4368, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167614125866522e-05, + "loss": 3.435, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.015924455715973e-05, + "loss": 3.4424, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.015085860964921e-05, + "loss": 3.4216, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014247266213869e-05, + "loss": 3.4431, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013408671462817e-05, + "loss": 3.4358, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125717145921384e-05, + "loss": 3.4441, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117331198410864e-05, + "loss": 3.4349, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0108945250900344e-05, + "loss": 3.4329, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100559303389824e-05, + "loss": 3.4286, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092189734683033e-05, + "loss": 3.4468, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0083803787172513e-05, + "loss": 3.4234, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0075417839661996e-05, + "loss": 3.437, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0067031892151476e-05, + "loss": 3.4333, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0058662323444685e-05, + "loss": 3.4328, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050276375934165e-05, + "loss": 3.4335, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041890428423645e-05, + "loss": 3.4359, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033504480913125e-05, + "loss": 3.433, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025134912206338e-05, + "loss": 3.4221, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0016748964695818e-05, + "loss": 3.433, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8568224906921387, + "eval_runtime": 304.7123, + "eval_samples_per_second": 1252.299, + "eval_steps_per_second": 39.135, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008363017185297e-05, + "loss": 3.421, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999977069674777e-05, + "loss": 3.4255, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991591122164257e-05, + "loss": 3.4364, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983205174653737e-05, + "loss": 3.4371, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997483560594695e-05, + "loss": 3.4495, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996644965843643e-05, + "loss": 3.429, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995806371092591e-05, + "loss": 3.4338, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949677763415386e-05, + "loss": 3.4309, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.99413081947086e-05, + "loss": 3.4265, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.993292224719808e-05, + "loss": 3.4423, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.992453629968756e-05, + "loss": 3.4288, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991615035217704e-05, + "loss": 3.4336, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.990779716227398e-05, + "loss": 3.4416, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.989941121476346e-05, + "loss": 3.4185, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.989102526725294e-05, + "loss": 3.4219, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.988263931974242e-05, + "loss": 3.4198, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874253372231904e-05, + "loss": 3.4379, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865867424721383e-05, + "loss": 3.4288, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985748147721086e-05, + "loss": 3.4267, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984909552970034e-05, + "loss": 3.445, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840725960993552e-05, + "loss": 3.4454, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832340013483032e-05, + "loss": 3.428, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823954065972512e-05, + "loss": 3.43, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815568118461992e-05, + "loss": 3.4272, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807198549755205e-05, + "loss": 3.4324, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798812602244685e-05, + "loss": 3.4291, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.979042665473416e-05, + "loss": 3.4301, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.978204070722364e-05, + "loss": 3.4382, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773671138516857e-05, + "loss": 3.4206, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765285191006334e-05, + "loss": 3.4225, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756899243495814e-05, + "loss": 3.4238, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748513295985294e-05, + "loss": 3.4298, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9740143727278506e-05, + "loss": 3.4335, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9731757779767983e-05, + "loss": 3.4396, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9723371832257466e-05, + "loss": 3.4249, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9714985884746946e-05, + "loss": 3.4272, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.970661631604016e-05, + "loss": 3.4364, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698230368529635e-05, + "loss": 3.4209, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689844421019115e-05, + "loss": 3.4216, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681458473508595e-05, + "loss": 3.4298, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673088904801807e-05, + "loss": 3.4183, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9664702957291287e-05, + "loss": 3.4294, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9656317009780767e-05, + "loss": 3.4314, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9647931062270247e-05, + "loss": 3.4317, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639561493563456e-05, + "loss": 3.4248, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631175546052936e-05, + "loss": 3.4335, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.962278959854242e-05, + "loss": 3.4287, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961442002983563e-05, + "loss": 3.4215, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960603408232511e-05, + "loss": 3.3998, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959764813481459e-05, + "loss": 3.4379, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958926218730407e-05, + "loss": 3.4253, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.958089261859728e-05, + "loss": 3.4307, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.957250667108676e-05, + "loss": 3.4236, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.956412072357624e-05, + "loss": 3.4183, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955573477606572e-05, + "loss": 3.4141, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954736520735893e-05, + "loss": 3.4203, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953897925984841e-05, + "loss": 3.4383, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.953059331233789e-05, + "loss": 3.411, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522207364827373e-05, + "loss": 3.4442, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513837796120582e-05, + "loss": 3.4258, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505451848610062e-05, + "loss": 3.4101, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9497065901099542e-05, + "loss": 3.4277, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488679953589022e-05, + "loss": 3.4174, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480310384882235e-05, + "loss": 3.4128, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471924437371715e-05, + "loss": 3.4281, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463538489861195e-05, + "loss": 3.4324, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455152542350675e-05, + "loss": 3.4149, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446782973643884e-05, + "loss": 3.4294, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438397026133364e-05, + "loss": 3.4076, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9430011078622844e-05, + "loss": 3.4257, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421625131112327e-05, + "loss": 3.4238, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413255562405536e-05, + "loss": 3.4244, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404869614895016e-05, + "loss": 3.4297, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396483667384496e-05, + "loss": 3.4252, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9388097719873976e-05, + "loss": 3.442, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.937972815116719e-05, + "loss": 3.4184, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.937134220365667e-05, + "loss": 3.4311, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.936295625614615e-05, + "loss": 3.4224, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.935457030863563e-05, + "loss": 3.4164, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346200739928837e-05, + "loss": 3.4333, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337814792418317e-05, + "loss": 3.4336, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9329428844907797e-05, + "loss": 3.4322, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9321042897397277e-05, + "loss": 3.4414, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931267332869049e-05, + "loss": 3.4194, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930428738117997e-05, + "loss": 3.4134, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929590143366945e-05, + "loss": 3.4247, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.928751548615893e-05, + "loss": 3.436, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279145917452142e-05, + "loss": 3.4224, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270759969941622e-05, + "loss": 3.4276, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262374022431102e-05, + "loss": 3.4278, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9253988074920582e-05, + "loss": 3.4244, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924561850621379e-05, + "loss": 3.424, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.923723255870327e-05, + "loss": 3.4177, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.922884661119275e-05, + "loss": 3.427, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.922046066368223e-05, + "loss": 3.4371, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9212091094975443e-05, + "loss": 3.4286, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9203705147464923e-05, + "loss": 3.4116, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9195319199954403e-05, + "loss": 3.4232, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.918693325244388e-05, + "loss": 3.4244, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178563683737092e-05, + "loss": 3.43, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9170177736226576e-05, + "loss": 3.4277, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161791788716056e-05, + "loss": 3.42, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153405841205532e-05, + "loss": 3.4186, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9145036272498745e-05, + "loss": 3.4108, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136650324988225e-05, + "loss": 3.425, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9128264377477705e-05, + "loss": 3.4211, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119878429967185e-05, + "loss": 3.4137, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111508861260397e-05, + "loss": 3.4305, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9103122913749877e-05, + "loss": 3.4191, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094736966239354e-05, + "loss": 3.4175, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086351018728834e-05, + "loss": 3.4123, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077981450022046e-05, + "loss": 3.4185, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.906959550251153e-05, + "loss": 3.4279, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061209555001006e-05, + "loss": 3.4168, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052823607490486e-05, + "loss": 3.4276, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.90444540387837e-05, + "loss": 3.4308, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036068091273175e-05, + "loss": 3.419, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902768214376266e-05, + "loss": 3.4284, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.901929619625214e-05, + "loss": 3.4193, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.901092662754535e-05, + "loss": 3.4326, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002540680034827e-05, + "loss": 3.4214, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994154732524307e-05, + "loss": 3.422, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985768785013787e-05, + "loss": 3.4202, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977399216307e-05, + "loss": 3.4278, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896901326879648e-05, + "loss": 3.4309, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896062732128596e-05, + "loss": 3.4172, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.895224137377544e-05, + "loss": 3.4134, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.894387180506865e-05, + "loss": 3.4191, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.893548585755813e-05, + "loss": 3.4243, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8927099910047612e-05, + "loss": 3.4265, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918713962537092e-05, + "loss": 3.424, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.89103443938303e-05, + "loss": 3.4309, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890195844631978e-05, + "loss": 3.4114, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889357249880926e-05, + "loss": 3.4358, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888518655129874e-05, + "loss": 3.4223, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876816982591953e-05, + "loss": 3.4313, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868431035081433e-05, + "loss": 3.4237, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8860045087570913e-05, + "loss": 3.4213, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851659140060393e-05, + "loss": 3.419, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8843289571353602e-05, + "loss": 3.4399, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8834903623843082e-05, + "loss": 3.4143, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826517676332566e-05, + "loss": 3.4272, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818131728822046e-05, + "loss": 3.4226, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809762160115255e-05, + "loss": 3.4236, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801376212604735e-05, + "loss": 3.4227, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8792990265094215e-05, + "loss": 3.4256, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784604317583695e-05, + "loss": 3.4191, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776234748876907e-05, + "loss": 3.4195, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767848801366387e-05, + "loss": 3.4173, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.857161521911621, + "eval_runtime": 304.7431, + "eval_samples_per_second": 1252.173, + "eval_steps_per_second": 39.131, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759462853855867e-05, + "loss": 3.4118, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751076906345347e-05, + "loss": 3.4149, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742690958834827e-05, + "loss": 3.424, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734305011324304e-05, + "loss": 3.4291, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8725935442617516e-05, + "loss": 3.4389, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717549495107e-05, + "loss": 3.4169, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.870916354759648e-05, + "loss": 3.424, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700777600085956e-05, + "loss": 3.4229, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.869240803137917e-05, + "loss": 3.4129, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684022083868648e-05, + "loss": 3.4324, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675636136358128e-05, + "loss": 3.4175, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667250188847608e-05, + "loss": 3.4251, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865889699894455e-05, + "loss": 3.4331, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865051105143403e-05, + "loss": 3.4091, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.864212510392351e-05, + "loss": 3.4103, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863373915641299e-05, + "loss": 3.4103, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.862535320890247e-05, + "loss": 3.4261, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8616967261391953e-05, + "loss": 3.4256, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860858131388143e-05, + "loss": 3.4111, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860019536637091e-05, + "loss": 3.4339, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591825797664122e-05, + "loss": 3.4345, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858345622895733e-05, + "loss": 3.4179, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8575070281446814e-05, + "loss": 3.4212, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566684333936294e-05, + "loss": 3.4184, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558298386425774e-05, + "loss": 3.4235, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.854991243891525e-05, + "loss": 3.4211, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.854152649140473e-05, + "loss": 3.4174, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853314054389421e-05, + "loss": 3.4264, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852475459638369e-05, + "loss": 3.4126, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516385027676903e-05, + "loss": 3.4091, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8507999080166383e-05, + "loss": 3.4122, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8499613132655863e-05, + "loss": 3.4194, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491227185145343e-05, + "loss": 3.4208, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8482857616438552e-05, + "loss": 3.4317, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8474471668928036e-05, + "loss": 3.4168, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466085721417516e-05, + "loss": 3.414, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457699773906996e-05, + "loss": 3.4307, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449330205200205e-05, + "loss": 3.4051, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8440944257689685e-05, + "loss": 3.4135, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432558310179165e-05, + "loss": 3.4186, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424172362668644e-05, + "loss": 3.4094, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8415802793961857e-05, + "loss": 3.4152, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407416846451337e-05, + "loss": 3.4224, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399030898940817e-05, + "loss": 3.4243, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390644951430297e-05, + "loss": 3.4138, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382275382723506e-05, + "loss": 3.4239, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8373889435212986e-05, + "loss": 3.417, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.836550348770247e-05, + "loss": 3.412, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835711754019195e-05, + "loss": 3.3917, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348747971485158e-05, + "loss": 3.4255, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340362023974638e-05, + "loss": 3.4149, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8331976076464118e-05, + "loss": 3.426, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323590128953598e-05, + "loss": 3.4077, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831522056024681e-05, + "loss": 3.4091, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830683461273629e-05, + "loss": 3.4037, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829844866522577e-05, + "loss": 3.4112, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.829006271771525e-05, + "loss": 3.431, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.828169314900846e-05, + "loss": 3.4035, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827330720149794e-05, + "loss": 3.4304, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8264921253987423e-05, + "loss": 3.4156, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256535306476903e-05, + "loss": 3.3994, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8248165737770112e-05, + "loss": 3.4133, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8239779790259592e-05, + "loss": 3.4061, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231393842749072e-05, + "loss": 3.4075, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223007895238552e-05, + "loss": 3.415, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214638326531764e-05, + "loss": 3.4241, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206252379021244e-05, + "loss": 3.4043, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8197866431510724e-05, + "loss": 3.4183, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.81894804840002e-05, + "loss": 3.3973, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181110915293413e-05, + "loss": 3.4161, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8172724967782893e-05, + "loss": 3.415, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164339020272377e-05, + "loss": 3.4149, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8155953072761853e-05, + "loss": 3.4146, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147583504055066e-05, + "loss": 3.4141, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139197556544546e-05, + "loss": 3.4321, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8130811609034022e-05, + "loss": 3.409, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122425661523505e-05, + "loss": 3.4228, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114056092816718e-05, + "loss": 3.4152, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105670145306198e-05, + "loss": 3.4042, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097284197795674e-05, + "loss": 3.4183, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088898250285154e-05, + "loss": 3.4241, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080528681578367e-05, + "loss": 3.4213, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072142734067847e-05, + "loss": 3.4316, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063756786557327e-05, + "loss": 3.4106, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055370839046807e-05, + "loss": 3.4036, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.804700127034002e-05, + "loss": 3.4143, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038615322829496e-05, + "loss": 3.4231, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030229375318976e-05, + "loss": 3.4151, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.802184342780846e-05, + "loss": 3.4182, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801347385910167e-05, + "loss": 3.4149, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005087911591148e-05, + "loss": 3.4159, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996701964080628e-05, + "loss": 3.4127, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988316016570108e-05, + "loss": 3.4054, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.797994644786332e-05, + "loss": 3.4153, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.79715605003528e-05, + "loss": 3.4286, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796317455284228e-05, + "loss": 3.4211, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795478860533176e-05, + "loss": 3.3977, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.794641903662497e-05, + "loss": 3.4148, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793803308911445e-05, + "loss": 3.4144, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792964714160393e-05, + "loss": 3.4199, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921277572897145e-05, + "loss": 3.4172, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7912891625386622e-05, + "loss": 3.4087, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904505677876102e-05, + "loss": 3.4068, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896119730365582e-05, + "loss": 3.4024, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887750161658794e-05, + "loss": 3.4171, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879364214148274e-05, + "loss": 3.4104, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7870978266637754e-05, + "loss": 3.4055, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862592319127234e-05, + "loss": 3.4167, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854222750420443e-05, + "loss": 3.4148, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845836802909923e-05, + "loss": 3.4057, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837450855399403e-05, + "loss": 3.4057, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829064907888883e-05, + "loss": 3.4058, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7820695339182096e-05, + "loss": 3.4208, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812309391671576e-05, + "loss": 3.402, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7803923444161056e-05, + "loss": 3.4182, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795537496650535e-05, + "loss": 3.4225, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787167927943745e-05, + "loss": 3.4089, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7778781980433225e-05, + "loss": 3.4192, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770396032922708e-05, + "loss": 3.412, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762010085412188e-05, + "loss": 3.423, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7753640516705397e-05, + "loss": 3.4139, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745254569194877e-05, + "loss": 3.4104, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736868621684357e-05, + "loss": 3.4116, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728482674173837e-05, + "loss": 3.413, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.772011310546705e-05, + "loss": 3.4149, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.771172715795653e-05, + "loss": 3.4112, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770334121044601e-05, + "loss": 3.401, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769495526293549e-05, + "loss": 3.412, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686585694228698e-05, + "loss": 3.4076, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678199746718178e-05, + "loss": 3.4205, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.766981379920766e-05, + "loss": 3.4135, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.766142785169714e-05, + "loss": 3.4194, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.765305828299035e-05, + "loss": 3.4013, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.764467233547983e-05, + "loss": 3.425, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.763628638796931e-05, + "loss": 3.41, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762790044045879e-05, + "loss": 3.4278, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619530871752003e-05, + "loss": 3.4129, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611144924241483e-05, + "loss": 3.4129, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7602758976730963e-05, + "loss": 3.4067, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7594373029220443e-05, + "loss": 3.4309, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7586003460513652e-05, + "loss": 3.4015, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7577617513003132e-05, + "loss": 3.4187, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569231565492615e-05, + "loss": 3.4126, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7560845617982095e-05, + "loss": 3.4128, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552476049275304e-05, + "loss": 3.4149, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544090101764784e-05, + "loss": 3.4103, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7535704154254264e-05, + "loss": 3.4119, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527318206743744e-05, + "loss": 3.4092, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7518948638036957e-05, + "loss": 3.4063, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8581855297088623, + "eval_runtime": 304.4065, + "eval_samples_per_second": 1253.557, + "eval_steps_per_second": 39.175, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510562690526437e-05, + "loss": 3.4009, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502176743015917e-05, + "loss": 3.4029, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493790795505393e-05, + "loss": 3.4154, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485421226798606e-05, + "loss": 3.4208, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477035279288086e-05, + "loss": 3.4282, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.746864933177757e-05, + "loss": 3.4073, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460263384267045e-05, + "loss": 3.4123, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451893815560258e-05, + "loss": 3.4168, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443507868049738e-05, + "loss": 3.4035, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435121920539218e-05, + "loss": 3.4142, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426735973028694e-05, + "loss": 3.4139, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741836640432191e-05, + "loss": 3.4131, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.740999683561512e-05, + "loss": 3.4203, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.74016108881046e-05, + "loss": 3.3991, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.739322494059408e-05, + "loss": 3.3978, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.738483899308356e-05, + "loss": 3.3969, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.737645304557304e-05, + "loss": 3.4195, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.736806709806252e-05, + "loss": 3.4118, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7359681150552e-05, + "loss": 3.4014, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735129520304148e-05, + "loss": 3.4222, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734292563433469e-05, + "loss": 3.4242, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.73345560656279e-05, + "loss": 3.4118, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326170118117384e-05, + "loss": 3.4096, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317784170606864e-05, + "loss": 3.4072, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.730939822309634e-05, + "loss": 3.4171, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.730101227558582e-05, + "loss": 3.41, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.72926263280753e-05, + "loss": 3.4043, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728424038056478e-05, + "loss": 3.4178, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727585443305426e-05, + "loss": 3.4006, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267484864347473e-05, + "loss": 3.3971, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259098916836953e-05, + "loss": 3.4076, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250712969326433e-05, + "loss": 3.4059, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242327021815913e-05, + "loss": 3.4141, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7233957453109122e-05, + "loss": 3.4245, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7225571505598602e-05, + "loss": 3.4027, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217185558088085e-05, + "loss": 3.407, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7208799610577565e-05, + "loss": 3.4185, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200430041870774e-05, + "loss": 3.3939, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192044094360254e-05, + "loss": 3.4055, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7183658146849734e-05, + "loss": 3.4074, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7175272199339214e-05, + "loss": 3.3987, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7166902630632426e-05, + "loss": 3.4073, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158516683121906e-05, + "loss": 3.4129, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150130735611386e-05, + "loss": 3.4148, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141744788100866e-05, + "loss": 3.4046, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133375219394075e-05, + "loss": 3.409, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7124989271883555e-05, + "loss": 3.4071, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.711660332437304e-05, + "loss": 3.4018, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.710821737686252e-05, + "loss": 3.3822, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099847808155728e-05, + "loss": 3.4125, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091461860645208e-05, + "loss": 3.4085, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7083075913134688e-05, + "loss": 3.4114, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7074689965624168e-05, + "loss": 3.4024, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.706632039691738e-05, + "loss": 3.3948, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705793444940686e-05, + "loss": 3.3967, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.704954850189634e-05, + "loss": 3.4006, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.704116255438582e-05, + "loss": 3.4173, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703279298567903e-05, + "loss": 3.3961, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702440703816851e-05, + "loss": 3.4173, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016021090657992e-05, + "loss": 3.4073, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.700763514314747e-05, + "loss": 3.3904, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.699926557444068e-05, + "loss": 3.4053, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.699087962693016e-05, + "loss": 3.3937, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.698249367941964e-05, + "loss": 3.395, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974107731909118e-05, + "loss": 3.4001, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965738163202334e-05, + "loss": 3.4176, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957352215691814e-05, + "loss": 3.395, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694896626818129e-05, + "loss": 3.4046, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.694058032067077e-05, + "loss": 3.389, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932210751963983e-05, + "loss": 3.4041, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6923824804453463e-05, + "loss": 3.4061, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915438856942943e-05, + "loss": 3.4067, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907052909432423e-05, + "loss": 3.4039, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898683340725635e-05, + "loss": 3.4049, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890297393215115e-05, + "loss": 3.4194, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.688191144570459e-05, + "loss": 3.4023, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687352549819407e-05, + "loss": 3.4086, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865155929487287e-05, + "loss": 3.4021, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6856769981976764e-05, + "loss": 3.4017, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848384034466244e-05, + "loss": 3.4123, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6839998086955724e-05, + "loss": 3.4076, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831628518248936e-05, + "loss": 3.4138, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823242570738416e-05, + "loss": 3.4209, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6814856623227896e-05, + "loss": 3.4091, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806470675717376e-05, + "loss": 3.3896, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.679810110701059e-05, + "loss": 3.4004, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789715159500065e-05, + "loss": 3.4117, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781329211989545e-05, + "loss": 3.4069, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6772943264479025e-05, + "loss": 3.4077, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764573695772238e-05, + "loss": 3.4051, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756187748261718e-05, + "loss": 3.4072, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6747801800751198e-05, + "loss": 3.4016, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739415853240678e-05, + "loss": 3.3985, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6731046284533887e-05, + "loss": 3.4089, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.672266033702337e-05, + "loss": 3.4171, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.671427438951285e-05, + "loss": 3.4098, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.670588844200233e-05, + "loss": 3.3872, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669751887329554e-05, + "loss": 3.405, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.668913292578502e-05, + "loss": 3.4073, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.66807469782745e-05, + "loss": 3.4105, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.667236103076398e-05, + "loss": 3.4074, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.666399146205719e-05, + "loss": 3.3976, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.665560551454667e-05, + "loss": 3.3973, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.664721956703615e-05, + "loss": 3.395, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.663883361952563e-05, + "loss": 3.4046, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.663046405081884e-05, + "loss": 3.4005, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6622078103308324e-05, + "loss": 3.3978, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613692155797804e-05, + "loss": 3.4075, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605306208287284e-05, + "loss": 3.4028, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6596936639580493e-05, + "loss": 3.3962, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6588550692069973e-05, + "loss": 3.3967, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580164744559453e-05, + "loss": 3.3922, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6571778797048933e-05, + "loss": 3.4091, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563409228342145e-05, + "loss": 3.3949, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6555023280831625e-05, + "loss": 3.4031, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6546637333321105e-05, + "loss": 3.4112, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538251385810585e-05, + "loss": 3.3998, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6529881817103794e-05, + "loss": 3.4067, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521495869593277e-05, + "loss": 3.4046, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6513109922082757e-05, + "loss": 3.4091, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6504723974572237e-05, + "loss": 3.4081, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496354405865446e-05, + "loss": 3.4016, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6487968458354926e-05, + "loss": 3.401, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479582510844406e-05, + "loss": 3.4034, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.647121294213762e-05, + "loss": 3.4091, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.64628269946271e-05, + "loss": 3.3996, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.645444104711658e-05, + "loss": 3.3924, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.644605509960606e-05, + "loss": 3.3989, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437685530899268e-05, + "loss": 3.3977, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429299583388748e-05, + "loss": 3.41, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.642091363587823e-05, + "loss": 3.4017, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641252768836771e-05, + "loss": 3.4113, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640415811966092e-05, + "loss": 3.3961, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.63957721721504e-05, + "loss": 3.41, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638738622463988e-05, + "loss": 3.4013, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.637900027712936e-05, + "loss": 3.4166, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370630708422572e-05, + "loss": 3.4041, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362244760912052e-05, + "loss": 3.4029, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6353858813401532e-05, + "loss": 3.3987, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6345472865891012e-05, + "loss": 3.4157, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.633710329718422e-05, + "loss": 3.3959, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.63287173496737e-05, + "loss": 3.4047, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320331402163185e-05, + "loss": 3.4039, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.631194545465266e-05, + "loss": 3.4018, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6303575885945874e-05, + "loss": 3.4038, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295189938435354e-05, + "loss": 3.4035, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6286803990924834e-05, + "loss": 3.4013, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627841804341431e-05, + "loss": 3.4015, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6270048474707526e-05, + "loss": 3.3948, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.8601090908050537, + "eval_runtime": 304.0859, + "eval_samples_per_second": 1254.879, + "eval_steps_per_second": 39.216, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261662527197006e-05, + "loss": 3.3867, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253276579686486e-05, + "loss": 3.3914, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244890632175963e-05, + "loss": 3.4038, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236504684665443e-05, + "loss": 3.411, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228135115958655e-05, + "loss": 3.4178, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219749168448135e-05, + "loss": 3.3957, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211363220937615e-05, + "loss": 3.4045, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6202977273427095e-05, + "loss": 3.4062, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194607704720307e-05, + "loss": 3.3948, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186221757209784e-05, + "loss": 3.4012, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6177835809699264e-05, + "loss": 3.4066, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6169449862188747e-05, + "loss": 3.4032, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.616109667228569e-05, + "loss": 3.4113, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615271072477517e-05, + "loss": 3.3904, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614432477726465e-05, + "loss": 3.3873, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613593882975413e-05, + "loss": 3.3882, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612755288224361e-05, + "loss": 3.4083, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.611916693473309e-05, + "loss": 3.4063, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.611078098722257e-05, + "loss": 3.391, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.610239503971205e-05, + "loss": 3.4097, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6094025471005258e-05, + "loss": 3.4178, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608565590229847e-05, + "loss": 3.3984, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077269954787954e-05, + "loss": 3.4018, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068884007277433e-05, + "loss": 3.3964, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.606049805976691e-05, + "loss": 3.4082, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.605211211225639e-05, + "loss": 3.3951, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604372616474587e-05, + "loss": 3.3957, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603534021723535e-05, + "loss": 3.4125, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602695426972483e-05, + "loss": 3.3894, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018584701018042e-05, + "loss": 3.3898, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010198753507522e-05, + "loss": 3.3947, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001812805997002e-05, + "loss": 3.3951, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993426858486482e-05, + "loss": 3.4056, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598505728977969e-05, + "loss": 3.4142, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597667134226917e-05, + "loss": 3.3893, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968285394758655e-05, + "loss": 3.4012, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959899447248135e-05, + "loss": 3.4071, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951529878541344e-05, + "loss": 3.3842, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5943143931030824e-05, + "loss": 3.3937, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5934757983520304e-05, + "loss": 3.4015, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5926372036009784e-05, + "loss": 3.3862, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5918002467302996e-05, + "loss": 3.3969, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909616519792476e-05, + "loss": 3.4059, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901230572281956e-05, + "loss": 3.4005, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892844624771436e-05, + "loss": 3.3925, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884475056064645e-05, + "loss": 3.4028, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876089108554125e-05, + "loss": 3.395, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5867703161043608e-05, + "loss": 3.3952, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859317213533088e-05, + "loss": 3.3726, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850947644826297e-05, + "loss": 3.4013, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842561697315777e-05, + "loss": 3.399, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834175749805257e-05, + "loss": 3.3999, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825789802294734e-05, + "loss": 3.3914, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581742023358795e-05, + "loss": 3.3863, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580903428607743e-05, + "loss": 3.3862, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.580064833856691e-05, + "loss": 3.3876, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792262391056386e-05, + "loss": 3.409, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.57838928223496e-05, + "loss": 3.3854, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577550687483908e-05, + "loss": 3.4009, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767120927328562e-05, + "loss": 3.3979, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.575873497981804e-05, + "loss": 3.3841, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575036541111125e-05, + "loss": 3.3904, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.574197946360073e-05, + "loss": 3.3866, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733593516090208e-05, + "loss": 3.3892, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725207568579687e-05, + "loss": 3.3863, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716837999872903e-05, + "loss": 3.4098, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708452052362383e-05, + "loss": 3.3905, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.570006610485186e-05, + "loss": 3.3884, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.569168015734134e-05, + "loss": 3.3838, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5683310588634552e-05, + "loss": 3.3932, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5674924641124032e-05, + "loss": 3.3954, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666538693613512e-05, + "loss": 3.3949, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5658152746102992e-05, + "loss": 3.3971, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5649783177396205e-05, + "loss": 3.3954, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.564139722988568e-05, + "loss": 3.4064, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.563301128237516e-05, + "loss": 3.3924, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562462533486464e-05, + "loss": 3.3998, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616255766157857e-05, + "loss": 3.3952, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5607869818647334e-05, + "loss": 3.3924, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599483871136814e-05, + "loss": 3.401, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591097923626293e-05, + "loss": 3.395, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5582728354919503e-05, + "loss": 3.4052, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574342407408986e-05, + "loss": 3.4088, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5565956459898466e-05, + "loss": 3.4027, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557570512387946e-05, + "loss": 3.38, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549200943681155e-05, + "loss": 3.3942, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5540814996170635e-05, + "loss": 3.4019, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532429048660115e-05, + "loss": 3.3996, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524043101149595e-05, + "loss": 3.393, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5515673532442807e-05, + "loss": 3.3967, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507287584932287e-05, + "loss": 3.3973, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498901637421767e-05, + "loss": 3.3901, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490515689911247e-05, + "loss": 3.3891, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5482146121204456e-05, + "loss": 3.3991, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547376017369394e-05, + "loss": 3.4035, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.546537422618342e-05, + "loss": 3.4035, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.54569882786729e-05, + "loss": 3.3767, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544861870996611e-05, + "loss": 3.3944, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.544023276245559e-05, + "loss": 3.397, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.543184681494507e-05, + "loss": 3.4018, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.542346086743455e-05, + "loss": 3.3961, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541509129872776e-05, + "loss": 3.3866, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.540670535121724e-05, + "loss": 3.3907, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539831940370672e-05, + "loss": 3.3797, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.53899334561962e-05, + "loss": 3.3971, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.538156388748941e-05, + "loss": 3.3873, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373177939978893e-05, + "loss": 3.3853, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364791992468373e-05, + "loss": 3.3988, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356406044957853e-05, + "loss": 3.3932, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5348036476251062e-05, + "loss": 3.3848, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5339650528740542e-05, + "loss": 3.3889, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5331264581230022e-05, + "loss": 3.3819, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322878633719502e-05, + "loss": 3.4013, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314509065012715e-05, + "loss": 3.3835, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306123117502195e-05, + "loss": 3.3996, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297737169991675e-05, + "loss": 3.3927, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289351222481155e-05, + "loss": 3.3948, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5280981653774364e-05, + "loss": 3.3948, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5272595706263847e-05, + "loss": 3.3927, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5264209758753327e-05, + "loss": 3.4027, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255823811242805e-05, + "loss": 3.3983, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247454242536016e-05, + "loss": 3.3895, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239068295025496e-05, + "loss": 3.3904, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5230682347514978e-05, + "loss": 3.3922, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222296400004458e-05, + "loss": 3.3972, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213926831297667e-05, + "loss": 3.389, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205540883787148e-05, + "loss": 3.3855, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197154936276628e-05, + "loss": 3.3852, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188785367569839e-05, + "loss": 3.3912, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180399420059319e-05, + "loss": 3.3967, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172013472548799e-05, + "loss": 3.3928, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163627525038279e-05, + "loss": 3.4052, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.515525795633149e-05, + "loss": 3.3819, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.514687200882097e-05, + "loss": 3.4004, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.513848606131045e-05, + "loss": 3.3949, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130100113799931e-05, + "loss": 3.4019, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.512173054509314e-05, + "loss": 3.3951, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.511334459758262e-05, + "loss": 3.3925, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104958650072102e-05, + "loss": 3.3926, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096572702561578e-05, + "loss": 3.407, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088203133854793e-05, + "loss": 3.3908, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079817186344273e-05, + "loss": 3.3904, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071431238833753e-05, + "loss": 3.3982, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.506304529132323e-05, + "loss": 3.3924, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054675722616443e-05, + "loss": 3.3902, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046289775105923e-05, + "loss": 3.4006, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037903827595403e-05, + "loss": 3.3866, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029517880084882e-05, + "loss": 3.3902, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021148311378094e-05, + "loss": 3.3869, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8600339889526367, + "eval_runtime": 308.1451, + "eval_samples_per_second": 1238.348, + "eval_steps_per_second": 38.699, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012762363867574e-05, + "loss": 3.3866, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004376416357052e-05, + "loss": 3.3783, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995990468846532e-05, + "loss": 3.3957, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987620900139746e-05, + "loss": 3.401, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979234952629226e-05, + "loss": 3.4037, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970849005118703e-05, + "loss": 3.3913, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962463057608185e-05, + "loss": 3.3919, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954093488901397e-05, + "loss": 3.3955, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4945707541390874e-05, + "loss": 3.3855, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937321593880355e-05, + "loss": 3.3916, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4928935646369835e-05, + "loss": 3.3965, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920566077663048e-05, + "loss": 3.3928, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912196508956258e-05, + "loss": 3.4065, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903810561445738e-05, + "loss": 3.3796, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895424613935218e-05, + "loss": 3.377, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887038666424698e-05, + "loss": 3.3767, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4878652718914177e-05, + "loss": 3.4019, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870266771403657e-05, + "loss": 3.3891, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861880823893136e-05, + "loss": 3.3839, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853494876382618e-05, + "loss": 3.4, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845125307675827e-05, + "loss": 3.4051, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836739360165309e-05, + "loss": 3.3899, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828369791458521e-05, + "loss": 3.392, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4819983843947998e-05, + "loss": 3.3879, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.481159789643748e-05, + "loss": 3.4013, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.480321194892696e-05, + "loss": 3.3868, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.479482600141644e-05, + "loss": 3.3822, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.478644005390592e-05, + "loss": 3.4039, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778054106395401e-05, + "loss": 3.3742, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.476968453768861e-05, + "loss": 3.3803, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.476129859017809e-05, + "loss": 3.3843, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752912642667572e-05, + "loss": 3.3862, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744526695157052e-05, + "loss": 3.3953, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736157126450263e-05, + "loss": 3.4001, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727771178939743e-05, + "loss": 3.3843, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719385231429222e-05, + "loss": 3.388, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4710999283918702e-05, + "loss": 3.397, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702629715211913e-05, + "loss": 3.3769, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694243767701393e-05, + "loss": 3.3878, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685857820190873e-05, + "loss": 3.3892, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677471872680355e-05, + "loss": 3.3765, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669102303973564e-05, + "loss": 3.3852, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660716356463044e-05, + "loss": 3.398, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652330408952525e-05, + "loss": 3.3882, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643944461442002e-05, + "loss": 3.3843, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635574892735216e-05, + "loss": 3.3982, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627188945224696e-05, + "loss": 3.3831, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618802997714176e-05, + "loss": 3.3851, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610417050203654e-05, + "loss": 3.3595, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4602047481496867e-05, + "loss": 3.3879, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593661533986347e-05, + "loss": 3.3963, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585275586475827e-05, + "loss": 3.3865, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576889638965305e-05, + "loss": 3.379, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568520070258518e-05, + "loss": 3.3798, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560134122747997e-05, + "loss": 3.3761, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551748175237476e-05, + "loss": 3.3751, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543362227726956e-05, + "loss": 3.4048, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.453499265902017e-05, + "loss": 3.3764, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.452660671150965e-05, + "loss": 3.3889, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518220763999126e-05, + "loss": 3.3905, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509834816488608e-05, + "loss": 3.3759, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.450146524778182e-05, + "loss": 3.3803, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.44930793002713e-05, + "loss": 3.3782, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484693352760779e-05, + "loss": 3.3779, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476307405250259e-05, + "loss": 3.3791, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467937836543471e-05, + "loss": 3.3963, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.445955188903295e-05, + "loss": 3.3875, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.445116594152243e-05, + "loss": 3.3771, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.444277999401191e-05, + "loss": 3.371, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434410425305122e-05, + "loss": 3.3826, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.44260244777946e-05, + "loss": 3.3861, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.441763853028408e-05, + "loss": 3.3889, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.440925258277356e-05, + "loss": 3.384, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400883014066774e-05, + "loss": 3.3869, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.439249706655625e-05, + "loss": 3.3964, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384111119045732e-05, + "loss": 3.3833, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375725171535212e-05, + "loss": 3.3846, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367355602828421e-05, + "loss": 3.3912, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4358969655317903e-05, + "loss": 3.3809, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350583707807383e-05, + "loss": 3.3882, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342197760296863e-05, + "loss": 3.3878, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333828191590074e-05, + "loss": 3.3925, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325442244079554e-05, + "loss": 3.4019, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317056296569034e-05, + "loss": 3.3911, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308670349058514e-05, + "loss": 3.3696, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300300780351724e-05, + "loss": 3.3802, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291914832841204e-05, + "loss": 3.393, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283528885330686e-05, + "loss": 3.3879, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275142937820166e-05, + "loss": 3.3836, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266773369113375e-05, + "loss": 3.3899, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258387421602857e-05, + "loss": 3.3882, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250001474092337e-05, + "loss": 3.3781, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241615526581817e-05, + "loss": 3.3779, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233245957875027e-05, + "loss": 3.3892, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224860010364507e-05, + "loss": 3.3869, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216474062853987e-05, + "loss": 3.393, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208104494147198e-05, + "loss": 3.3752, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199718546636678e-05, + "loss": 3.3804, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191332599126158e-05, + "loss": 3.391, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.418294665161564e-05, + "loss": 3.39, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174577082908849e-05, + "loss": 3.3878, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166191135398329e-05, + "loss": 3.3769, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.415780518788781e-05, + "loss": 3.3781, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.414941924037729e-05, + "loss": 3.373, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141049671670501e-05, + "loss": 3.3887, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132663724159981e-05, + "loss": 3.3758, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124277776649461e-05, + "loss": 3.3783, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115891829138941e-05, + "loss": 3.3874, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107505881628421e-05, + "loss": 3.3823, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099136312921632e-05, + "loss": 3.3791, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090750365411112e-05, + "loss": 3.3815, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082364417900593e-05, + "loss": 3.3672, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4073994849193803e-05, + "loss": 3.3885, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065608901683282e-05, + "loss": 3.377, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057222954172764e-05, + "loss": 3.3833, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048837006662244e-05, + "loss": 3.3864, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040467437955455e-05, + "loss": 3.3872, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4032081490444935e-05, + "loss": 3.3834, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4023695542934415e-05, + "loss": 3.3846, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015309595423895e-05, + "loss": 3.3904, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4006940026717106e-05, + "loss": 3.3842, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3998554079206585e-05, + "loss": 3.3827, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3990168131696065e-05, + "loss": 3.3821, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981782184185545e-05, + "loss": 3.3804, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973412615478756e-05, + "loss": 3.3905, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3965026667968236e-05, + "loss": 3.3756, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956640720457718e-05, + "loss": 3.3784, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948254772947198e-05, + "loss": 3.3742, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3939885204240407e-05, + "loss": 3.383, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931499256729888e-05, + "loss": 3.3909, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923113309219368e-05, + "loss": 3.3802, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914727361708845e-05, + "loss": 3.3924, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.390635779300206e-05, + "loss": 3.3777, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897971845491539e-05, + "loss": 3.388, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889585897981019e-05, + "loss": 3.3836, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881199950470497e-05, + "loss": 3.3915, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.387283038176371e-05, + "loss": 3.382, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.386444443425319e-05, + "loss": 3.3843, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856058486742671e-05, + "loss": 3.3817, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847672539232148e-05, + "loss": 3.3954, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.383930297052536e-05, + "loss": 3.3804, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830917023014842e-05, + "loss": 3.3804, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822531075504319e-05, + "loss": 3.3872, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814145127993799e-05, + "loss": 3.3806, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805775559287013e-05, + "loss": 3.3779, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797389611776493e-05, + "loss": 3.3928, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789003664265971e-05, + "loss": 3.3775, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780617716755451e-05, + "loss": 3.3799, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772248148048664e-05, + "loss": 3.3774, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8615918159484863, + "eval_runtime": 304.0646, + "eval_samples_per_second": 1254.967, + "eval_steps_per_second": 39.219, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763862200538143e-05, + "loss": 3.3809, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755476253027622e-05, + "loss": 3.3695, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747090305517102e-05, + "loss": 3.385, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738704358006582e-05, + "loss": 3.3958, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730334789299792e-05, + "loss": 3.389, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721948841789272e-05, + "loss": 3.3863, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713562894278752e-05, + "loss": 3.376, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705176946768234e-05, + "loss": 3.387, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696807378061443e-05, + "loss": 3.3739, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688421430550925e-05, + "loss": 3.387, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3680035483040405e-05, + "loss": 3.3827, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671649535529885e-05, + "loss": 3.3819, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663296345626828e-05, + "loss": 3.3964, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654910398116308e-05, + "loss": 3.3681, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646524450605788e-05, + "loss": 3.3691, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638138503095266e-05, + "loss": 3.3717, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629752555584746e-05, + "loss": 3.3933, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621366608074226e-05, + "loss": 3.3782, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612980660563706e-05, + "loss": 3.3763, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604594713053188e-05, + "loss": 3.3878, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596225144346397e-05, + "loss": 3.3963, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587839196835878e-05, + "loss": 3.3798, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579469628129088e-05, + "loss": 3.3791, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571083680618567e-05, + "loss": 3.3797, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562697733108049e-05, + "loss": 3.3906, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554311785597529e-05, + "loss": 3.3775, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545925838087009e-05, + "loss": 3.3726, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537539890576489e-05, + "loss": 3.3952, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529153943065969e-05, + "loss": 3.3653, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.352078437435918e-05, + "loss": 3.3718, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.351239842684866e-05, + "loss": 3.3751, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3504012479338141e-05, + "loss": 3.3773, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495626531827621e-05, + "loss": 3.3846, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.348725696312083e-05, + "loss": 3.3927, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478871015610312e-05, + "loss": 3.3757, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470485068099792e-05, + "loss": 3.3779, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462099120589269e-05, + "loss": 3.3867, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453729551882483e-05, + "loss": 3.3682, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445343604371963e-05, + "loss": 3.3781, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436957656861443e-05, + "loss": 3.3775, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428571709350921e-05, + "loss": 3.3739, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420202140644133e-05, + "loss": 3.3702, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411816193133613e-05, + "loss": 3.3913, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403430245623095e-05, + "loss": 3.374, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395044298112572e-05, + "loss": 3.3787, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386674729405784e-05, + "loss": 3.385, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378288781895266e-05, + "loss": 3.3757, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3369902834384742e-05, + "loss": 3.3731, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361516886874222e-05, + "loss": 3.3546, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353147318167436e-05, + "loss": 3.3738, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344761370656916e-05, + "loss": 3.3872, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336375423146395e-05, + "loss": 3.3818, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3327989475635875e-05, + "loss": 3.3664, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319619906929087e-05, + "loss": 3.3667, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311233959418567e-05, + "loss": 3.372, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302848011908045e-05, + "loss": 3.363, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294462064397525e-05, + "loss": 3.3958, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286092495690738e-05, + "loss": 3.3654, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277706548180216e-05, + "loss": 3.3825, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269320600669696e-05, + "loss": 3.3806, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260934653159176e-05, + "loss": 3.3634, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.325256508445239e-05, + "loss": 3.3727, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244179136941867e-05, + "loss": 3.3681, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235793189431348e-05, + "loss": 3.3685, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227407241920828e-05, + "loss": 3.3681, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.321903767321404e-05, + "loss": 3.3876, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210651725703519e-05, + "loss": 3.3775, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202265778192999e-05, + "loss": 3.3707, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193879830682479e-05, + "loss": 3.362, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.318551026197569e-05, + "loss": 3.3724, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.317712431446517e-05, + "loss": 3.3786, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.316873836695465e-05, + "loss": 3.3774, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.316035241944413e-05, + "loss": 3.3712, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.315198285073734e-05, + "loss": 3.3776, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.314359690322682e-05, + "loss": 3.3879, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135210955716302e-05, + "loss": 3.3742, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126825008205782e-05, + "loss": 3.377, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118471818302725e-05, + "loss": 3.3751, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110085870792205e-05, + "loss": 3.3759, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101699923281685e-05, + "loss": 3.3806, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093313975771163e-05, + "loss": 3.3802, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084928028260643e-05, + "loss": 3.3841, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076542080750123e-05, + "loss": 3.3876, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068156133239603e-05, + "loss": 3.3813, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059770185729083e-05, + "loss": 3.3607, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051400617022294e-05, + "loss": 3.3676, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043014669511774e-05, + "loss": 3.3855, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034628722001254e-05, + "loss": 3.3814, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026242774490736e-05, + "loss": 3.3756, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017873205783945e-05, + "loss": 3.3772, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009487258273426e-05, + "loss": 3.3837, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001101310762906e-05, + "loss": 3.3686, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992715363252386e-05, + "loss": 3.3681, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984345794545597e-05, + "loss": 3.3801, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975959847035077e-05, + "loss": 3.3749, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967573899524557e-05, + "loss": 3.3875, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959187952014037e-05, + "loss": 3.3644, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950818383307248e-05, + "loss": 3.3697, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942432435796728e-05, + "loss": 3.3796, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934046488286208e-05, + "loss": 3.3796, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.292566054077569e-05, + "loss": 3.3764, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917290972068898e-05, + "loss": 3.3696, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.290890502455838e-05, + "loss": 3.3676, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.290051907704786e-05, + "loss": 3.3611, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.289213312953734e-05, + "loss": 3.379, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.288376356083055e-05, + "loss": 3.3637, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.287537761332003e-05, + "loss": 3.3679, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.286699166580951e-05, + "loss": 3.378, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.285860571829899e-05, + "loss": 3.3738, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850236149592201e-05, + "loss": 3.3631, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841850202081681e-05, + "loss": 3.3745, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833464254571161e-05, + "loss": 3.3622, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.282507830706064e-05, + "loss": 3.3774, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816708738353852e-05, + "loss": 3.3702, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808322790843334e-05, + "loss": 3.3726, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799936843332814e-05, + "loss": 3.3786, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.279155089582229e-05, + "loss": 3.3773, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783181327115504e-05, + "loss": 3.371, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774795379604984e-05, + "loss": 3.3765, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766409432094464e-05, + "loss": 3.3845, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2758023484583943e-05, + "loss": 3.3734, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749653915877155e-05, + "loss": 3.3713, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741267968366635e-05, + "loss": 3.3727, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732882020856113e-05, + "loss": 3.3731, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724496073345593e-05, + "loss": 3.3797, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716126504638806e-05, + "loss": 3.3672, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707740557128287e-05, + "loss": 3.3679, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699354609617764e-05, + "loss": 3.3688, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690968662107244e-05, + "loss": 3.3696, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682599093400458e-05, + "loss": 3.3783, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674213145889938e-05, + "loss": 3.3772, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665827198379415e-05, + "loss": 3.3811, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657441250868896e-05, + "loss": 3.3678, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649071682162109e-05, + "loss": 3.3798, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640685734651587e-05, + "loss": 3.3717, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632299787141067e-05, + "loss": 3.385, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.262393021843428e-05, + "loss": 3.3722, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.261554427092376e-05, + "loss": 3.3746, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607158323413238e-05, + "loss": 3.3746, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598772375902718e-05, + "loss": 3.3874, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.259040280719593e-05, + "loss": 3.371, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582016859685412e-05, + "loss": 3.3709, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573630912174888e-05, + "loss": 3.3785, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565244964664368e-05, + "loss": 3.3717, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556875395957582e-05, + "loss": 3.3694, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548489448447059e-05, + "loss": 3.3825, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540103500936539e-05, + "loss": 3.3617, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.253171755342602e-05, + "loss": 3.3767, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.25233316059155e-05, + "loss": 3.3635, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8609561920166016, + "eval_runtime": 303.4522, + "eval_samples_per_second": 1257.5, + "eval_steps_per_second": 39.298, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514962037208711e-05, + "loss": 3.3694, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506576089698191e-05, + "loss": 3.3621, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498190142187671e-05, + "loss": 3.3712, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489820573480884e-05, + "loss": 3.3853, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481434625970364e-05, + "loss": 3.3822, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2473048678459842e-05, + "loss": 3.3763, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464662730949322e-05, + "loss": 3.3633, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2456293162242534e-05, + "loss": 3.3774, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2447907214732014e-05, + "loss": 3.3689, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2439521267221493e-05, + "loss": 3.3745, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431135319710974e-05, + "loss": 3.3728, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422765751004185e-05, + "loss": 3.3753, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2414396182297398e-05, + "loss": 3.3862, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2406010234786876e-05, + "loss": 3.3618, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397624287276356e-05, + "loss": 3.3558, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2389238339765836e-05, + "loss": 3.3615, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2380852392255316e-05, + "loss": 3.3804, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372466444744796e-05, + "loss": 3.372, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364080497234276e-05, + "loss": 3.3682, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355694549723756e-05, + "loss": 3.3767, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347324981016966e-05, + "loss": 3.3885, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2338939033506446e-05, + "loss": 3.3698, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330569464799659e-05, + "loss": 3.37, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2322183517289137e-05, + "loss": 3.3722, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313797569778619e-05, + "loss": 3.3833, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305411622268099e-05, + "loss": 3.3627, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297025674757579e-05, + "loss": 3.3673, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288639727247057e-05, + "loss": 3.3805, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2280253779736538e-05, + "loss": 3.3584, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.227188421102975e-05, + "loss": 3.3611, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263498263519228e-05, + "loss": 3.3613, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.225511231600871e-05, + "loss": 3.3686, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2246726368498189e-05, + "loss": 3.3745, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.22383567997914e-05, + "loss": 3.3788, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.222997085228088e-05, + "loss": 3.3684, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.222158490477036e-05, + "loss": 3.3673, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.221319895725984e-05, + "loss": 3.3757, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204829388553052e-05, + "loss": 3.3575, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.219644344104253e-05, + "loss": 3.3683, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.218805749353201e-05, + "loss": 3.3684, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179671546021492e-05, + "loss": 3.3681, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171301977314701e-05, + "loss": 3.3579, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162916029804181e-05, + "loss": 3.382, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154530082293663e-05, + "loss": 3.364, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146144134783143e-05, + "loss": 3.3722, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137774566076354e-05, + "loss": 3.3754, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129388618565834e-05, + "loss": 3.3675, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121002671055314e-05, + "loss": 3.3651, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112616723544792e-05, + "loss": 3.3476, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104247154838004e-05, + "loss": 3.3655, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2095861207327484e-05, + "loss": 3.375, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2087475259816964e-05, + "loss": 3.3708, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079089312306444e-05, + "loss": 3.3595, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070719743599655e-05, + "loss": 3.3565, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062333796089135e-05, + "loss": 3.3647, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2053947848578617e-05, + "loss": 3.3524, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045561901068095e-05, + "loss": 3.3844, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037192332361307e-05, + "loss": 3.3592, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028806384850787e-05, + "loss": 3.3705, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020420437340265e-05, + "loss": 3.3718, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2012034489829745e-05, + "loss": 3.3551, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2003664921122958e-05, + "loss": 3.3631, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995278973612438e-05, + "loss": 3.3613, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986893026101916e-05, + "loss": 3.3538, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978507078591398e-05, + "loss": 3.3534, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970137509884609e-05, + "loss": 3.3798, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961751562374089e-05, + "loss": 3.3677, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953365614863568e-05, + "loss": 3.3597, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1944979667353048e-05, + "loss": 3.3526, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.193661009864626e-05, + "loss": 3.3585, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.192822415113574e-05, + "loss": 3.3701, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919838203625219e-05, + "loss": 3.3688, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911452256114699e-05, + "loss": 3.3608, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1903082687407912e-05, + "loss": 3.3689, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.189469673989739e-05, + "loss": 3.374, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.188631079238687e-05, + "loss": 3.3712, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1877924844876351e-05, + "loss": 3.3629, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869555276169562e-05, + "loss": 3.3677, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861169328659042e-05, + "loss": 3.3673, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852783381148522e-05, + "loss": 3.367, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844397433638002e-05, + "loss": 3.3712, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1836027864931213e-05, + "loss": 3.3733, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827641917420693e-05, + "loss": 3.3795, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1819255969910173e-05, + "loss": 3.3678, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810870022399653e-05, + "loss": 3.355, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802500453692864e-05, + "loss": 3.3611, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794114506182344e-05, + "loss": 3.3764, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785728558671823e-05, + "loss": 3.3712, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777342611161303e-05, + "loss": 3.3664, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768973042454514e-05, + "loss": 3.3669, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760587094943996e-05, + "loss": 3.3729, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752201147433476e-05, + "loss": 3.3584, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743815199922954e-05, + "loss": 3.3635, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1735445631216167e-05, + "loss": 3.3632, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1727059683705647e-05, + "loss": 3.3705, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718673736195125e-05, + "loss": 3.372, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710287788684605e-05, + "loss": 3.3652, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1701918219977817e-05, + "loss": 3.3526, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693532272467297e-05, + "loss": 3.3728, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1685146324956777e-05, + "loss": 3.3686, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1676760377446257e-05, + "loss": 3.3665, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668390808739468e-05, + "loss": 3.3634, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1660004861228948e-05, + "loss": 3.3559, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1651618913718428e-05, + "loss": 3.3532, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643232966207908e-05, + "loss": 3.3675, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.163486339750112e-05, + "loss": 3.3564, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626477449990598e-05, + "loss": 3.3568, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1618091502480078e-05, + "loss": 3.3706, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1609705554969558e-05, + "loss": 3.3684, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1601335986262771e-05, + "loss": 3.3547, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1592950038752249e-05, + "loss": 3.3632, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.158456409124173e-05, + "loss": 3.3528, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.157617814373121e-05, + "loss": 3.3665, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567808575024422e-05, + "loss": 3.3602, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559422627513902e-05, + "loss": 3.3639, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1551036680003381e-05, + "loss": 3.3673, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542650732492861e-05, + "loss": 3.369, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1534281163786072e-05, + "loss": 3.3627, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525895216275552e-05, + "loss": 3.3686, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1517509268765032e-05, + "loss": 3.3709, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1509123321254512e-05, + "loss": 3.3655, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1500753752547723e-05, + "loss": 3.3572, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492367805037203e-05, + "loss": 3.3673, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483981857526683e-05, + "loss": 3.3616, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475595910016163e-05, + "loss": 3.3706, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1467226341309374e-05, + "loss": 3.3587, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458840393798855e-05, + "loss": 3.3568, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450454446288335e-05, + "loss": 3.3584, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1442084877581546e-05, + "loss": 3.3636, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433698930071026e-05, + "loss": 3.3621, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425312982560506e-05, + "loss": 3.369, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1416927035049986e-05, + "loss": 3.3711, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408557466343197e-05, + "loss": 3.3574, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400171518832677e-05, + "loss": 3.3682, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391785571322156e-05, + "loss": 3.3663, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383399623811636e-05, + "loss": 3.3769, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1375030055104847e-05, + "loss": 3.3597, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1366644107594327e-05, + "loss": 3.3668, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1358258160083809e-05, + "loss": 3.3699, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1349872212573287e-05, + "loss": 3.373, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341502643866498e-05, + "loss": 3.3606, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.133311669635598e-05, + "loss": 3.3619, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.132473074884546e-05, + "loss": 3.3701, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316344801334938e-05, + "loss": 3.36, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.130797523262815e-05, + "loss": 3.3572, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.129958928511763e-05, + "loss": 3.374, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1291203337607108e-05, + "loss": 3.3582, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.128281739009659e-05, + "loss": 3.3657, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1274447821389801e-05, + "loss": 3.3569, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.8627355098724365, + "eval_runtime": 313.2615, + "eval_samples_per_second": 1218.123, + "eval_steps_per_second": 38.067, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1266061873879281e-05, + "loss": 3.3354, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.125767592636876e-05, + "loss": 3.3534, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.124928997885824e-05, + "loss": 3.3626, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.124090403134772e-05, + "loss": 3.3757, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1232534462640933e-05, + "loss": 3.3693, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224148515130411e-05, + "loss": 3.3705, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1215762567619891e-05, + "loss": 3.3575, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207376620109371e-05, + "loss": 3.3663, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1199007051402582e-05, + "loss": 3.3575, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190621103892062e-05, + "loss": 3.3662, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1182235156381544e-05, + "loss": 3.3623, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1173849208871024e-05, + "loss": 3.3683, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165496018967965e-05, + "loss": 3.378, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1157110071457445e-05, + "loss": 3.355, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1148724123946925e-05, + "loss": 3.3455, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1140338176436405e-05, + "loss": 3.3483, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1131952228925885e-05, + "loss": 3.3657, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123566281415365e-05, + "loss": 3.3615, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1115180333904845e-05, + "loss": 3.3584, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106794386394325e-05, + "loss": 3.3625, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098424817687536e-05, + "loss": 3.3843, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1090038870177016e-05, + "loss": 3.3579, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081669301470228e-05, + "loss": 3.3577, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073283353959707e-05, + "loss": 3.363, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064897406449186e-05, + "loss": 3.3716, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1056511458938668e-05, + "loss": 3.3503, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1048125511428146e-05, + "loss": 3.3609, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039739563917626e-05, + "loss": 3.3686, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031353616407106e-05, + "loss": 3.3557, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1022967668896586e-05, + "loss": 3.3509, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1014598100189797e-05, + "loss": 3.3494, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1006212152679279e-05, + "loss": 3.358, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0997826205168759e-05, + "loss": 3.3682, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989456636461968e-05, + "loss": 3.368, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.098107068895145e-05, + "loss": 3.363, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.097268474144093e-05, + "loss": 3.3552, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.096429879393041e-05, + "loss": 3.3666, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.095592922522362e-05, + "loss": 3.3507, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.09475432777131e-05, + "loss": 3.359, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.093915733020258e-05, + "loss": 3.3593, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.093077138269206e-05, + "loss": 3.3552, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.092240181398527e-05, + "loss": 3.3505, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.091401586647475e-05, + "loss": 3.3716, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905629918964232e-05, + "loss": 3.3549, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.089724397145371e-05, + "loss": 3.3611, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0888874402746921e-05, + "loss": 3.3675, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0880488455236403e-05, + "loss": 3.3571, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0872102507725883e-05, + "loss": 3.3554, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0863716560215361e-05, + "loss": 3.3386, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855346991508574e-05, + "loss": 3.3528, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0846961043998054e-05, + "loss": 3.364, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838575096487532e-05, + "loss": 3.3609, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830189148977014e-05, + "loss": 3.3493, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0821819580270224e-05, + "loss": 3.3465, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0813433632759704e-05, + "loss": 3.3546, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0805047685249184e-05, + "loss": 3.3448, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0796661737738664e-05, + "loss": 3.3711, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0788292169031875e-05, + "loss": 3.3516, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0779906221521357e-05, + "loss": 3.3605, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771520274010835e-05, + "loss": 3.3659, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0763134326500315e-05, + "loss": 3.344, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754764757793527e-05, + "loss": 3.35, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746378810283006e-05, + "loss": 3.3541, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0737992862772486e-05, + "loss": 3.3461, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729606915261967e-05, + "loss": 3.3474, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0721237346555178e-05, + "loss": 3.3631, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712851399044656e-05, + "loss": 3.3619, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704465451534138e-05, + "loss": 3.3519, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0696079504023618e-05, + "loss": 3.3415, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687709935316829e-05, + "loss": 3.352, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0679323987806309e-05, + "loss": 3.3594, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0670938040295789e-05, + "loss": 3.3572, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0662552092785269e-05, + "loss": 3.3555, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.065418252407848e-05, + "loss": 3.3596, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.064579657656796e-05, + "loss": 3.3662, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.063741062905744e-05, + "loss": 3.36, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0629024681546921e-05, + "loss": 3.3486, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.062065511284013e-05, + "loss": 3.3637, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.061226916532961e-05, + "loss": 3.3582, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0603883217819092e-05, + "loss": 3.3539, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.059549727030857e-05, + "loss": 3.3651, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0587127701601782e-05, + "loss": 3.3622, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0578741754091262e-05, + "loss": 3.3713, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570355806580742e-05, + "loss": 3.3617, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.056196985907022e-05, + "loss": 3.3476, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0553600290363433e-05, + "loss": 3.3493, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545214342852913e-05, + "loss": 3.361, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0536828395342393e-05, + "loss": 3.3649, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0528442447831873e-05, + "loss": 3.3577, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0520072879125084e-05, + "loss": 3.3566, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0511686931614564e-05, + "loss": 3.3636, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503300984104044e-05, + "loss": 3.3505, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0494915036593524e-05, + "loss": 3.3537, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486545467886736e-05, + "loss": 3.351, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478159520376216e-05, + "loss": 3.3598, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469773572865694e-05, + "loss": 3.3667, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461387625355174e-05, + "loss": 3.3552, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0453018056648387e-05, + "loss": 3.3439, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444632109137865e-05, + "loss": 3.3596, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436246161627345e-05, + "loss": 3.359, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427860214116827e-05, + "loss": 3.3608, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419490645410037e-05, + "loss": 3.3512, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411104697899517e-05, + "loss": 3.3498, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0402718750388997e-05, + "loss": 3.3439, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394332802878477e-05, + "loss": 3.3607, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.038596323417169e-05, + "loss": 3.3466, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377577286661168e-05, + "loss": 3.3531, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369191339150648e-05, + "loss": 3.3585, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0360805391640128e-05, + "loss": 3.355, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352435822933339e-05, + "loss": 3.3457, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0344049875422819e-05, + "loss": 3.3513, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0335663927912299e-05, + "loss": 3.3449, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.032727798040178e-05, + "loss": 3.358, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.031890841169499e-05, + "loss": 3.3515, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0310522464184471e-05, + "loss": 3.3564, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302136516673951e-05, + "loss": 3.3533, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.029375056916343e-05, + "loss": 3.3617, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285381000456642e-05, + "loss": 3.3531, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0276995052946122e-05, + "loss": 3.3613, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0268609105435602e-05, + "loss": 3.3609, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.026022315792508e-05, + "loss": 3.3581, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0251853589218292e-05, + "loss": 3.3417, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0243467641707772e-05, + "loss": 3.3591, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0235081694197252e-05, + "loss": 3.3546, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0226695746686732e-05, + "loss": 3.3611, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0218326177979943e-05, + "loss": 3.3475, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0209940230469425e-05, + "loss": 3.3484, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0201554282958903e-05, + "loss": 3.3491, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0193184714252114e-05, + "loss": 3.3527, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0184798766741595e-05, + "loss": 3.3519, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0176412819231075e-05, + "loss": 3.3618, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0168026871720554e-05, + "loss": 3.3657, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159657303013766e-05, + "loss": 3.3519, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0151271355503246e-05, + "loss": 3.3549, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0142885407992726e-05, + "loss": 3.3574, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0134499460482206e-05, + "loss": 3.3621, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0126129891775417e-05, + "loss": 3.3586, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117743944264897e-05, + "loss": 3.3567, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0109357996754377e-05, + "loss": 3.3624, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0100972049243857e-05, + "loss": 3.3593, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092602480537067e-05, + "loss": 3.355, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.008423291183028e-05, + "loss": 3.3534, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075846964319758e-05, + "loss": 3.3596, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.006746101680924e-05, + "loss": 3.3519, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.005907506929872e-05, + "loss": 3.345, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.00506891217882e-05, + "loss": 3.3664, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042303174277678e-05, + "loss": 3.3507, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.003391722676716e-05, + "loss": 3.3538, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.002553127925664e-05, + "loss": 3.3463, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0017161710549849e-05, + "loss": 3.348, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.8634111881256104, + "eval_runtime": 313.158, + "eval_samples_per_second": 1218.525, + "eval_steps_per_second": 38.08, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.000877576303933e-05, + "loss": 3.3402, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 1.000038981552881e-05, + "loss": 3.3554, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.99200386801829e-06, + "loss": 3.3642, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.983634299311501e-06, + "loss": 3.3595, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.975248351800981e-06, + "loss": 3.3637, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.966862404290461e-06, + "loss": 3.3505, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.958476456779941e-06, + "loss": 3.356, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.950106888073152e-06, + "loss": 3.3482, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.941720940562632e-06, + "loss": 3.3603, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.933334993052112e-06, + "loss": 3.3541, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.924949045541592e-06, + "loss": 3.3592, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.916579476834802e-06, + "loss": 3.3586, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.908209908128015e-06, + "loss": 3.3522, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.899823960617495e-06, + "loss": 3.3376, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.891438013106975e-06, + "loss": 3.3443, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.883052065596455e-06, + "loss": 3.3477, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.874666118085935e-06, + "loss": 3.3546, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.866280170575413e-06, + "loss": 3.3494, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.857894223064895e-06, + "loss": 3.356, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.849524654358105e-06, + "loss": 3.3778, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.841138706847585e-06, + "loss": 3.3511, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.832769138140796e-06, + "loss": 3.351, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.824383190630276e-06, + "loss": 3.3532, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.815997243119756e-06, + "loss": 3.3617, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.807611295609238e-06, + "loss": 3.342, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.799225348098716e-06, + "loss": 3.3469, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.790839400588196e-06, + "loss": 3.3615, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.782453453077676e-06, + "loss": 3.3486, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.774067505567156e-06, + "loss": 3.3386, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.765697936860367e-06, + "loss": 3.341, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.757311989349848e-06, + "loss": 3.3508, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.748926041839327e-06, + "loss": 3.3557, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.740540094328806e-06, + "loss": 3.3645, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.732170525622019e-06, + "loss": 3.3491, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.723784578111499e-06, + "loss": 3.348, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.715398630600977e-06, + "loss": 3.3574, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.70702906189419e-06, + "loss": 3.3394, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.69864311438367e-06, + "loss": 3.3511, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.69025716687315e-06, + "loss": 3.347, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.68187121936263e-06, + "loss": 3.3492, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.67350165065584e-06, + "loss": 3.3389, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.66511570314532e-06, + "loss": 3.3631, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.6567297556348e-06, + "loss": 3.3462, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.64834380812428e-06, + "loss": 3.351, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.639974239417491e-06, + "loss": 3.3591, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.631588291906973e-06, + "loss": 3.3512, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.623202344396451e-06, + "loss": 3.345, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.61481639688593e-06, + "loss": 3.3352, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.606446828179143e-06, + "loss": 3.3407, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.598060880668623e-06, + "loss": 3.3579, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.589674933158102e-06, + "loss": 3.3499, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.581288985647583e-06, + "loss": 3.3393, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.572919416940794e-06, + "loss": 3.3395, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.564533469430272e-06, + "loss": 3.3477, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.556147521919754e-06, + "loss": 3.3372, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.547761574409234e-06, + "loss": 3.3563, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.539392005702445e-06, + "loss": 3.3442, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.531006058191925e-06, + "loss": 3.3506, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.522620110681405e-06, + "loss": 3.3539, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.514234163170884e-06, + "loss": 3.3426, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.505864594464097e-06, + "loss": 3.337, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.497478646953575e-06, + "loss": 3.3453, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.489092699443055e-06, + "loss": 3.3373, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.480706751932535e-06, + "loss": 3.339, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.472337183225746e-06, + "loss": 3.3539, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.463951235715226e-06, + "loss": 3.3572, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.455565288204708e-06, + "loss": 3.3411, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.447179340694188e-06, + "loss": 3.3379, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.438809771987398e-06, + "loss": 3.3373, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.430423824476878e-06, + "loss": 3.3494, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.422037876966358e-06, + "loss": 3.3456, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.413651929455836e-06, + "loss": 3.3487, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.405282360749049e-06, + "loss": 3.3517, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.396896413238529e-06, + "loss": 3.3545, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.388510465728009e-06, + "loss": 3.3568, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.380124518217489e-06, + "loss": 3.3357, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.3717549495107e-06, + "loss": 3.3511, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.36336900200018e-06, + "loss": 3.3519, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.354983054489661e-06, + "loss": 3.3436, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.34659710697914e-06, + "loss": 3.359, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.33822753827235e-06, + "loss": 3.3534, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.329841590761832e-06, + "loss": 3.3602, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.32145564325131e-06, + "loss": 3.3542, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.31306969574079e-06, + "loss": 3.3335, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.304700127034003e-06, + "loss": 3.3431, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.296314179523483e-06, + "loss": 3.3527, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.28792823201296e-06, + "loss": 3.3543, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.279542284502442e-06, + "loss": 3.3493, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.271172715795653e-06, + "loss": 3.3449, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.262786768285133e-06, + "loss": 3.3505, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.254400820774613e-06, + "loss": 3.3448, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.246014873264093e-06, + "loss": 3.3405, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.237645304557304e-06, + "loss": 3.3439, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.229259357046784e-06, + "loss": 3.352, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.220873409536264e-06, + "loss": 3.361, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.212487462025744e-06, + "loss": 3.3441, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.204117893318956e-06, + "loss": 3.3382, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.195731945808435e-06, + "loss": 3.3473, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.187345998297915e-06, + "loss": 3.352, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.178976429591127e-06, + "loss": 3.3502, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.170590482080607e-06, + "loss": 3.3437, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.162204534570085e-06, + "loss": 3.3444, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.153818587059567e-06, + "loss": 3.3314, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.145449018352778e-06, + "loss": 3.3508, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.137063070842258e-06, + "loss": 3.3405, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.128677123331738e-06, + "loss": 3.3403, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.120291175821218e-06, + "loss": 3.3464, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.11192160711443e-06, + "loss": 3.3484, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.103535659603908e-06, + "loss": 3.34, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.095149712093388e-06, + "loss": 3.3443, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.086763764582868e-06, + "loss": 3.3374, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.078394195876079e-06, + "loss": 3.3475, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.070008248365559e-06, + "loss": 3.3398, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.061622300855039e-06, + "loss": 3.3452, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.05323635334452e-06, + "loss": 3.3469, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.04486678463773e-06, + "loss": 3.349, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.036480837127211e-06, + "loss": 3.3452, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.028094889616691e-06, + "loss": 3.3509, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.01970894210617e-06, + "loss": 3.3509, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.011339373399382e-06, + "loss": 3.3477, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 9.002953425888862e-06, + "loss": 3.3343, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.994567478378342e-06, + "loss": 3.3512, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.986181530867822e-06, + "loss": 3.3435, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.977811962161033e-06, + "loss": 3.3512, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.969426014650513e-06, + "loss": 3.342, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.961040067139993e-06, + "loss": 3.3385, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.952654119629473e-06, + "loss": 3.3371, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.944284550922683e-06, + "loss": 3.3444, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.935898603412165e-06, + "loss": 3.3421, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.927512655901643e-06, + "loss": 3.355, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.919126708391123e-06, + "loss": 3.3574, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.910757139684336e-06, + "loss": 3.3428, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.902371192173816e-06, + "loss": 3.3409, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.893985244663294e-06, + "loss": 3.3449, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.885599297152774e-06, + "loss": 3.3515, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.877229728445986e-06, + "loss": 3.3509, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.868843780935466e-06, + "loss": 3.3513, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.860457833424946e-06, + "loss": 3.348, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.852071885914426e-06, + "loss": 3.349, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.843702317207637e-06, + "loss": 3.3472, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.835316369697117e-06, + "loss": 3.345, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.826930422186597e-06, + "loss": 3.3519, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.818544474676077e-06, + "loss": 3.3461, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.81017490596929e-06, + "loss": 3.3293, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.801788958458768e-06, + "loss": 3.3599, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.793403010948248e-06, + "loss": 3.3417, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.785017063437727e-06, + "loss": 3.3441, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.77664749473094e-06, + "loss": 3.3359, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.768261547220418e-06, + "loss": 3.3387, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.864062547683716, + "eval_runtime": 304.5059, + "eval_samples_per_second": 1253.148, + "eval_steps_per_second": 39.162, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.7598755997099e-06, + "loss": 3.3314, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.75148965219938e-06, + "loss": 3.347, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.743120083492589e-06, + "loss": 3.3591, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.73473413598207e-06, + "loss": 3.3413, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.72634818847155e-06, + "loss": 3.3607, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.71796224096103e-06, + "loss": 3.3359, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.709592672254241e-06, + "loss": 3.3466, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.701206724743721e-06, + "loss": 3.3398, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.692820777233201e-06, + "loss": 3.3492, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.684434829722681e-06, + "loss": 3.3462, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.676065261015892e-06, + "loss": 3.346, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.667679313505372e-06, + "loss": 3.3499, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.659309744798584e-06, + "loss": 3.3424, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.650923797288063e-06, + "loss": 3.3337, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.642537849777543e-06, + "loss": 3.3346, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.634151902267024e-06, + "loss": 3.3394, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.625765954756504e-06, + "loss": 3.3475, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.617380007245982e-06, + "loss": 3.3384, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.608994059735462e-06, + "loss": 3.3461, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.600624491028675e-06, + "loss": 3.3689, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.592238543518153e-06, + "loss": 3.3427, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.583868974811366e-06, + "loss": 3.3378, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.575483027300846e-06, + "loss": 3.3434, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.567097079790326e-06, + "loss": 3.3511, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.558711132279806e-06, + "loss": 3.3346, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.550325184769285e-06, + "loss": 3.3453, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.541939237258765e-06, + "loss": 3.3478, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.533553289748244e-06, + "loss": 3.3419, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.525167342237725e-06, + "loss": 3.3263, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.516797773530936e-06, + "loss": 3.3369, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.508411826020416e-06, + "loss": 3.3379, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.500025878509896e-06, + "loss": 3.3476, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.491639930999376e-06, + "loss": 3.3549, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.483270362292588e-06, + "loss": 3.3392, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.474884414782067e-06, + "loss": 3.3358, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.466498467271547e-06, + "loss": 3.3492, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.458112519761027e-06, + "loss": 3.3297, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.449742951054239e-06, + "loss": 3.3438, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.441357003543717e-06, + "loss": 3.3345, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.432971056033197e-06, + "loss": 3.3387, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.42460148732641e-06, + "loss": 3.3316, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.41621553981589e-06, + "loss": 3.3536, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.40782959230537e-06, + "loss": 3.3409, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.39944364479485e-06, + "loss": 3.3395, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.39105769728433e-06, + "loss": 3.3459, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.38268812857754e-06, + "loss": 3.347, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.37430218106702e-06, + "loss": 3.333, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.3659162335565e-06, + "loss": 3.3262, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.357546664849713e-06, + "loss": 3.3277, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.349160717339191e-06, + "loss": 3.3491, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.340774769828671e-06, + "loss": 3.3409, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.332388822318151e-06, + "loss": 3.3299, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.324019253611364e-06, + "loss": 3.332, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.315633306100842e-06, + "loss": 3.3382, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.307247358590323e-06, + "loss": 3.3298, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.298861411079803e-06, + "loss": 3.3452, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.290491842373012e-06, + "loss": 3.335, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.282105894862494e-06, + "loss": 3.3386, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.273719947351974e-06, + "loss": 3.3472, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.265333999841454e-06, + "loss": 3.3308, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.256964431134665e-06, + "loss": 3.3301, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.248578483624145e-06, + "loss": 3.3408, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.240192536113625e-06, + "loss": 3.3258, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.231806588603105e-06, + "loss": 3.328, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.223437019896315e-06, + "loss": 3.3438, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.215051072385795e-06, + "loss": 3.3461, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.206665124875277e-06, + "loss": 3.3319, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.198279177364755e-06, + "loss": 3.3309, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.189909608657966e-06, + "loss": 3.3238, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.181523661147448e-06, + "loss": 3.3397, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.173137713636928e-06, + "loss": 3.3353, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.164751766126406e-06, + "loss": 3.339, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.156382197419618e-06, + "loss": 3.3418, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.147996249909098e-06, + "loss": 3.3427, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.139610302398577e-06, + "loss": 3.3493, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.131224354888058e-06, + "loss": 3.3302, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.122854786181269e-06, + "loss": 3.3427, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.114468838670749e-06, + "loss": 3.3433, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.106082891160229e-06, + "loss": 3.3275, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.097696943649709e-06, + "loss": 3.3518, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.08932737494292e-06, + "loss": 3.3451, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.080941427432401e-06, + "loss": 3.3491, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.07255547992188e-06, + "loss": 3.3467, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.06416953241136e-06, + "loss": 3.3242, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.055799963704572e-06, + "loss": 3.3373, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.04741401619405e-06, + "loss": 3.3388, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.03902806868353e-06, + "loss": 3.3445, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.030642121173012e-06, + "loss": 3.3414, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.022272552466223e-06, + "loss": 3.3361, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.013886604955701e-06, + "loss": 3.3443, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.005500657445183e-06, + "loss": 3.3383, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.997114709934663e-06, + "loss": 3.3271, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.988745141227873e-06, + "loss": 3.333, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.980359193717353e-06, + "loss": 3.3454, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.971973246206833e-06, + "loss": 3.353, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.963587298696313e-06, + "loss": 3.3361, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.955217729989524e-06, + "loss": 3.3248, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.946831782479004e-06, + "loss": 3.341, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.938445834968484e-06, + "loss": 3.3417, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.930059887457966e-06, + "loss": 3.3401, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.921690318751175e-06, + "loss": 3.3371, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.913304371240655e-06, + "loss": 3.3331, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.904918423730136e-06, + "loss": 3.3262, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.896532476219615e-06, + "loss": 3.3383, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.888162907512827e-06, + "loss": 3.3303, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.879776960002307e-06, + "loss": 3.3343, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.871391012491787e-06, + "loss": 3.3344, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.863021443784998e-06, + "loss": 3.3415, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.854635496274478e-06, + "loss": 3.3277, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.846249548763958e-06, + "loss": 3.3364, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.837863601253438e-06, + "loss": 3.3309, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.829494032546649e-06, + "loss": 3.3358, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.821108085036128e-06, + "loss": 3.3321, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.812722137525608e-06, + "loss": 3.3339, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.804336190015088e-06, + "loss": 3.3418, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.7959666213083e-06, + "loss": 3.3433, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.787580673797779e-06, + "loss": 3.3356, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.77919472628726e-06, + "loss": 3.3371, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.770808778776739e-06, + "loss": 3.341, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.762439210069952e-06, + "loss": 3.339, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.754053262559431e-06, + "loss": 3.3269, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.74566731504891e-06, + "loss": 3.343, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.73728136753839e-06, + "loss": 3.3355, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.728911798831602e-06, + "loss": 3.3409, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.720525851321082e-06, + "loss": 3.3326, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.712139903810562e-06, + "loss": 3.3312, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.703753956300042e-06, + "loss": 3.3299, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.695384387593253e-06, + "loss": 3.3318, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.686998440082733e-06, + "loss": 3.3349, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.678612492572213e-06, + "loss": 3.3438, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.670226545061693e-06, + "loss": 3.3503, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.661856976354905e-06, + "loss": 3.3369, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.653471028844383e-06, + "loss": 3.3306, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.645085081333863e-06, + "loss": 3.3395, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.636699133823343e-06, + "loss": 3.342, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.628329565116556e-06, + "loss": 3.3444, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.619943617606035e-06, + "loss": 3.3385, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.611557670095515e-06, + "loss": 3.3403, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.603171722584995e-06, + "loss": 3.333, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.5948021538782065e-06, + "loss": 3.3419, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.586416206367686e-06, + "loss": 3.336, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.578030258857166e-06, + "loss": 3.3381, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.569644311346646e-06, + "loss": 3.3395, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.561274742639856e-06, + "loss": 3.3262, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.552888795129337e-06, + "loss": 3.3497, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.544502847618817e-06, + "loss": 3.3368, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.536116900108298e-06, + "loss": 3.3321, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.527747331401508e-06, + "loss": 3.3297, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.519361383890989e-06, + "loss": 3.3283, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.8637282848358154, + "eval_runtime": 305.0428, + "eval_samples_per_second": 1250.942, + "eval_steps_per_second": 39.093, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.5109754363804686e-06, + "loss": 3.3211, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.502589488869948e-06, + "loss": 3.339, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.494203541359428e-06, + "loss": 3.3484, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.4858175938489084e-06, + "loss": 3.3338, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.47744802514212e-06, + "loss": 3.3514, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.469062077631598e-06, + "loss": 3.3291, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.460676130121079e-06, + "loss": 3.3382, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.452290182610559e-06, + "loss": 3.3263, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.443920613903771e-06, + "loss": 3.3424, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.43553466639325e-06, + "loss": 3.3359, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.42714871888273e-06, + "loss": 3.3342, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.4187791501759414e-06, + "loss": 3.3461, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.410409581469153e-06, + "loss": 3.3308, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.402023633958632e-06, + "loss": 3.3242, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.393637686448113e-06, + "loss": 3.3249, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.385251738937593e-06, + "loss": 3.3328, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.376865791427072e-06, + "loss": 3.3379, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.368479843916552e-06, + "loss": 3.3304, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.360110275209764e-06, + "loss": 3.3357, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.3517243276992444e-06, + "loss": 3.3576, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.3433383801887235e-06, + "loss": 3.3349, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.3349524326782035e-06, + "loss": 3.33, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.3265664851676835e-06, + "loss": 3.3358, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.3181805376571626e-06, + "loss": 3.3411, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.309794590146643e-06, + "loss": 3.3267, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.301408642636123e-06, + "loss": 3.3348, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.293039073929335e-06, + "loss": 3.3372, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.284653126418814e-06, + "loss": 3.332, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.276267178908294e-06, + "loss": 3.3199, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.267881231397775e-06, + "loss": 3.3306, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.259511662690985e-06, + "loss": 3.3314, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.251125715180465e-06, + "loss": 3.3353, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.2427397676699455e-06, + "loss": 3.3502, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.2343538201594255e-06, + "loss": 3.3296, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.225984251452636e-06, + "loss": 3.3274, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.217598303942116e-06, + "loss": 3.3397, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.209212356431597e-06, + "loss": 3.3269, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.200826408921075e-06, + "loss": 3.3304, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.192456840214287e-06, + "loss": 3.325, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.184070892703768e-06, + "loss": 3.3321, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.175684945193248e-06, + "loss": 3.3201, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.167298997682727e-06, + "loss": 3.3455, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.1589294289759384e-06, + "loss": 3.3286, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.150543481465418e-06, + "loss": 3.3352, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.1421575339548975e-06, + "loss": 3.3378, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.133771586444378e-06, + "loss": 3.3343, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.12540201773759e-06, + "loss": 3.3285, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.11701607022707e-06, + "loss": 3.32, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.108630122716549e-06, + "loss": 3.3185, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.100244175206029e-06, + "loss": 3.3413, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.091874606499241e-06, + "loss": 3.332, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.083488658988721e-06, + "loss": 3.3214, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.0751027114782e-06, + "loss": 3.3257, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.0667167639676805e-06, + "loss": 3.3307, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.058347195260892e-06, + "loss": 3.3141, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.049961247750371e-06, + "loss": 3.3361, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.041575300239851e-06, + "loss": 3.328, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.033189352729332e-06, + "loss": 3.3286, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.024819784022544e-06, + "loss": 3.3405, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.016433836512022e-06, + "loss": 3.322, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.008047889001503e-06, + "loss": 3.3203, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.999661941490983e-06, + "loss": 3.3337, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.991292372784194e-06, + "loss": 3.3189, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.982906425273673e-06, + "loss": 3.3199, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.974520477763153e-06, + "loss": 3.3329, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.966134530252634e-06, + "loss": 3.3367, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.957764961545844e-06, + "loss": 3.3208, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.949379014035325e-06, + "loss": 3.3224, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.940993066524805e-06, + "loss": 3.3133, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.932607119014286e-06, + "loss": 3.3316, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.924237550307496e-06, + "loss": 3.3253, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.9158516027969755e-06, + "loss": 3.3324, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.907465655286456e-06, + "loss": 3.3315, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.8990797077759355e-06, + "loss": 3.3329, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.890710139069147e-06, + "loss": 3.3447, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.882324191558627e-06, + "loss": 3.319, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.873938244048107e-06, + "loss": 3.3317, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.865552296537586e-06, + "loss": 3.334, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.857182727830798e-06, + "loss": 3.3215, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.8487967803202786e-06, + "loss": 3.3405, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.8404108328097585e-06, + "loss": 3.3359, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.832024885299238e-06, + "loss": 3.3417, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.823655316592449e-06, + "loss": 3.3373, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.815269369081929e-06, + "loss": 3.3155, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.806883421571408e-06, + "loss": 3.3288, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.798497474060888e-06, + "loss": 3.3272, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.7901279053541e-06, + "loss": 3.3374, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.781741957843581e-06, + "loss": 3.3319, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.77335601033306e-06, + "loss": 3.3293, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.7649864416262715e-06, + "loss": 3.3333, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.756600494115751e-06, + "loss": 3.3318, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.748214546605232e-06, + "loss": 3.3154, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.7398285990947105e-06, + "loss": 3.3236, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.731459030387922e-06, + "loss": 3.3349, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.723073082877403e-06, + "loss": 3.3403, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.714687135366882e-06, + "loss": 3.3313, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.706301187856362e-06, + "loss": 3.3141, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.697931619149574e-06, + "loss": 3.3316, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.689545671639054e-06, + "loss": 3.334, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.681159724128533e-06, + "loss": 3.3301, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.6727737766180135e-06, + "loss": 3.3267, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.664404207911225e-06, + "loss": 3.3259, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.656018260400705e-06, + "loss": 3.3159, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.647632312890184e-06, + "loss": 3.3342, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.639246365379664e-06, + "loss": 3.3154, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.630876796672876e-06, + "loss": 3.3269, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.622490849162355e-06, + "loss": 3.3211, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.614104901651835e-06, + "loss": 3.3334, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.605718954141316e-06, + "loss": 3.3159, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.597349385434527e-06, + "loss": 3.3318, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.588963437924006e-06, + "loss": 3.3223, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.580577490413486e-06, + "loss": 3.3247, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.572191542902967e-06, + "loss": 3.3261, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.563821974196179e-06, + "loss": 3.3227, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.555436026685657e-06, + "loss": 3.3359, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.547050079175138e-06, + "loss": 3.3325, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.538664131664618e-06, + "loss": 3.3287, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.530294562957829e-06, + "loss": 3.327, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.5219086154473086e-06, + "loss": 3.3316, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.5135226679367885e-06, + "loss": 3.3325, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.505136720426268e-06, + "loss": 3.3145, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.496767151719479e-06, + "loss": 3.3339, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.48838120420896e-06, + "loss": 3.3277, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.47999525669844e-06, + "loss": 3.3319, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.471609309187919e-06, + "loss": 3.3245, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.463239740481131e-06, + "loss": 3.3274, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.454853792970611e-06, + "loss": 3.3177, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.4464678454600915e-06, + "loss": 3.3221, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.438081897949571e-06, + "loss": 3.3259, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.429712329242782e-06, + "loss": 3.3321, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.421326381732262e-06, + "loss": 3.3417, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.412940434221741e-06, + "loss": 3.3292, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.404554486711221e-06, + "loss": 3.3202, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.396184918004433e-06, + "loss": 3.3308, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.387798970493914e-06, + "loss": 3.335, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.379413022983392e-06, + "loss": 3.3336, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.371027075472873e-06, + "loss": 3.3305, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.3626575067660844e-06, + "loss": 3.3263, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.354271559255564e-06, + "loss": 3.33, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.3458856117450435e-06, + "loss": 3.3343, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.337516043038255e-06, + "loss": 3.326, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.329130095527735e-06, + "loss": 3.3293, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.320744148017214e-06, + "loss": 3.3285, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.312358200506695e-06, + "loss": 3.318, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.303988631799907e-06, + "loss": 3.3378, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.295602684289387e-06, + "loss": 3.3298, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.287216736778866e-06, + "loss": 3.3241, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.278830789268346e-06, + "loss": 3.3204, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.270461220561557e-06, + "loss": 3.3184, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.864201068878174, + "eval_runtime": 307.9165, + "eval_samples_per_second": 1239.268, + "eval_steps_per_second": 38.728, + "step": 2671200 + }, + { + "epoch": 1.0, + "learning_rate": 6.262075273051038e-06, + "loss": 3.3161, + "step": 2671616 + }, + { + "epoch": 1.0, + "learning_rate": 6.253689325540517e-06, + "loss": 3.3296, + "step": 2672128 + }, + { + "epoch": 1.0, + "learning_rate": 6.245303378029997e-06, + "loss": 3.3381, + "step": 2672640 + }, + { + "epoch": 1.0, + "learning_rate": 6.236933809323209e-06, + "loss": 3.328, + "step": 2673152 + }, + { + "epoch": 1.0, + "learning_rate": 6.228547861812689e-06, + "loss": 3.3461, + "step": 2673664 + }, + { + "epoch": 1.0, + "learning_rate": 6.220161914302168e-06, + "loss": 3.3158, + "step": 2674176 + }, + { + "epoch": 1.0, + "learning_rate": 6.211775966791649e-06, + "loss": 3.3326, + "step": 2674688 + }, + { + "epoch": 1.0, + "learning_rate": 6.2034063980848595e-06, + "loss": 3.3151, + "step": 2675200 + }, + { + "epoch": 1.0, + "learning_rate": 6.195020450574339e-06, + "loss": 3.3316, + "step": 2675712 + }, + { + "epoch": 1.0, + "learning_rate": 6.186634503063819e-06, + "loss": 3.3312, + "step": 2676224 + }, + { + "epoch": 1.0, + "learning_rate": 6.1782485555532985e-06, + "loss": 3.3227, + "step": 2676736 + }, + { + "epoch": 1.0, + "learning_rate": 6.16987898684651e-06, + "loss": 3.3367, + "step": 2677248 + }, + { + "epoch": 1.0, + "learning_rate": 6.161509418139723e-06, + "loss": 3.3222, + "step": 2677760 + }, + { + "epoch": 1.0, + "learning_rate": 6.153123470629202e-06, + "loss": 3.3162, + "step": 2678272 + }, + { + "epoch": 1.0, + "learning_rate": 6.144737523118682e-06, + "loss": 3.3164, + "step": 2678784 + }, + { + "epoch": 1.0, + "learning_rate": 6.136351575608162e-06, + "loss": 3.3221, + "step": 2679296 + }, + { + "epoch": 1.0, + "learning_rate": 6.127965628097642e-06, + "loss": 3.3286, + "step": 2679808 + }, + { + "epoch": 1.0, + "learning_rate": 6.1195796805871215e-06, + "loss": 3.3202, + "step": 2680320 + }, + { + "epoch": 1.0, + "learning_rate": 6.1111937330766015e-06, + "loss": 3.3267, + "step": 2680832 + }, + { + "epoch": 1.0, + "learning_rate": 6.102807785566081e-06, + "loss": 3.3482, + "step": 2681344 + }, + { + "epoch": 1.0, + "learning_rate": 6.094438216859292e-06, + "loss": 3.3275, + "step": 2681856 + }, + { + "epoch": 1.0, + "learning_rate": 6.086068648152504e-06, + "loss": 3.3255, + "step": 2682368 + }, + { + "epoch": 1.0, + "learning_rate": 6.077682700641984e-06, + "loss": 3.3266, + "step": 2682880 + }, + { + "epoch": 1.0, + "learning_rate": 6.069296753131464e-06, + "loss": 3.3313, + "step": 2683392 + }, + { + "epoch": 1.0, + "learning_rate": 6.060910805620944e-06, + "loss": 3.3185, + "step": 2683904 + }, + { + "epoch": 1.0, + "learning_rate": 6.052524858110424e-06, + "loss": 3.3284, + "step": 2684416 + }, + { + "epoch": 1.0, + "learning_rate": 6.044138910599904e-06, + "loss": 3.3286, + "step": 2684928 + }, + { + "epoch": 1.0, + "learning_rate": 6.035752963089384e-06, + "loss": 3.3203, + "step": 2685440 + }, + { + "epoch": 1.0, + "learning_rate": 6.027367015578863e-06, + "loss": 3.3135, + "step": 2685952 + }, + { + "epoch": 1.01, + "learning_rate": 6.018997446872074e-06, + "loss": 3.317, + "step": 2686464 + }, + { + "epoch": 1.01, + "learning_rate": 6.010611499361554e-06, + "loss": 3.3261, + "step": 2686976 + }, + { + "epoch": 1.01, + "learning_rate": 6.002225551851034e-06, + "loss": 3.325, + "step": 2687488 + }, + { + "epoch": 1.01, + "learning_rate": 5.993839604340514e-06, + "loss": 3.3394, + "step": 2688000 + }, + { + "epoch": 1.01, + "learning_rate": 5.985470035633726e-06, + "loss": 3.325, + "step": 2688512 + }, + { + "epoch": 1.01, + "learning_rate": 5.977084088123206e-06, + "loss": 3.3166, + "step": 2689024 + }, + { + "epoch": 1.01, + "learning_rate": 5.968698140612686e-06, + "loss": 3.3281, + "step": 2689536 + }, + { + "epoch": 1.01, + "learning_rate": 5.960312193102166e-06, + "loss": 3.3218, + "step": 2690048 + }, + { + "epoch": 1.01, + "learning_rate": 5.951942624395377e-06, + "loss": 3.3173, + "step": 2690560 + }, + { + "epoch": 1.01, + "learning_rate": 5.9435566768848565e-06, + "loss": 3.3202, + "step": 2691072 + }, + { + "epoch": 1.01, + "learning_rate": 5.9351707293743364e-06, + "loss": 3.3213, + "step": 2691584 + }, + { + "epoch": 1.01, + "learning_rate": 5.926784781863816e-06, + "loss": 3.3135, + "step": 2692096 + }, + { + "epoch": 1.01, + "learning_rate": 5.918415213157027e-06, + "loss": 3.3352, + "step": 2692608 + }, + { + "epoch": 1.01, + "learning_rate": 5.910029265646508e-06, + "loss": 3.322, + "step": 2693120 + }, + { + "epoch": 1.01, + "learning_rate": 5.901643318135987e-06, + "loss": 3.3272, + "step": 2693632 + }, + { + "epoch": 1.01, + "learning_rate": 5.893257370625468e-06, + "loss": 3.3314, + "step": 2694144 + }, + { + "epoch": 1.01, + "learning_rate": 5.884887801918679e-06, + "loss": 3.3233, + "step": 2694656 + }, + { + "epoch": 1.01, + "learning_rate": 5.876501854408159e-06, + "loss": 3.3218, + "step": 2695168 + }, + { + "epoch": 1.01, + "learning_rate": 5.868115906897639e-06, + "loss": 3.3089, + "step": 2695680 + }, + { + "epoch": 1.01, + "learning_rate": 5.8597299593871185e-06, + "loss": 3.3031, + "step": 2696192 + }, + { + "epoch": 1.01, + "learning_rate": 5.85136039068033e-06, + "loss": 3.3382, + "step": 2696704 + }, + { + "epoch": 1.01, + "learning_rate": 5.842974443169809e-06, + "loss": 3.3224, + "step": 2697216 + }, + { + "epoch": 1.01, + "learning_rate": 5.83458849565929e-06, + "loss": 3.317, + "step": 2697728 + }, + { + "epoch": 1.01, + "learning_rate": 5.826218926952501e-06, + "loss": 3.3167, + "step": 2698240 + }, + { + "epoch": 1.01, + "learning_rate": 5.817832979441981e-06, + "loss": 3.3189, + "step": 2698752 + }, + { + "epoch": 1.01, + "learning_rate": 5.809447031931461e-06, + "loss": 3.3067, + "step": 2699264 + }, + { + "epoch": 1.01, + "learning_rate": 5.801061084420941e-06, + "loss": 3.3258, + "step": 2699776 + }, + { + "epoch": 1.01, + "learning_rate": 5.792691515714152e-06, + "loss": 3.3241, + "step": 2700288 + }, + { + "epoch": 1.01, + "learning_rate": 5.784305568203632e-06, + "loss": 3.3185, + "step": 2700800 + }, + { + "epoch": 1.01, + "learning_rate": 5.775919620693112e-06, + "loss": 3.33, + "step": 2701312 + }, + { + "epoch": 1.01, + "learning_rate": 5.767533673182591e-06, + "loss": 3.3115, + "step": 2701824 + }, + { + "epoch": 1.01, + "learning_rate": 5.759164104475803e-06, + "loss": 3.31, + "step": 2702336 + }, + { + "epoch": 1.01, + "learning_rate": 5.750778156965283e-06, + "loss": 3.3284, + "step": 2702848 + }, + { + "epoch": 1.01, + "learning_rate": 5.742392209454763e-06, + "loss": 3.3067, + "step": 2703360 + }, + { + "epoch": 1.01, + "learning_rate": 5.734006261944243e-06, + "loss": 3.308, + "step": 2703872 + }, + { + "epoch": 1.01, + "learning_rate": 5.7256366932374546e-06, + "loss": 3.3285, + "step": 2704384 + }, + { + "epoch": 1.01, + "learning_rate": 5.717250745726934e-06, + "loss": 3.329, + "step": 2704896 + }, + { + "epoch": 1.01, + "learning_rate": 5.7088647982164145e-06, + "loss": 3.3086, + "step": 2705408 + }, + { + "epoch": 1.01, + "learning_rate": 5.7004788507058936e-06, + "loss": 3.3213, + "step": 2705920 + }, + { + "epoch": 1.01, + "learning_rate": 5.692109281999106e-06, + "loss": 3.3027, + "step": 2706432 + }, + { + "epoch": 1.01, + "learning_rate": 5.683723334488585e-06, + "loss": 3.3249, + "step": 2706944 + }, + { + "epoch": 1.01, + "learning_rate": 5.675337386978065e-06, + "loss": 3.3167, + "step": 2707456 + }, + { + "epoch": 1.01, + "learning_rate": 5.666951439467545e-06, + "loss": 3.3253, + "step": 2707968 + }, + { + "epoch": 1.01, + "learning_rate": 5.658581870760756e-06, + "loss": 3.3205, + "step": 2708480 + }, + { + "epoch": 1.01, + "learning_rate": 5.650195923250237e-06, + "loss": 3.328, + "step": 2708992 + }, + { + "epoch": 1.01, + "learning_rate": 5.641809975739716e-06, + "loss": 3.3355, + "step": 2709504 + }, + { + "epoch": 1.01, + "learning_rate": 5.633424028229197e-06, + "loss": 3.3102, + "step": 2710016 + }, + { + "epoch": 1.01, + "learning_rate": 5.625054459522407e-06, + "loss": 3.3267, + "step": 2710528 + }, + { + "epoch": 1.01, + "learning_rate": 5.616668512011887e-06, + "loss": 3.3265, + "step": 2711040 + }, + { + "epoch": 1.01, + "learning_rate": 5.608282564501367e-06, + "loss": 3.3071, + "step": 2711552 + }, + { + "epoch": 1.01, + "learning_rate": 5.599896616990847e-06, + "loss": 3.3338, + "step": 2712064 + }, + { + "epoch": 1.01, + "learning_rate": 5.591527048284059e-06, + "loss": 3.3272, + "step": 2712576 + }, + { + "epoch": 1.01, + "learning_rate": 5.583141100773538e-06, + "loss": 3.3282, + "step": 2713088 + }, + { + "epoch": 1.01, + "learning_rate": 5.574755153263019e-06, + "loss": 3.3317, + "step": 2713600 + }, + { + "epoch": 1.01, + "learning_rate": 5.566369205752498e-06, + "loss": 3.3114, + "step": 2714112 + }, + { + "epoch": 1.01, + "learning_rate": 5.5579996370457095e-06, + "loss": 3.3154, + "step": 2714624 + }, + { + "epoch": 1.01, + "learning_rate": 5.5496136895351895e-06, + "loss": 3.3216, + "step": 2715136 + }, + { + "epoch": 1.01, + "learning_rate": 5.5412277420246694e-06, + "loss": 3.3292, + "step": 2715648 + }, + { + "epoch": 1.01, + "learning_rate": 5.532841794514149e-06, + "loss": 3.3238, + "step": 2716160 + }, + { + "epoch": 1.01, + "learning_rate": 5.52447222580736e-06, + "loss": 3.3214, + "step": 2716672 + }, + { + "epoch": 1.02, + "learning_rate": 5.516086278296841e-06, + "loss": 3.3214, + "step": 2717184 + }, + { + "epoch": 1.02, + "learning_rate": 5.50770033078632e-06, + "loss": 3.3295, + "step": 2717696 + }, + { + "epoch": 1.02, + "learning_rate": 5.499314383275801e-06, + "loss": 3.3093, + "step": 2718208 + }, + { + "epoch": 1.02, + "learning_rate": 5.490944814569012e-06, + "loss": 3.3138, + "step": 2718720 + }, + { + "epoch": 1.02, + "learning_rate": 5.482558867058492e-06, + "loss": 3.3272, + "step": 2719232 + }, + { + "epoch": 1.02, + "learning_rate": 5.474172919547972e-06, + "loss": 3.3332, + "step": 2719744 + }, + { + "epoch": 1.02, + "learning_rate": 5.465786972037451e-06, + "loss": 3.3228, + "step": 2720256 + }, + { + "epoch": 1.02, + "learning_rate": 5.457417403330662e-06, + "loss": 3.3073, + "step": 2720768 + }, + { + "epoch": 1.02, + "learning_rate": 5.449031455820142e-06, + "loss": 3.3205, + "step": 2721280 + }, + { + "epoch": 1.02, + "learning_rate": 5.440645508309622e-06, + "loss": 3.3224, + "step": 2721792 + }, + { + "epoch": 1.02, + "learning_rate": 5.432259560799102e-06, + "loss": 3.3227, + "step": 2722304 + }, + { + "epoch": 1.02, + "learning_rate": 5.423889992092314e-06, + "loss": 3.321, + "step": 2722816 + }, + { + "epoch": 1.02, + "learning_rate": 5.415504044581794e-06, + "loss": 3.318, + "step": 2723328 + }, + { + "epoch": 1.02, + "learning_rate": 5.407118097071274e-06, + "loss": 3.3091, + "step": 2723840 + }, + { + "epoch": 1.02, + "learning_rate": 5.398732149560754e-06, + "loss": 3.3216, + "step": 2724352 + }, + { + "epoch": 1.02, + "learning_rate": 5.390362580853965e-06, + "loss": 3.3118, + "step": 2724864 + }, + { + "epoch": 1.02, + "learning_rate": 5.3819766333434445e-06, + "loss": 3.3191, + "step": 2725376 + }, + { + "epoch": 1.02, + "learning_rate": 5.3735906858329244e-06, + "loss": 3.3102, + "step": 2725888 + }, + { + "epoch": 1.02, + "learning_rate": 5.365204738322404e-06, + "loss": 3.3269, + "step": 2726400 + }, + { + "epoch": 1.02, + "learning_rate": 5.356835169615616e-06, + "loss": 3.3081, + "step": 2726912 + }, + { + "epoch": 1.02, + "learning_rate": 5.348465600908828e-06, + "loss": 3.3251, + "step": 2727424 + }, + { + "epoch": 1.02, + "learning_rate": 5.340079653398307e-06, + "loss": 3.3088, + "step": 2727936 + }, + { + "epoch": 1.02, + "learning_rate": 5.3316937058877876e-06, + "loss": 3.3165, + "step": 2728448 + }, + { + "epoch": 1.02, + "learning_rate": 5.323307758377267e-06, + "loss": 3.3152, + "step": 2728960 + }, + { + "epoch": 1.02, + "learning_rate": 5.3149218108667475e-06, + "loss": 3.318, + "step": 2729472 + }, + { + "epoch": 1.02, + "learning_rate": 5.306535863356227e-06, + "loss": 3.3216, + "step": 2729984 + }, + { + "epoch": 1.02, + "learning_rate": 5.2981499158457065e-06, + "loss": 3.3277, + "step": 2730496 + }, + { + "epoch": 1.02, + "learning_rate": 5.2897639683351865e-06, + "loss": 3.3196, + "step": 2731008 + }, + { + "epoch": 1.02, + "learning_rate": 5.281394399628397e-06, + "loss": 3.317, + "step": 2731520 + }, + { + "epoch": 1.02, + "learning_rate": 5.273008452117878e-06, + "loss": 3.3232, + "step": 2732032 + }, + { + "epoch": 1.02, + "learning_rate": 5.264622504607357e-06, + "loss": 3.3229, + "step": 2732544 + }, + { + "epoch": 1.02, + "learning_rate": 5.256236557096838e-06, + "loss": 3.3077, + "step": 2733056 + }, + { + "epoch": 1.02, + "learning_rate": 5.247866988390049e-06, + "loss": 3.3268, + "step": 2733568 + }, + { + "epoch": 1.02, + "learning_rate": 5.23948104087953e-06, + "loss": 3.3158, + "step": 2734080 + }, + { + "epoch": 1.02, + "learning_rate": 5.231095093369009e-06, + "loss": 3.3243, + "step": 2734592 + }, + { + "epoch": 1.02, + "learning_rate": 5.222709145858489e-06, + "loss": 3.3152, + "step": 2735104 + }, + { + "epoch": 1.02, + "learning_rate": 5.2143395771517e-06, + "loss": 3.3205, + "step": 2735616 + }, + { + "epoch": 1.02, + "learning_rate": 5.205953629641179e-06, + "loss": 3.3067, + "step": 2736128 + }, + { + "epoch": 1.02, + "learning_rate": 5.19756768213066e-06, + "loss": 3.3168, + "step": 2736640 + }, + { + "epoch": 1.02, + "learning_rate": 5.189181734620139e-06, + "loss": 3.3165, + "step": 2737152 + }, + { + "epoch": 1.02, + "learning_rate": 5.180812165913351e-06, + "loss": 3.3198, + "step": 2737664 + }, + { + "epoch": 1.02, + "learning_rate": 5.172426218402831e-06, + "loss": 3.3292, + "step": 2738176 + }, + { + "epoch": 1.02, + "learning_rate": 5.164040270892311e-06, + "loss": 3.3242, + "step": 2738688 + }, + { + "epoch": 1.02, + "learning_rate": 5.155654323381791e-06, + "loss": 3.3094, + "step": 2739200 + }, + { + "epoch": 1.02, + "learning_rate": 5.1472847546750025e-06, + "loss": 3.3228, + "step": 2739712 + }, + { + "epoch": 1.02, + "learning_rate": 5.138898807164482e-06, + "loss": 3.325, + "step": 2740224 + }, + { + "epoch": 1.02, + "learning_rate": 5.1305128596539615e-06, + "loss": 3.3256, + "step": 2740736 + }, + { + "epoch": 1.02, + "learning_rate": 5.122126912143442e-06, + "loss": 3.3249, + "step": 2741248 + }, + { + "epoch": 1.02, + "learning_rate": 5.113757343436653e-06, + "loss": 3.3175, + "step": 2741760 + }, + { + "epoch": 1.02, + "learning_rate": 5.105371395926133e-06, + "loss": 3.3181, + "step": 2742272 + }, + { + "epoch": 1.02, + "learning_rate": 5.096985448415613e-06, + "loss": 3.3281, + "step": 2742784 + }, + { + "epoch": 1.02, + "learning_rate": 5.088599500905093e-06, + "loss": 3.3174, + "step": 2743296 + }, + { + "epoch": 1.02, + "learning_rate": 5.080229932198304e-06, + "loss": 3.323, + "step": 2743808 + }, + { + "epoch": 1.02, + "learning_rate": 5.071843984687785e-06, + "loss": 3.3149, + "step": 2744320 + }, + { + "epoch": 1.02, + "learning_rate": 5.0634580371772645e-06, + "loss": 3.3156, + "step": 2744832 + }, + { + "epoch": 1.02, + "learning_rate": 5.055072089666744e-06, + "loss": 3.3259, + "step": 2745344 + }, + { + "epoch": 1.02, + "learning_rate": 5.046702520959955e-06, + "loss": 3.3217, + "step": 2745856 + }, + { + "epoch": 1.02, + "learning_rate": 5.038316573449435e-06, + "loss": 3.3136, + "step": 2746368 + }, + { + "epoch": 1.02, + "learning_rate": 5.029930625938915e-06, + "loss": 3.3076, + "step": 2746880 + }, + { + "epoch": 1.02, + "learning_rate": 5.021544678428395e-06, + "loss": 3.313, + "step": 2747392 + }, + { + "epoch": 1.03, + "eval_loss": 3.864366054534912, + "eval_runtime": 309.6236, + "eval_samples_per_second": 1232.435, + "eval_steps_per_second": 38.515, + "step": 2747520 + }, + { + "epoch": 0.0, + "learning_rate": 5.013175109721607e-06, + "loss": 3.3032, + "step": 2747904 + }, + { + "epoch": 0.0, + "learning_rate": 5.004789162211086e-06, + "loss": 3.3193, + "step": 2748416 + }, + { + "epoch": 0.0, + "learning_rate": 4.996403214700567e-06, + "loss": 3.3258, + "step": 2748928 + }, + { + "epoch": 0.0, + "learning_rate": 4.988017267190046e-06, + "loss": 3.3222, + "step": 2749440 + }, + { + "epoch": 0.0, + "learning_rate": 4.9796476984832574e-06, + "loss": 3.3361, + "step": 2749952 + }, + { + "epoch": 0.0, + "learning_rate": 4.971261750972737e-06, + "loss": 3.315, + "step": 2750464 + }, + { + "epoch": 0.0, + "learning_rate": 4.962875803462217e-06, + "loss": 3.3203, + "step": 2750976 + }, + { + "epoch": 0.0, + "learning_rate": 4.954489855951697e-06, + "loss": 3.3105, + "step": 2751488 + }, + { + "epoch": 0.0, + "learning_rate": 4.946120287244908e-06, + "loss": 3.3192, + "step": 2752000 + }, + { + "epoch": 0.0, + "learning_rate": 4.937734339734389e-06, + "loss": 3.3211, + "step": 2752512 + }, + { + "epoch": 0.0, + "learning_rate": 4.929348392223868e-06, + "loss": 3.3171, + "step": 2753024 + }, + { + "epoch": 0.0, + "learning_rate": 4.920962444713349e-06, + "loss": 3.3272, + "step": 2753536 + }, + { + "epoch": 0.0, + "learning_rate": 4.912609254810291e-06, + "loss": 3.3125, + "step": 2754048 + }, + { + "epoch": 0.0, + "learning_rate": 4.904223307299771e-06, + "loss": 3.3098, + "step": 2754560 + }, + { + "epoch": 0.0, + "learning_rate": 4.895837359789251e-06, + "loss": 3.31, + "step": 2755072 + }, + { + "epoch": 0.0, + "learning_rate": 4.887451412278731e-06, + "loss": 3.3104, + "step": 2755584 + }, + { + "epoch": 0.0, + "learning_rate": 4.879065464768211e-06, + "loss": 3.3222, + "step": 2756096 + }, + { + "epoch": 0.0, + "learning_rate": 4.87067951725769e-06, + "loss": 3.3098, + "step": 2756608 + }, + { + "epoch": 0.0, + "learning_rate": 4.862293569747171e-06, + "loss": 3.3219, + "step": 2757120 + }, + { + "epoch": 0.0, + "learning_rate": 4.85390762223665e-06, + "loss": 3.3384, + "step": 2757632 + }, + { + "epoch": 0.0, + "learning_rate": 4.845538053529862e-06, + "loss": 3.3211, + "step": 2758144 + }, + { + "epoch": 0.0, + "learning_rate": 4.8371684848230726e-06, + "loss": 3.3171, + "step": 2758656 + }, + { + "epoch": 0.0, + "learning_rate": 4.828782537312553e-06, + "loss": 3.3159, + "step": 2759168 + }, + { + "epoch": 0.0, + "learning_rate": 4.8203965898020325e-06, + "loss": 3.3197, + "step": 2759680 + }, + { + "epoch": 0.0, + "learning_rate": 4.8120106422915124e-06, + "loss": 3.3095, + "step": 2760192 + }, + { + "epoch": 0.0, + "learning_rate": 4.803624694780992e-06, + "loss": 3.3226, + "step": 2760704 + }, + { + "epoch": 0.0, + "learning_rate": 4.795238747270472e-06, + "loss": 3.3164, + "step": 2761216 + }, + { + "epoch": 0.0, + "learning_rate": 4.786852799759952e-06, + "loss": 3.3125, + "step": 2761728 + }, + { + "epoch": 0.0, + "learning_rate": 4.778466852249432e-06, + "loss": 3.3052, + "step": 2762240 + }, + { + "epoch": 0.0, + "learning_rate": 4.770097283542644e-06, + "loss": 3.3123, + "step": 2762752 + }, + { + "epoch": 0.01, + "learning_rate": 4.761711336032124e-06, + "loss": 3.3152, + "step": 2763264 + }, + { + "epoch": 0.01, + "learning_rate": 4.753325388521603e-06, + "loss": 3.3187, + "step": 2763776 + }, + { + "epoch": 0.01, + "learning_rate": 4.744939441011084e-06, + "loss": 3.3292, + "step": 2764288 + }, + { + "epoch": 0.01, + "learning_rate": 4.7365698723042945e-06, + "loss": 3.3157, + "step": 2764800 + }, + { + "epoch": 0.01, + "learning_rate": 4.7281839247937745e-06, + "loss": 3.3074, + "step": 2765312 + }, + { + "epoch": 0.01, + "learning_rate": 4.7197979772832545e-06, + "loss": 3.3206, + "step": 2765824 + }, + { + "epoch": 0.01, + "learning_rate": 4.711412029772734e-06, + "loss": 3.3182, + "step": 2766336 + }, + { + "epoch": 0.01, + "learning_rate": 4.703042461065946e-06, + "loss": 3.3054, + "step": 2766848 + }, + { + "epoch": 0.01, + "learning_rate": 4.694656513555426e-06, + "loss": 3.3087, + "step": 2767360 + }, + { + "epoch": 0.01, + "learning_rate": 4.686270566044906e-06, + "loss": 3.3156, + "step": 2767872 + }, + { + "epoch": 0.01, + "learning_rate": 4.677884618534385e-06, + "loss": 3.3032, + "step": 2768384 + }, + { + "epoch": 0.01, + "learning_rate": 4.669515049827597e-06, + "loss": 3.3273, + "step": 2768896 + }, + { + "epoch": 0.01, + "learning_rate": 4.661129102317077e-06, + "loss": 3.3154, + "step": 2769408 + }, + { + "epoch": 0.01, + "learning_rate": 4.652743154806557e-06, + "loss": 3.3138, + "step": 2769920 + }, + { + "epoch": 0.01, + "learning_rate": 4.644357207296037e-06, + "loss": 3.3209, + "step": 2770432 + }, + { + "epoch": 0.01, + "learning_rate": 4.635987638589248e-06, + "loss": 3.3206, + "step": 2770944 + }, + { + "epoch": 0.01, + "learning_rate": 4.627601691078727e-06, + "loss": 3.3134, + "step": 2771456 + }, + { + "epoch": 0.01, + "learning_rate": 4.619215743568208e-06, + "loss": 3.3008, + "step": 2771968 + }, + { + "epoch": 0.01, + "learning_rate": 4.610829796057688e-06, + "loss": 3.2901, + "step": 2772480 + }, + { + "epoch": 0.01, + "learning_rate": 4.6024602273509e-06, + "loss": 3.332, + "step": 2772992 + }, + { + "epoch": 0.01, + "learning_rate": 4.594074279840379e-06, + "loss": 3.3116, + "step": 2773504 + }, + { + "epoch": 0.01, + "learning_rate": 4.585688332329859e-06, + "loss": 3.3127, + "step": 2774016 + }, + { + "epoch": 0.01, + "learning_rate": 4.577302384819339e-06, + "loss": 3.3092, + "step": 2774528 + }, + { + "epoch": 0.01, + "learning_rate": 4.5689328161125495e-06, + "loss": 3.3064, + "step": 2775040 + }, + { + "epoch": 0.01, + "learning_rate": 4.56054686860203e-06, + "loss": 3.3016, + "step": 2775552 + }, + { + "epoch": 0.01, + "learning_rate": 4.5521609210915094e-06, + "loss": 3.3137, + "step": 2776064 + }, + { + "epoch": 0.01, + "learning_rate": 4.543791352384721e-06, + "loss": 3.3166, + "step": 2776576 + }, + { + "epoch": 0.01, + "learning_rate": 4.535405404874201e-06, + "loss": 3.309, + "step": 2777088 + }, + { + "epoch": 0.01, + "learning_rate": 4.527019457363681e-06, + "loss": 3.3271, + "step": 2777600 + }, + { + "epoch": 0.01, + "learning_rate": 4.518633509853161e-06, + "loss": 3.3031, + "step": 2778112 + }, + { + "epoch": 0.01, + "learning_rate": 4.510263941146373e-06, + "loss": 3.3006, + "step": 2778624 + }, + { + "epoch": 0.01, + "learning_rate": 4.5018779936358525e-06, + "loss": 3.3226, + "step": 2779136 + }, + { + "epoch": 0.01, + "learning_rate": 4.493492046125332e-06, + "loss": 3.2958, + "step": 2779648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4851060986148125e-06, + "loss": 3.2982, + "step": 2780160 + }, + { + "epoch": 0.01, + "learning_rate": 4.476736529908023e-06, + "loss": 3.3214, + "step": 2780672 + }, + { + "epoch": 0.01, + "learning_rate": 4.468350582397503e-06, + "loss": 3.3216, + "step": 2781184 + }, + { + "epoch": 0.01, + "learning_rate": 4.459964634886983e-06, + "loss": 3.3014, + "step": 2781696 + }, + { + "epoch": 0.01, + "learning_rate": 4.451578687376463e-06, + "loss": 3.3126, + "step": 2782208 + }, + { + "epoch": 0.01, + "learning_rate": 4.443209118669675e-06, + "loss": 3.2954, + "step": 2782720 + }, + { + "epoch": 0.01, + "learning_rate": 4.434823171159155e-06, + "loss": 3.3136, + "step": 2783232 + }, + { + "epoch": 0.01, + "learning_rate": 4.426437223648635e-06, + "loss": 3.3084, + "step": 2783744 + }, + { + "epoch": 0.01, + "learning_rate": 4.418051276138114e-06, + "loss": 3.3149, + "step": 2784256 + }, + { + "epoch": 0.01, + "learning_rate": 4.409681707431325e-06, + "loss": 3.3098, + "step": 2784768 + }, + { + "epoch": 0.01, + "learning_rate": 4.401295759920805e-06, + "loss": 3.3183, + "step": 2785280 + }, + { + "epoch": 0.01, + "learning_rate": 4.392909812410285e-06, + "loss": 3.3262, + "step": 2785792 + }, + { + "epoch": 0.01, + "learning_rate": 4.384523864899765e-06, + "loss": 3.3062, + "step": 2786304 + }, + { + "epoch": 0.01, + "learning_rate": 4.376154296192977e-06, + "loss": 3.3146, + "step": 2786816 + }, + { + "epoch": 0.01, + "learning_rate": 4.367768348682456e-06, + "loss": 3.3179, + "step": 2787328 + }, + { + "epoch": 0.01, + "learning_rate": 4.359382401171937e-06, + "loss": 3.2992, + "step": 2787840 + }, + { + "epoch": 0.01, + "learning_rate": 4.350996453661416e-06, + "loss": 3.3246, + "step": 2788352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3426268849546276e-06, + "loss": 3.3233, + "step": 2788864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3342409374441075e-06, + "loss": 3.3188, + "step": 2789376 + }, + { + "epoch": 0.01, + "learning_rate": 4.3258549899335875e-06, + "loss": 3.3244, + "step": 2789888 + }, + { + "epoch": 0.01, + "learning_rate": 4.3174690424230674e-06, + "loss": 3.3076, + "step": 2790400 + }, + { + "epoch": 0.01, + "learning_rate": 4.309099473716278e-06, + "loss": 3.3051, + "step": 2790912 + }, + { + "epoch": 0.01, + "learning_rate": 4.300713526205759e-06, + "loss": 3.3111, + "step": 2791424 + }, + { + "epoch": 0.01, + "learning_rate": 4.292327578695238e-06, + "loss": 3.3218, + "step": 2791936 + }, + { + "epoch": 0.01, + "learning_rate": 4.283941631184719e-06, + "loss": 3.3172, + "step": 2792448 + }, + { + "epoch": 0.01, + "learning_rate": 4.27557206247793e-06, + "loss": 3.3112, + "step": 2792960 + }, + { + "epoch": 0.02, + "learning_rate": 4.26718611496741e-06, + "loss": 3.3088, + "step": 2793472 + }, + { + "epoch": 0.02, + "learning_rate": 4.25880016745689e-06, + "loss": 3.3213, + "step": 2793984 + }, + { + "epoch": 0.02, + "learning_rate": 4.25041421994637e-06, + "loss": 3.3044, + "step": 2794496 + }, + { + "epoch": 0.02, + "learning_rate": 4.242044651239581e-06, + "loss": 3.3033, + "step": 2795008 + }, + { + "epoch": 0.02, + "learning_rate": 4.23365870372906e-06, + "loss": 3.3141, + "step": 2795520 + }, + { + "epoch": 0.02, + "learning_rate": 4.225272756218541e-06, + "loss": 3.3251, + "step": 2796032 + }, + { + "epoch": 0.02, + "learning_rate": 4.21688680870802e-06, + "loss": 3.3182, + "step": 2796544 + }, + { + "epoch": 0.02, + "learning_rate": 4.208517240001232e-06, + "loss": 3.3007, + "step": 2797056 + }, + { + "epoch": 0.02, + "learning_rate": 4.200131292490712e-06, + "loss": 3.31, + "step": 2797568 + }, + { + "epoch": 0.02, + "learning_rate": 4.191745344980191e-06, + "loss": 3.3142, + "step": 2798080 + }, + { + "epoch": 0.02, + "learning_rate": 4.183359397469672e-06, + "loss": 3.3171, + "step": 2798592 + }, + { + "epoch": 0.02, + "learning_rate": 4.1749898287628825e-06, + "loss": 3.3097, + "step": 2799104 + }, + { + "epoch": 0.02, + "learning_rate": 4.1666038812523625e-06, + "loss": 3.313, + "step": 2799616 + }, + { + "epoch": 0.02, + "learning_rate": 4.1582179337418425e-06, + "loss": 3.2989, + "step": 2800128 + }, + { + "epoch": 0.02, + "learning_rate": 4.149831986231323e-06, + "loss": 3.3095, + "step": 2800640 + }, + { + "epoch": 0.02, + "learning_rate": 4.141462417524534e-06, + "loss": 3.3046, + "step": 2801152 + }, + { + "epoch": 0.02, + "learning_rate": 4.133076470014014e-06, + "loss": 3.313, + "step": 2801664 + }, + { + "epoch": 0.02, + "learning_rate": 4.124690522503494e-06, + "loss": 3.2976, + "step": 2802176 + }, + { + "epoch": 0.02, + "learning_rate": 4.116304574992973e-06, + "loss": 3.3249, + "step": 2802688 + }, + { + "epoch": 0.02, + "learning_rate": 4.107935006286185e-06, + "loss": 3.3039, + "step": 2803200 + }, + { + "epoch": 0.02, + "learning_rate": 4.099549058775665e-06, + "loss": 3.312, + "step": 2803712 + }, + { + "epoch": 0.02, + "learning_rate": 4.091163111265145e-06, + "loss": 3.3032, + "step": 2804224 + }, + { + "epoch": 0.02, + "learning_rate": 4.082777163754625e-06, + "loss": 3.3081, + "step": 2804736 + }, + { + "epoch": 0.02, + "learning_rate": 4.074407595047836e-06, + "loss": 3.3086, + "step": 2805248 + }, + { + "epoch": 0.02, + "learning_rate": 4.066021647537316e-06, + "loss": 3.311, + "step": 2805760 + }, + { + "epoch": 0.02, + "learning_rate": 4.057635700026796e-06, + "loss": 3.3125, + "step": 2806272 + }, + { + "epoch": 0.02, + "learning_rate": 4.049249752516276e-06, + "loss": 3.3192, + "step": 2806784 + }, + { + "epoch": 0.02, + "learning_rate": 4.040880183809488e-06, + "loss": 3.3094, + "step": 2807296 + }, + { + "epoch": 0.02, + "learning_rate": 4.032494236298967e-06, + "loss": 3.3116, + "step": 2807808 + }, + { + "epoch": 0.02, + "learning_rate": 4.024108288788447e-06, + "loss": 3.3133, + "step": 2808320 + }, + { + "epoch": 0.02, + "learning_rate": 4.015722341277927e-06, + "loss": 3.3186, + "step": 2808832 + }, + { + "epoch": 0.02, + "learning_rate": 4.0073527725711375e-06, + "loss": 3.2944, + "step": 2809344 + }, + { + "epoch": 0.02, + "learning_rate": 3.998966825060618e-06, + "loss": 3.3183, + "step": 2809856 + }, + { + "epoch": 0.02, + "learning_rate": 3.990580877550098e-06, + "loss": 3.3073, + "step": 2810368 + }, + { + "epoch": 0.02, + "learning_rate": 3.982194930039578e-06, + "loss": 3.3164, + "step": 2810880 + }, + { + "epoch": 0.02, + "learning_rate": 3.973825361332789e-06, + "loss": 3.308, + "step": 2811392 + }, + { + "epoch": 0.02, + "learning_rate": 3.96543941382227e-06, + "loss": 3.3118, + "step": 2811904 + }, + { + "epoch": 0.02, + "learning_rate": 3.957053466311749e-06, + "loss": 3.3002, + "step": 2812416 + }, + { + "epoch": 0.02, + "learning_rate": 3.948683897604961e-06, + "loss": 3.3052, + "step": 2812928 + }, + { + "epoch": 0.02, + "learning_rate": 3.9402979500944405e-06, + "loss": 3.3133, + "step": 2813440 + }, + { + "epoch": 0.02, + "learning_rate": 3.93191200258392e-06, + "loss": 3.3101, + "step": 2813952 + }, + { + "epoch": 0.02, + "learning_rate": 3.9235260550734005e-06, + "loss": 3.3169, + "step": 2814464 + }, + { + "epoch": 0.02, + "learning_rate": 3.915156486366611e-06, + "loss": 3.3209, + "step": 2814976 + }, + { + "epoch": 0.02, + "learning_rate": 3.906770538856091e-06, + "loss": 3.3003, + "step": 2815488 + }, + { + "epoch": 0.02, + "learning_rate": 3.898384591345571e-06, + "loss": 3.315, + "step": 2816000 + }, + { + "epoch": 0.02, + "learning_rate": 3.889998643835051e-06, + "loss": 3.318, + "step": 2816512 + }, + { + "epoch": 0.02, + "learning_rate": 3.881629075128263e-06, + "loss": 3.316, + "step": 2817024 + }, + { + "epoch": 0.02, + "learning_rate": 3.873243127617743e-06, + "loss": 3.312, + "step": 2817536 + }, + { + "epoch": 0.02, + "learning_rate": 3.864857180107223e-06, + "loss": 3.3155, + "step": 2818048 + }, + { + "epoch": 0.02, + "learning_rate": 3.856471232596702e-06, + "loss": 3.3077, + "step": 2818560 + }, + { + "epoch": 0.02, + "learning_rate": 3.848101663889913e-06, + "loss": 3.3216, + "step": 2819072 + }, + { + "epoch": 0.02, + "learning_rate": 3.839715716379393e-06, + "loss": 3.3043, + "step": 2819584 + }, + { + "epoch": 0.02, + "learning_rate": 3.831329768868873e-06, + "loss": 3.3157, + "step": 2820096 + }, + { + "epoch": 0.02, + "learning_rate": 3.822943821358353e-06, + "loss": 3.3078, + "step": 2820608 + }, + { + "epoch": 0.02, + "learning_rate": 3.814574252651565e-06, + "loss": 3.3064, + "step": 2821120 + }, + { + "epoch": 0.02, + "learning_rate": 3.8061883051410444e-06, + "loss": 3.3197, + "step": 2821632 + }, + { + "epoch": 0.02, + "learning_rate": 3.797802357630525e-06, + "loss": 3.3119, + "step": 2822144 + }, + { + "epoch": 0.02, + "learning_rate": 3.7894164101200044e-06, + "loss": 3.3093, + "step": 2822656 + }, + { + "epoch": 0.02, + "learning_rate": 3.781046841413216e-06, + "loss": 3.2964, + "step": 2823168 + }, + { + "epoch": 0.02, + "learning_rate": 3.7726608939026955e-06, + "loss": 3.3042, + "step": 2823680 + }, + { + "epoch": 0.03, + "eval_loss": 3.8638782501220703, + "eval_runtime": 304.7274, + "eval_samples_per_second": 1252.237, + "eval_steps_per_second": 39.133, + "step": 2823840 + }, + { + "epoch": 1.0, + "learning_rate": 3.7642749463921755e-06, + "loss": 3.2995, + "step": 2824192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7558889988816554e-06, + "loss": 3.3094, + "step": 2824704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7475194301748666e-06, + "loss": 3.3195, + "step": 2825216 + }, + { + "epoch": 1.0, + "learning_rate": 3.739133482664347e-06, + "loss": 3.3147, + "step": 2825728 + }, + { + "epoch": 1.0, + "learning_rate": 3.7307475351538266e-06, + "loss": 3.3262, + "step": 2826240 + }, + { + "epoch": 1.0, + "learning_rate": 3.722361587643307e-06, + "loss": 3.3067, + "step": 2826752 + }, + { + "epoch": 1.0, + "learning_rate": 3.7139920189365177e-06, + "loss": 3.3074, + "step": 2827264 + }, + { + "epoch": 1.0, + "learning_rate": 3.705606071425998e-06, + "loss": 3.3056, + "step": 2827776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6972201239154776e-06, + "loss": 3.3071, + "step": 2828288 + }, + { + "epoch": 1.0, + "learning_rate": 3.688834176404957e-06, + "loss": 3.3156, + "step": 2828800 + }, + { + "epoch": 1.0, + "learning_rate": 3.680464607698169e-06, + "loss": 3.315, + "step": 2829312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6720786601876488e-06, + "loss": 3.3141, + "step": 2829824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6637090914808604e-06, + "loss": 3.3094, + "step": 2830336 + }, + { + "epoch": 1.0, + "learning_rate": 3.65532314397034e-06, + "loss": 3.3, + "step": 2830848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6469371964598203e-06, + "loss": 3.301, + "step": 2831360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6385512489493e-06, + "loss": 3.3019, + "step": 2831872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6301653014387802e-06, + "loss": 3.3126, + "step": 2832384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6217793539282598e-06, + "loss": 3.3052, + "step": 2832896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6133934064177393e-06, + "loss": 3.3121, + "step": 2833408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6050074589072197e-06, + "loss": 3.3274, + "step": 2833920 + }, + { + "epoch": 1.0, + "learning_rate": 3.5966378902004305e-06, + "loss": 3.3161, + "step": 2834432 + }, + { + "epoch": 1.0, + "learning_rate": 3.588268321493642e-06, + "loss": 3.3039, + "step": 2834944 + }, + { + "epoch": 1.0, + "learning_rate": 3.579882373983122e-06, + "loss": 3.3092, + "step": 2835456 + }, + { + "epoch": 1.0, + "learning_rate": 3.5714964264726024e-06, + "loss": 3.3104, + "step": 2835968 + }, + { + "epoch": 1.0, + "learning_rate": 3.563110478962082e-06, + "loss": 3.3026, + "step": 2836480 + }, + { + "epoch": 1.0, + "learning_rate": 3.5547245314515615e-06, + "loss": 3.3148, + "step": 2836992 + }, + { + "epoch": 1.0, + "learning_rate": 3.546338583941042e-06, + "loss": 3.3091, + "step": 2837504 + }, + { + "epoch": 1.0, + "learning_rate": 3.5379526364305214e-06, + "loss": 3.3058, + "step": 2838016 + }, + { + "epoch": 1.0, + "learning_rate": 3.5295666889200018e-06, + "loss": 3.3014, + "step": 2838528 + }, + { + "epoch": 1.0, + "learning_rate": 3.5211971202132126e-06, + "loss": 3.2998, + "step": 2839040 + }, + { + "epoch": 1.01, + "learning_rate": 3.512811172702693e-06, + "loss": 3.3091, + "step": 2839552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5044252251921725e-06, + "loss": 3.3105, + "step": 2840064 + }, + { + "epoch": 1.01, + "learning_rate": 3.4960392776816524e-06, + "loss": 3.3181, + "step": 2840576 + }, + { + "epoch": 1.01, + "learning_rate": 3.487669708974864e-06, + "loss": 3.3102, + "step": 2841088 + }, + { + "epoch": 1.01, + "learning_rate": 3.4792837614643436e-06, + "loss": 3.2984, + "step": 2841600 + }, + { + "epoch": 1.01, + "learning_rate": 3.470897813953824e-06, + "loss": 3.3138, + "step": 2842112 + }, + { + "epoch": 1.01, + "learning_rate": 3.4625118664433035e-06, + "loss": 3.3096, + "step": 2842624 + }, + { + "epoch": 1.01, + "learning_rate": 3.454142297736515e-06, + "loss": 3.2919, + "step": 2843136 + }, + { + "epoch": 1.01, + "learning_rate": 3.4457563502259947e-06, + "loss": 3.307, + "step": 2843648 + }, + { + "epoch": 1.01, + "learning_rate": 3.437370402715475e-06, + "loss": 3.3042, + "step": 2844160 + }, + { + "epoch": 1.01, + "learning_rate": 3.4289844552049546e-06, + "loss": 3.2995, + "step": 2844672 + }, + { + "epoch": 1.01, + "learning_rate": 3.4206148864981662e-06, + "loss": 3.3169, + "step": 2845184 + }, + { + "epoch": 1.01, + "learning_rate": 3.4122289389876458e-06, + "loss": 3.3075, + "step": 2845696 + }, + { + "epoch": 1.01, + "learning_rate": 3.4038429914771257e-06, + "loss": 3.3043, + "step": 2846208 + }, + { + "epoch": 1.01, + "learning_rate": 3.3954570439666057e-06, + "loss": 3.3097, + "step": 2846720 + }, + { + "epoch": 1.01, + "learning_rate": 3.387087475259817e-06, + "loss": 3.3103, + "step": 2847232 + }, + { + "epoch": 1.01, + "learning_rate": 3.3787015277492973e-06, + "loss": 3.308, + "step": 2847744 + }, + { + "epoch": 1.01, + "learning_rate": 3.370315580238777e-06, + "loss": 3.2944, + "step": 2848256 + }, + { + "epoch": 1.01, + "learning_rate": 3.361929632728257e-06, + "loss": 3.2804, + "step": 2848768 + }, + { + "epoch": 1.01, + "learning_rate": 3.353560064021468e-06, + "loss": 3.3249, + "step": 2849280 + }, + { + "epoch": 1.01, + "learning_rate": 3.3451741165109484e-06, + "loss": 3.3027, + "step": 2849792 + }, + { + "epoch": 1.01, + "learning_rate": 3.336788169000428e-06, + "loss": 3.3083, + "step": 2850304 + }, + { + "epoch": 1.01, + "learning_rate": 3.3284022214899074e-06, + "loss": 3.2965, + "step": 2850816 + }, + { + "epoch": 1.01, + "learning_rate": 3.320032652783119e-06, + "loss": 3.299, + "step": 2851328 + }, + { + "epoch": 1.01, + "learning_rate": 3.311646705272599e-06, + "loss": 3.2968, + "step": 2851840 + }, + { + "epoch": 1.01, + "learning_rate": 3.303260757762079e-06, + "loss": 3.2997, + "step": 2852352 + }, + { + "epoch": 1.01, + "learning_rate": 3.294874810251559e-06, + "loss": 3.3091, + "step": 2852864 + }, + { + "epoch": 1.01, + "learning_rate": 3.2865052415447706e-06, + "loss": 3.2982, + "step": 2853376 + }, + { + "epoch": 1.01, + "learning_rate": 3.27811929403425e-06, + "loss": 3.3187, + "step": 2853888 + }, + { + "epoch": 1.01, + "learning_rate": 3.2697333465237305e-06, + "loss": 3.2986, + "step": 2854400 + }, + { + "epoch": 1.01, + "learning_rate": 3.2613637778169413e-06, + "loss": 3.2891, + "step": 2854912 + }, + { + "epoch": 1.01, + "learning_rate": 3.2529778303064217e-06, + "loss": 3.3157, + "step": 2855424 + }, + { + "epoch": 1.01, + "learning_rate": 3.244591882795901e-06, + "loss": 3.292, + "step": 2855936 + }, + { + "epoch": 1.01, + "learning_rate": 3.2362059352853807e-06, + "loss": 3.2872, + "step": 2856448 + }, + { + "epoch": 1.01, + "learning_rate": 3.2278363665785924e-06, + "loss": 3.3134, + "step": 2856960 + }, + { + "epoch": 1.01, + "learning_rate": 3.2194504190680723e-06, + "loss": 3.3093, + "step": 2857472 + }, + { + "epoch": 1.01, + "learning_rate": 3.2110644715575523e-06, + "loss": 3.2971, + "step": 2857984 + }, + { + "epoch": 1.01, + "learning_rate": 3.2026785240470322e-06, + "loss": 3.3052, + "step": 2858496 + }, + { + "epoch": 1.01, + "learning_rate": 3.194308955340244e-06, + "loss": 3.2885, + "step": 2859008 + }, + { + "epoch": 1.01, + "learning_rate": 3.1859230078297234e-06, + "loss": 3.3057, + "step": 2859520 + }, + { + "epoch": 1.01, + "learning_rate": 3.1775370603192038e-06, + "loss": 3.2974, + "step": 2860032 + }, + { + "epoch": 1.01, + "learning_rate": 3.1691511128086833e-06, + "loss": 3.3099, + "step": 2860544 + }, + { + "epoch": 1.01, + "learning_rate": 3.160781544101895e-06, + "loss": 3.3013, + "step": 2861056 + }, + { + "epoch": 1.01, + "learning_rate": 3.1523955965913745e-06, + "loss": 3.3103, + "step": 2861568 + }, + { + "epoch": 1.01, + "learning_rate": 3.144009649080854e-06, + "loss": 3.3172, + "step": 2862080 + }, + { + "epoch": 1.01, + "learning_rate": 3.1356237015703344e-06, + "loss": 3.2976, + "step": 2862592 + }, + { + "epoch": 1.01, + "learning_rate": 3.1272541328635456e-06, + "loss": 3.3079, + "step": 2863104 + }, + { + "epoch": 1.01, + "learning_rate": 3.118868185353026e-06, + "loss": 3.3089, + "step": 2863616 + }, + { + "epoch": 1.01, + "learning_rate": 3.1104822378425055e-06, + "loss": 3.2913, + "step": 2864128 + }, + { + "epoch": 1.01, + "learning_rate": 3.1020962903319855e-06, + "loss": 3.3144, + "step": 2864640 + }, + { + "epoch": 1.01, + "learning_rate": 3.0937267216251967e-06, + "loss": 3.3175, + "step": 2865152 + }, + { + "epoch": 1.01, + "learning_rate": 3.0853407741146766e-06, + "loss": 3.3101, + "step": 2865664 + }, + { + "epoch": 1.01, + "learning_rate": 3.0769548266041566e-06, + "loss": 3.3219, + "step": 2866176 + }, + { + "epoch": 1.01, + "learning_rate": 3.0685688790936365e-06, + "loss": 3.2954, + "step": 2866688 + }, + { + "epoch": 1.01, + "learning_rate": 3.0601993103868478e-06, + "loss": 3.2951, + "step": 2867200 + }, + { + "epoch": 1.01, + "learning_rate": 3.0518133628763277e-06, + "loss": 3.3055, + "step": 2867712 + }, + { + "epoch": 1.01, + "learning_rate": 3.0434274153658072e-06, + "loss": 3.3111, + "step": 2868224 + }, + { + "epoch": 1.01, + "learning_rate": 3.0350414678552876e-06, + "loss": 3.3119, + "step": 2868736 + }, + { + "epoch": 1.01, + "learning_rate": 3.026671899148499e-06, + "loss": 3.303, + "step": 2869248 + }, + { + "epoch": 1.02, + "learning_rate": 3.018285951637979e-06, + "loss": 3.3012, + "step": 2869760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0099000041274588e-06, + "loss": 3.3133, + "step": 2870272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0015140566169387e-06, + "loss": 3.2971, + "step": 2870784 + }, + { + "epoch": 1.02, + "learning_rate": 2.99314448791015e-06, + "loss": 3.2967, + "step": 2871296 + }, + { + "epoch": 1.02, + "learning_rate": 2.98475854039963e-06, + "loss": 3.3071, + "step": 2871808 + }, + { + "epoch": 1.02, + "learning_rate": 2.97637259288911e-06, + "loss": 3.3154, + "step": 2872320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9679866453785894e-06, + "loss": 3.3102, + "step": 2872832 + }, + { + "epoch": 1.02, + "learning_rate": 2.959617076671801e-06, + "loss": 3.2893, + "step": 2873344 + }, + { + "epoch": 1.02, + "learning_rate": 2.951231129161281e-06, + "loss": 3.3038, + "step": 2873856 + }, + { + "epoch": 1.02, + "learning_rate": 2.942845181650761e-06, + "loss": 3.306, + "step": 2874368 + }, + { + "epoch": 1.02, + "learning_rate": 2.934459234140241e-06, + "loss": 3.3062, + "step": 2874880 + }, + { + "epoch": 1.02, + "learning_rate": 2.926089665433452e-06, + "loss": 3.3046, + "step": 2875392 + }, + { + "epoch": 1.02, + "learning_rate": 2.917703717922932e-06, + "loss": 3.3056, + "step": 2875904 + }, + { + "epoch": 1.02, + "learning_rate": 2.909317770412412e-06, + "loss": 3.2899, + "step": 2876416 + }, + { + "epoch": 1.02, + "learning_rate": 2.900931822901892e-06, + "loss": 3.3007, + "step": 2876928 + }, + { + "epoch": 1.02, + "learning_rate": 2.892562254195103e-06, + "loss": 3.3003, + "step": 2877440 + }, + { + "epoch": 1.02, + "learning_rate": 2.884176306684583e-06, + "loss": 3.3033, + "step": 2877952 + }, + { + "epoch": 1.02, + "learning_rate": 2.8757903591740627e-06, + "loss": 3.2877, + "step": 2878464 + }, + { + "epoch": 1.02, + "learning_rate": 2.8674044116635426e-06, + "loss": 3.3164, + "step": 2878976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8590348429567542e-06, + "loss": 3.2953, + "step": 2879488 + }, + { + "epoch": 1.02, + "learning_rate": 2.850648895446234e-06, + "loss": 3.3001, + "step": 2880000 + }, + { + "epoch": 1.02, + "learning_rate": 2.842262947935714e-06, + "loss": 3.2934, + "step": 2880512 + }, + { + "epoch": 1.02, + "learning_rate": 2.8338933792289254e-06, + "loss": 3.3066, + "step": 2881024 + }, + { + "epoch": 1.02, + "learning_rate": 2.8255074317184053e-06, + "loss": 3.2974, + "step": 2881536 + }, + { + "epoch": 1.02, + "learning_rate": 2.8171214842078853e-06, + "loss": 3.2984, + "step": 2882048 + }, + { + "epoch": 1.02, + "learning_rate": 2.8087355366973652e-06, + "loss": 3.3047, + "step": 2882560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8003659679905765e-06, + "loss": 3.3132, + "step": 2883072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919800204800564e-06, + "loss": 3.2995, + "step": 2883584 + }, + { + "epoch": 1.02, + "learning_rate": 2.783594072969536e-06, + "loss": 3.3097, + "step": 2884096 + }, + { + "epoch": 1.02, + "learning_rate": 2.775208125459016e-06, + "loss": 3.3003, + "step": 2884608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7668385567522275e-06, + "loss": 3.3111, + "step": 2885120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7584526092417075e-06, + "loss": 3.2921, + "step": 2885632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7500666617311874e-06, + "loss": 3.3106, + "step": 2886144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7416807142206674e-06, + "loss": 3.2976, + "step": 2886656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7333111455138786e-06, + "loss": 3.309, + "step": 2887168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7249251980033586e-06, + "loss": 3.3024, + "step": 2887680 + }, + { + "epoch": 1.02, + "learning_rate": 2.716539250492838e-06, + "loss": 3.3039, + "step": 2888192 + }, + { + "epoch": 1.02, + "learning_rate": 2.708153302982318e-06, + "loss": 3.2909, + "step": 2888704 + }, + { + "epoch": 1.02, + "learning_rate": 2.6997837342755293e-06, + "loss": 3.3005, + "step": 2889216 + }, + { + "epoch": 1.02, + "learning_rate": 2.6913977867650092e-06, + "loss": 3.3045, + "step": 2889728 + }, + { + "epoch": 1.02, + "learning_rate": 2.683011839254489e-06, + "loss": 3.3051, + "step": 2890240 + }, + { + "epoch": 1.02, + "learning_rate": 2.674625891743969e-06, + "loss": 3.3032, + "step": 2890752 + }, + { + "epoch": 1.02, + "learning_rate": 2.6662563230371808e-06, + "loss": 3.3123, + "step": 2891264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6578703755266607e-06, + "loss": 3.296, + "step": 2891776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6494844280161407e-06, + "loss": 3.3065, + "step": 2892288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6410984805056202e-06, + "loss": 3.3091, + "step": 2892800 + }, + { + "epoch": 1.02, + "learning_rate": 2.632728911798832e-06, + "loss": 3.3097, + "step": 2893312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6243429642883114e-06, + "loss": 3.3006, + "step": 2893824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6159570167777913e-06, + "loss": 3.306, + "step": 2894336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6075710692672713e-06, + "loss": 3.2991, + "step": 2894848 + }, + { + "epoch": 1.02, + "learning_rate": 2.5992015005604825e-06, + "loss": 3.3182, + "step": 2895360 + }, + { + "epoch": 1.02, + "learning_rate": 2.5908155530499625e-06, + "loss": 3.2972, + "step": 2895872 + }, + { + "epoch": 1.02, + "learning_rate": 2.582429605539443e-06, + "loss": 3.3075, + "step": 2896384 + }, + { + "epoch": 1.02, + "learning_rate": 2.574043658028923e-06, + "loss": 3.2996, + "step": 2896896 + }, + { + "epoch": 1.02, + "learning_rate": 2.565674089322134e-06, + "loss": 3.3011, + "step": 2897408 + }, + { + "epoch": 1.02, + "learning_rate": 2.557288141811614e-06, + "loss": 3.3073, + "step": 2897920 + }, + { + "epoch": 1.02, + "learning_rate": 2.5489021943010935e-06, + "loss": 3.3024, + "step": 2898432 + }, + { + "epoch": 1.02, + "learning_rate": 2.5405162467905735e-06, + "loss": 3.3049, + "step": 2898944 + }, + { + "epoch": 1.02, + "learning_rate": 2.5321466780837847e-06, + "loss": 3.2863, + "step": 2899456 + }, + { + "epoch": 1.02, + "learning_rate": 2.5237607305732646e-06, + "loss": 3.3007, + "step": 2899968 + }, + { + "epoch": 1.03, + "eval_loss": 3.863445281982422, + "eval_runtime": 305.4916, + "eval_samples_per_second": 1249.105, + "eval_steps_per_second": 39.035, + "step": 2900160 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 2.0100977395458785e+18, + "trial_name": null, + "trial_params": null +}