diff --git "a/checkpoint-2289600/trainer_state.json" "b/checkpoint-2289600/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2289600/trainer_state.json" @@ -0,0 +1,27091 @@ +{ + "best_metric": 3.893625020980835, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj2/transformer/3/checkpoints/checkpoint-839520", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2289600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9425, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8235, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1923, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9802, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8087, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6995, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6031, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5332, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4518, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3997, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3471, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3074, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2692, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2153, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.185, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1314, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1178, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0824, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0454, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0235, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0234, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.9771, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9628, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9371, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9122, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9025, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.866, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8641, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8469, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8185, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8118, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.791, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7909, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.771, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7534, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7477, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7503, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7123, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7062, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6993, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.681, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6729, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6742, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6624, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6481, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.64, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6314, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6307, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.5992, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5989, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6077, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5975, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5835, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5653, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5726, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5519, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5722, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5388, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.554, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5335, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5215, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5237, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5101, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.5071, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4992, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5077, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4833, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4775, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4668, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4667, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4852, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4741, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.456, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4545, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4597, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4533, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4367, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4405, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4319, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4307, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4236, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4205, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4253, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4167, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3954, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.4055, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4056, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.3978, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3917, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.381, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3884, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3767, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.383, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3707, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3669, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3853, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.35, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3483, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3588, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3572, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3602, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3459, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3383, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3371, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3412, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3235, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3204, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3342, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3223, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3157, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3089, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3077, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3191, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3047, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3036, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3067, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3061, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.295, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.3005, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.2977, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.2948, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.2796, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.2909, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2832, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2891, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2712, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2812, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2699, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.274, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2535, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2799, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2797, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2619, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2512, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2724, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.2591, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2606, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.253, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.2599, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.2511, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.25, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2348, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2483, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2441, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2354, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2537, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.231, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2377, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2412, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2304, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.243399143218994, + "eval_runtime": 303.9974, + "eval_samples_per_second": 1255.244, + "eval_steps_per_second": 39.227, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2151, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2193, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2303, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2201, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2215, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2072, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2094, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.2039, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2139, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2005, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2069, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2107, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1944, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1915, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1804, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1889, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1852, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.1812, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1806, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.208, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1785, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.181, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1853, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1786, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1717, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1633, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1702, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1678, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.155, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1669, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1566, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.168, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1627, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1477, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1617, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1706, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1416, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.153, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.1477, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.1382, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.1427, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.151, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.1481, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.138, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1455, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1349, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.142, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1218, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1245, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1396, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.1387, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1265, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1184, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1304, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.1109, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.1368, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.119, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.1335, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825637806996108e-05, + "loss": 4.1199, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.1107, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823960617494004e-05, + "loss": 4.1142, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823122022742952e-05, + "loss": 4.1167, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.1057, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821446471121221e-05, + "loss": 4.1041, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.1183, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.1043, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.095, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.0932, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.0952, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.1135, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.111, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147409888735514e-05, + "loss": 4.095, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139023941224994e-05, + "loss": 4.0995, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.1037, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.0995, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811388247749716e-05, + "loss": 4.0918, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810549652998664e-05, + "loss": 4.0995, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.0915, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.0967, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.0885, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807196911874829e-05, + "loss": 4.092, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.0937, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0937, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.075, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803844170750995e-05, + "loss": 4.0877, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803005575999943e-05, + "loss": 4.0848, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802166981248891e-05, + "loss": 4.0859, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.0827, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800489791746787e-05, + "loss": 4.071, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996528348761076e-05, + "loss": 4.0825, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988142401250556e-05, + "loss": 4.0747, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979756453740036e-05, + "loss": 4.0839, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971370506229516e-05, + "loss": 4.0689, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963000937522725e-05, + "loss": 4.0738, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795461499001221e-05, + "loss": 4.0846, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794622904250169e-05, + "loss": 4.0717, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793784309499117e-05, + "loss": 4.0523, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792947352628438e-05, + "loss": 4.0703, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792108757877386e-05, + "loss": 4.0735, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791270163126334e-05, + "loss": 4.0742, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.0678, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789594611504603e-05, + "loss": 4.0617, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788756016753551e-05, + "loss": 4.0574, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787917422002499e-05, + "loss": 4.0692, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787078827251447e-05, + "loss": 4.0492, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862435082611415e-05, + "loss": 4.0544, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854049135100895e-05, + "loss": 4.0633, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845663187590375e-05, + "loss": 4.0632, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837277240079855e-05, + "loss": 4.0414, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828891292569335e-05, + "loss": 4.0544, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820505345058815e-05, + "loss": 4.0442, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812119397548295e-05, + "loss": 4.0633, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.049, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795363881330984e-05, + "loss": 4.0424, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786977933820464e-05, + "loss": 4.0616, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778591986309944e-05, + "loss": 4.0546, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777022241760315e-05, + "loss": 4.0466, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776183647009263e-05, + "loss": 4.0528, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775345052258212e-05, + "loss": 4.0479, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.77450645750716e-05, + "loss": 4.0508, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773667862756108e-05, + "loss": 4.0316, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772829268005055e-05, + "loss": 4.0534, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771990673254003e-05, + "loss": 4.04, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771152078502951e-05, + "loss": 4.0489, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770315121632272e-05, + "loss": 4.0382, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.76947652688122e-05, + "loss": 4.0442, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768637932130168e-05, + "loss": 4.0363, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767799337379116e-05, + "loss": 4.0391, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766962380508437e-05, + "loss": 4.0218, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766123785757386e-05, + "loss": 4.052, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765285191006334e-05, + "loss": 4.0462, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764446596255282e-05, + "loss": 4.0358, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636096393846026e-05, + "loss": 4.0259, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.7627710446335506e-05, + "loss": 4.0448, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.7619324498824986e-05, + "loss": 4.0404, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610938551314466e-05, + "loss": 4.0336, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.029, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.039, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.032, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577411140076115e-05, + "loss": 4.0418, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569041571369324e-05, + "loss": 4.019, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756065562385881e-05, + "loss": 4.0345, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755226967634829e-05, + "loss": 4.0294, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0217, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.043, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0223, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751874226510994e-05, + "loss": 4.0278, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751035631759942e-05, + "loss": 4.0277, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.75019703700889e-05, + "loss": 4.0273, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.07391881942749, + "eval_runtime": 304.0061, + "eval_samples_per_second": 1255.208, + "eval_steps_per_second": 39.226, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749358442257838e-05, + "loss": 4.0097, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748519847506786e-05, + "loss": 4.0189, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747681252755734e-05, + "loss": 4.0279, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746842658004682e-05, + "loss": 4.0208, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.74600406325363e-05, + "loss": 4.0267, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745165468502578e-05, + "loss": 4.0046, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744326873751526e-05, + "loss": 4.0124, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743488279000474e-05, + "loss": 4.0077, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742649684249422e-05, + "loss": 4.0179, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.74181108949837e-05, + "loss": 4.0077, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740972494747318e-05, + "loss": 4.0154, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740135537876639e-05, + "loss": 4.0173, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392985810059604e-05, + "loss": 4.0032, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384599862549084e-05, + "loss": 4.0071, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737621391503856e-05, + "loss": 3.99, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736782796752804e-05, + "loss": 4.0005, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735944202001752e-05, + "loss": 4.001, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7351056072507e-05, + "loss": 3.9969, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734267012499648e-05, + "loss": 3.9968, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733430055628969e-05, + "loss": 4.0228, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732591460877917e-05, + "loss": 3.9991, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731752866126865e-05, + "loss": 3.9984, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730914271375813e-05, + "loss": 4.006, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730077314505134e-05, + "loss": 4.0005, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729238719754082e-05, + "loss": 3.9922, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.72840012500303e-05, + "loss": 3.9873, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727561530251978e-05, + "loss": 3.998, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726724573381299e-05, + "loss": 3.9886, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725885978630247e-05, + "loss": 3.9825, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725047383879195e-05, + "loss": 3.9941, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724208789128143e-05, + "loss": 3.9847, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233718322574647e-05, + "loss": 3.9957, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225332375064127e-05, + "loss": 3.9915, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216946427553606e-05, + "loss": 3.9816, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208560480043086e-05, + "loss": 3.9927, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 4.0046, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191804963825775e-05, + "loss": 3.9735, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183419016315255e-05, + "loss": 3.9889, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175033068804735e-05, + "loss": 3.9769, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166663500097945e-05, + "loss": 3.9778, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158277552587424e-05, + "loss": 3.9775, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149891605076904e-05, + "loss": 3.9916, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141505657566384e-05, + "loss": 3.9864, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71331360888596e-05, + "loss": 3.9781, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712475014134908e-05, + "loss": 3.983, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711636419383856e-05, + "loss": 3.9739, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710797824632804e-05, + "loss": 3.9849, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709960867762125e-05, + "loss": 3.9655, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9684, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708283678260021e-05, + "loss": 3.9813, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707445083508969e-05, + "loss": 3.9787, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9724, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9673, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9761, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040939802655074e-05, + "loss": 3.9564, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9811, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9711, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9807, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9744, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.9612, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.9638, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9702, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697386860137464e-05, + "loss": 3.9561, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.9582, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9692, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9609, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9485, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693195524262577e-05, + "loss": 3.951, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692356929511526e-05, + "loss": 3.9519, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9721, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906830157701677e-05, + "loss": 3.9661, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9553, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.9627, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.9588, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.9628, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864900420149076e-05, + "loss": 3.9518, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9628, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848144903931765e-05, + "loss": 3.9563, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9564, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.9508, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9573, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9572, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9569, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.944, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9499, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9473, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9506, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676431818643403e-05, + "loss": 3.9539, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9366, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674754629141298e-05, + "loss": 3.9499, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673916034390246e-05, + "loss": 3.9456, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9541, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.9344, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671401888017464e-05, + "loss": 3.9444, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.9554, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9412, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.9242, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668049146893629e-05, + "loss": 3.9413, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.9457, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9465, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.944, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9316, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663856173138369e-05, + "loss": 3.9337, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301921626769e-05, + "loss": 3.9435, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621806215166383e-05, + "loss": 3.9256, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613420267655863e-05, + "loss": 3.9317, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9393, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.9399, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658827880392803e-05, + "loss": 3.9166, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657989285641751e-05, + "loss": 3.9318, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657152328771072e-05, + "loss": 3.9236, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9377, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655475139268968e-05, + "loss": 3.9326, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9241, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653797949766864e-05, + "loss": 3.9405, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652959355015812e-05, + "loss": 3.9364, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652122398145134e-05, + "loss": 3.9257, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651283803394082e-05, + "loss": 3.933, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.65044520864303e-05, + "loss": 3.9326, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649606613891978e-05, + "loss": 3.9296, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648768019140926e-05, + "loss": 3.9167, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.9313, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.9247, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462538727681426e-05, + "loss": 3.9307, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.9273, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445766832660386e-05, + "loss": 3.9306, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437380885149866e-05, + "loss": 3.9167, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.9213, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420625368932555e-05, + "loss": 3.9104, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412239421422035e-05, + "loss": 3.9375, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.9278, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395467526401e-05, + "loss": 3.926, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.9138, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378695631379955e-05, + "loss": 3.9308, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9293, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636194011516265e-05, + "loss": 3.918, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9178, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9265, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.9198, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632841270392429e-05, + "loss": 3.9307, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632002675641377e-05, + "loss": 3.9118, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.9234, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9179, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9117, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628649934517543e-05, + "loss": 3.9342, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627811339766491e-05, + "loss": 3.911, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626972745015439e-05, + "loss": 3.9201, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9199, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9168, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9984824657440186, + "eval_runtime": 301.9446, + "eval_samples_per_second": 1263.778, + "eval_steps_per_second": 39.494, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624458598642656e-05, + "loss": 3.9098, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623620003891604e-05, + "loss": 3.911, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622781409140552e-05, + "loss": 3.9206, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9151, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9213, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.9002, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.9089, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.8984, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.9194, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.902, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616074289012509e-05, + "loss": 3.9126, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9138, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614400375271151e-05, + "loss": 3.9052, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613561780520099e-05, + "loss": 3.8957, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612723185769047e-05, + "loss": 3.8955, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.8926, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.9027, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.8956, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.8958, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.9183, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.901, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.8972, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.9061, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9018, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043388761389006e-05, + "loss": 3.895, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603500281387848e-05, + "loss": 3.8876, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602661686636796e-05, + "loss": 3.903, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.8838, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009861350150655e-05, + "loss": 3.8878, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600147540264013e-05, + "loss": 3.8917, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993089455129615e-05, + "loss": 3.8875, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598471988642283e-05, + "loss": 3.9014, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.8932, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967947991401784e-05, + "loss": 3.8841, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959562043891264e-05, + "loss": 3.8968, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595119247518448e-05, + "loss": 3.906, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594280652767395e-05, + "loss": 3.8821, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593442058016343e-05, + "loss": 3.8938, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592603463265291e-05, + "loss": 3.8759, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591764868514239e-05, + "loss": 3.8923, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590926273763187e-05, + "loss": 3.8776, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590087679012135e-05, + "loss": 3.9006, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589250722141457e-05, + "loss": 3.8902, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588412127390405e-05, + "loss": 3.8842, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587573532639353e-05, + "loss": 3.8921, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586734937888301e-05, + "loss": 3.8818, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585896343137249e-05, + "loss": 3.8913, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.58505938626657e-05, + "loss": 3.876, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584220791515518e-05, + "loss": 3.8732, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583382196764466e-05, + "loss": 3.8909, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582543602013414e-05, + "loss": 3.885, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581705007262362e-05, + "loss": 3.8855, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580868050391683e-05, + "loss": 3.8731, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580029455640631e-05, + "loss": 3.8824, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579190860889579e-05, + "loss": 3.8666, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783522661385267e-05, + "loss": 3.8883, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577513671387475e-05, + "loss": 3.8794, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576675076636423e-05, + "loss": 3.8931, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575836481885371e-05, + "loss": 3.8846, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574999525014692e-05, + "loss": 3.8747, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.57416093026364e-05, + "loss": 3.8706, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573322335512588e-05, + "loss": 3.8805, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572483740761536e-05, + "loss": 3.8686, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571646783890857e-05, + "loss": 3.8693, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570808189139805e-05, + "loss": 3.8785, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569969594388753e-05, + "loss": 3.8764, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569130999637701e-05, + "loss": 3.8599, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568294042767022e-05, + "loss": 3.8627, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567455448015971e-05, + "loss": 3.8617, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566616853264919e-05, + "loss": 3.8875, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565778258513867e-05, + "loss": 3.8774, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649413016431876e-05, + "loss": 3.8702, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641027068921356e-05, + "loss": 3.8749, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632641121410836e-05, + "loss": 3.8698, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624255173900316e-05, + "loss": 3.8818, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615885605193525e-05, + "loss": 3.8614, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607499657683005e-05, + "loss": 3.882, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599113710172485e-05, + "loss": 3.8668, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590727762661965e-05, + "loss": 3.8714, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582341815151445e-05, + "loss": 3.8709, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5573972246444654e-05, + "loss": 3.8682, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556558629893414e-05, + "loss": 3.8775, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557200351423614e-05, + "loss": 3.8687, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548814403913094e-05, + "loss": 3.859, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554044483520631e-05, + "loss": 3.8678, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553205888769579e-05, + "loss": 3.8602, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552367294018526e-05, + "loss": 3.8738, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551528699267474e-05, + "loss": 3.8687, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550690104516422e-05, + "loss": 3.8534, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549853147645744e-05, + "loss": 3.869, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549014552894691e-05, + "loss": 3.8612, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548175958143639e-05, + "loss": 3.8694, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547337363392588e-05, + "loss": 3.855, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546498768641536e-05, + "loss": 3.8629, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545661811770857e-05, + "loss": 3.873, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544823217019805e-05, + "loss": 3.8582, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543984622268753e-05, + "loss": 3.8465, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543146027517701e-05, + "loss": 3.8608, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423090706470216e-05, + "loss": 3.859, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414704758959696e-05, + "loss": 3.8708, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406318811449176e-05, + "loss": 3.8614, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397932863938656e-05, + "loss": 3.8536, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389546916428136e-05, + "loss": 3.8537, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381177347721345e-05, + "loss": 3.8649, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537279140021083e-05, + "loss": 3.8442, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536440545270031e-05, + "loss": 3.8552, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535601950518979e-05, + "loss": 3.8584, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347649936483e-05, + "loss": 3.8616, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533926398897248e-05, + "loss": 3.8342, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533087804146196e-05, + "loss": 3.8534, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532249209395144e-05, + "loss": 3.8518, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531410614644092e-05, + "loss": 3.8505, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530573657773413e-05, + "loss": 3.856, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529735063022361e-05, + "loss": 3.8442, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528896468271309e-05, + "loss": 3.8653, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528057873520257e-05, + "loss": 3.8551, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272209166495786e-05, + "loss": 3.8496, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263823218985266e-05, + "loss": 3.8554, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255437271474746e-05, + "loss": 3.8544, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247051323964226e-05, + "loss": 3.8542, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238681755257435e-05, + "loss": 3.8346, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230295807746915e-05, + "loss": 3.8585, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221909860236395e-05, + "loss": 3.8459, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213523912725875e-05, + "loss": 3.8533, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205154344019084e-05, + "loss": 3.8504, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196768396508564e-05, + "loss": 3.8575, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188382448998044e-05, + "loss": 3.8456, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8406, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171610553977003e-05, + "loss": 3.8373, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163224606466483e-05, + "loss": 3.8584, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.51548550377597e-05, + "loss": 3.8526, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514646909024918e-05, + "loss": 3.8519, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513808314273866e-05, + "loss": 3.8405, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512969719522814e-05, + "loss": 3.8548, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512132762652135e-05, + "loss": 3.8525, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511294167901083e-05, + "loss": 3.8423, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510455573150031e-05, + "loss": 3.8436, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509616978398979e-05, + "loss": 3.8515, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087800215283e-05, + "loss": 3.85, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507941426777248e-05, + "loss": 3.8545, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507102832026196e-05, + "loss": 3.8374, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506264237275144e-05, + "loss": 3.8507, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505427280404465e-05, + "loss": 3.8419, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504588685653413e-05, + "loss": 3.8413, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503751728782734e-05, + "loss": 3.8561, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502913134031682e-05, + "loss": 3.8427, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.50207453928063e-05, + "loss": 3.8475, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501235944529578e-05, + "loss": 3.8416, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500397349778526e-05, + "loss": 3.8483, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.95876407623291, + "eval_runtime": 301.8238, + "eval_samples_per_second": 1264.284, + "eval_steps_per_second": 39.51, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499558755027474e-05, + "loss": 3.8307, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987201602764215e-05, + "loss": 3.8409, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978815655253695e-05, + "loss": 3.8487, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970429707743175e-05, + "loss": 3.8414, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496204376023266e-05, + "loss": 3.8517, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495365781272214e-05, + "loss": 3.8271, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494527186521162e-05, + "loss": 3.8389, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49368859177011e-05, + "loss": 3.8284, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492851634899431e-05, + "loss": 3.8454, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492013040148379e-05, + "loss": 3.8379, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491174445397327e-05, + "loss": 3.8384, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490335850646275e-05, + "loss": 3.8372, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489498893775596e-05, + "loss": 3.8335, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488660299024544e-05, + "loss": 3.826, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487821704273492e-05, + "loss": 3.8286, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698310952244e-05, + "loss": 3.8191, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486144514771388e-05, + "loss": 3.8342, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485305920020336e-05, + "loss": 3.8253, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484467325269284e-05, + "loss": 3.8245, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836287305182326e-05, + "loss": 3.8538, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827917736475535e-05, + "loss": 3.8285, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819531788965015e-05, + "loss": 3.833, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811145841454495e-05, + "loss": 3.8358, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802759893943975e-05, + "loss": 3.8305, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794390325237184e-05, + "loss": 3.8262, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.4786004377726664e-05, + "loss": 3.8206, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.4777618430216144e-05, + "loss": 3.8346, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.4769232482705624e-05, + "loss": 3.8132, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476086291399883e-05, + "loss": 3.8223, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475247696648831e-05, + "loss": 3.8218, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474409101897779e-05, + "loss": 3.8234, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473570507146728e-05, + "loss": 3.8342, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472733550276049e-05, + "loss": 3.826, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471894955524997e-05, + "loss": 3.8221, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471056360773945e-05, + "loss": 3.8291, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470217766022893e-05, + "loss": 3.8356, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469380809152214e-05, + "loss": 3.8175, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468542214401162e-05, + "loss": 3.8287, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.46770361965011e-05, + "loss": 3.8109, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466865024899058e-05, + "loss": 3.8244, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466028068028379e-05, + "loss": 3.8088, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465189473277327e-05, + "loss": 3.8361, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464350878526275e-05, + "loss": 3.824, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463512283775223e-05, + "loss": 3.819, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462675326904544e-05, + "loss": 3.8252, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461836732153492e-05, + "loss": 3.8175, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.46099813740244e-05, + "loss": 3.8246, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460159542651388e-05, + "loss": 3.812, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459322585780709e-05, + "loss": 3.8076, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458483991029657e-05, + "loss": 3.8279, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457645396278605e-05, + "loss": 3.819, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568068015275525e-05, + "loss": 3.8205, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455969844656874e-05, + "loss": 3.8109, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455131249905822e-05, + "loss": 3.8171, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.45429265515477e-05, + "loss": 3.8062, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453454060403718e-05, + "loss": 3.822, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526171035330396e-05, + "loss": 3.8159, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8301, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509399140309356e-05, + "loss": 3.8207, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450101319279883e-05, + "loss": 3.8088, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492643624092045e-05, + "loss": 3.8105, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8158, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.8042, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446748578156048e-05, + "loss": 3.8108, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445909983404996e-05, + "loss": 3.8128, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.8153, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.797, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433958370322134e-05, + "loss": 3.802, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425572422811614e-05, + "loss": 3.8003, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441720285410482e-05, + "loss": 3.8203, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088169065943e-05, + "loss": 3.8119, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440043095908378e-05, + "loss": 3.8095, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439204501157326e-05, + "loss": 3.812, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438367544286647e-05, + "loss": 3.8083, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437528949535595e-05, + "loss": 3.8248, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436690354784543e-05, + "loss": 3.7985, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435851760033491e-05, + "loss": 3.8172, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435014803162813e-05, + "loss": 3.8087, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434176208411761e-05, + "loss": 3.8091, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433337613660709e-05, + "loss": 3.8111, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432499018909657e-05, + "loss": 3.8088, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431660424158605e-05, + "loss": 3.8137, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308234672879257e-05, + "loss": 3.8094, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299848725368737e-05, + "loss": 3.7946, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291462777858217e-05, + "loss": 3.8082, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283076830347696e-05, + "loss": 3.8007, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274707261640906e-05, + "loss": 3.8106, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266321314130386e-05, + "loss": 3.8063, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257935366619865e-05, + "loss": 3.7942, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249549419109345e-05, + "loss": 3.8091, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424117985040256e-05, + "loss": 3.8022, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423279390289204e-05, + "loss": 3.8116, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422440795538152e-05, + "loss": 3.7914, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216022007871e-05, + "loss": 3.8079, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420763606036048e-05, + "loss": 3.8198, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419926649165369e-05, + "loss": 3.7969, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419088054414317e-05, + "loss": 3.7833, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418249459663265e-05, + "loss": 3.7998, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417410864912213e-05, + "loss": 3.8047, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416573908041534e-05, + "loss": 3.8078, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415735313290482e-05, + "loss": 3.8064, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41489671853943e-05, + "loss": 3.7962, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414058123788378e-05, + "loss": 3.7964, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132211669176995e-05, + "loss": 3.8048, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123825721666475e-05, + "loss": 3.7864, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115439774155955e-05, + "loss": 3.7954, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107053826645435e-05, + "loss": 3.7995, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098684257938644e-05, + "loss": 3.8039, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090298310428124e-05, + "loss": 3.7766, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081912362917604e-05, + "loss": 3.7958, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073526415407084e-05, + "loss": 3.7919, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065140467896564e-05, + "loss": 3.7968, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405677089918977e-05, + "loss": 3.794, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404838495167925e-05, + "loss": 3.7898, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403999900416873e-05, + "loss": 3.8031, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403161305665822e-05, + "loss": 3.8022, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402325986675516e-05, + "loss": 3.7912, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401487391924464e-05, + "loss": 3.8006, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400648797173412e-05, + "loss": 3.795, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39981020242236e-05, + "loss": 3.7997, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398971607671308e-05, + "loss": 3.7813, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398133012920256e-05, + "loss": 3.8033, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397294418169204e-05, + "loss": 3.7836, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396455823418152e-05, + "loss": 3.7969, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956188665474726e-05, + "loss": 3.7886, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947802717964206e-05, + "loss": 3.8045, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939416770453686e-05, + "loss": 3.7922, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393103082294317e-05, + "loss": 3.7867, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392266125423638e-05, + "loss": 3.7787, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391427530672586e-05, + "loss": 3.8065, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390588935921534e-05, + "loss": 3.7906, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389750341170482e-05, + "loss": 3.7981, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388913384299803e-05, + "loss": 3.7835, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388074789548751e-05, + "loss": 3.7991, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387236194797699e-05, + "loss": 3.7994, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386397600046647e-05, + "loss": 3.7871, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385560643175968e-05, + "loss": 3.786, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384722048424916e-05, + "loss": 3.7957, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383883453673864e-05, + "loss": 3.7954, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383044858922813e-05, + "loss": 3.8006, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822079020521336e-05, + "loss": 3.7801, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813693073010816e-05, + "loss": 3.7946, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805307125500296e-05, + "loss": 3.7883, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796921177989776e-05, + "loss": 3.7911, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788551609282985e-05, + "loss": 3.7994, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780165661772465e-05, + "loss": 3.7842, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771779714261945e-05, + "loss": 3.7989, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763393766751425e-05, + "loss": 3.7841, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.37550078192409e-05, + "loss": 3.799, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.9349238872528076, + "eval_runtime": 302.9482, + "eval_samples_per_second": 1259.592, + "eval_steps_per_second": 39.363, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.374662187173038e-05, + "loss": 3.7748, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738235924219865e-05, + "loss": 3.7879, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.3729849976709345e-05, + "loss": 3.7905, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721464029198824e-05, + "loss": 3.7877, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3713078081688304e-05, + "loss": 3.7971, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704692134177784e-05, + "loss": 3.7768, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.3696306186667264e-05, + "loss": 3.7823, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.3687920239156744e-05, + "loss": 3.7741, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.3679550670449953e-05, + "loss": 3.7924, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367116472293943e-05, + "loss": 3.7891, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366277877542891e-05, + "loss": 3.7828, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365439282791839e-05, + "loss": 3.7874, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364603963801533e-05, + "loss": 3.7777, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363765369050482e-05, + "loss": 3.7743, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.36292677429943e-05, + "loss": 3.7765, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362088179548378e-05, + "loss": 3.7655, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361249584797326e-05, + "loss": 3.7778, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360410990046274e-05, + "loss": 3.7712, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359572395295222e-05, + "loss": 3.7722, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.35873380054417e-05, + "loss": 3.8069, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357896843673491e-05, + "loss": 3.7724, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357058248922439e-05, + "loss": 3.7813, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356219654171387e-05, + "loss": 3.7831, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355381059420335e-05, + "loss": 3.7796, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545441025496556e-05, + "loss": 3.7711, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.3537055077986036e-05, + "loss": 3.7724, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.3528669130475516e-05, + "loss": 3.7807, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.3520283182964996e-05, + "loss": 3.7615, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351191361425821e-05, + "loss": 3.7693, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350352766674769e-05, + "loss": 3.7695, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349514171923717e-05, + "loss": 3.7756, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348675577172665e-05, + "loss": 3.7789, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347838620301986e-05, + "loss": 3.7764, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347000025550934e-05, + "loss": 3.772, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346161430799882e-05, + "loss": 3.7788, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.34532283604883e-05, + "loss": 3.7809, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344485879178151e-05, + "loss": 3.767, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343647284427099e-05, + "loss": 3.7798, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342808689676047e-05, + "loss": 3.7588, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341970094924995e-05, + "loss": 3.779, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411331380543165e-05, + "loss": 3.7545, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402945433032645e-05, + "loss": 3.7906, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394559485522125e-05, + "loss": 3.7744, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3386173538011605e-05, + "loss": 3.7706, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377803969304814e-05, + "loss": 3.775, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369418021794294e-05, + "loss": 3.7723, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361032074283774e-05, + "loss": 3.7709, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352646126773254e-05, + "loss": 3.7594, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334427655806646e-05, + "loss": 3.7518, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333589061055594e-05, + "loss": 3.7819, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332750466304542e-05, + "loss": 3.7702, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.33191187155349e-05, + "loss": 3.7769, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331074914682812e-05, + "loss": 3.7615, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7679, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329399363061081e-05, + "loss": 3.7564, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328560768310029e-05, + "loss": 3.7713, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327722173558977e-05, + "loss": 3.7636, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.7777, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.775, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325206389305821e-05, + "loss": 3.7571, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324367794554768e-05, + "loss": 3.7625, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323529199803716e-05, + "loss": 3.7704, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322692242933038e-05, + "loss": 3.7563, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321853648181986e-05, + "loss": 3.7609, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321015053430934e-05, + "loss": 3.7669, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320176458679882e-05, + "loss": 3.7656, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319339501809203e-05, + "loss": 3.7501, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185009070581506e-05, + "loss": 3.7565, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.3176623123070986e-05, + "loss": 3.7509, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.3168237175560466e-05, + "loss": 3.7714, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.7635, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151481659343155e-05, + "loss": 3.7605, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3143095711832635e-05, + "loss": 3.7688, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.3134709764322115e-05, + "loss": 3.7572, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.7768, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311795424810481e-05, + "loss": 3.7525, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310956830059429e-05, + "loss": 3.7677, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310118235308377e-05, + "loss": 3.762, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7604, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308442683686646e-05, + "loss": 3.765, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307604088935594e-05, + "loss": 3.7625, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306765494184542e-05, + "loss": 3.7638, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305928537313863e-05, + "loss": 3.7647, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305089942562811e-05, + "loss": 3.7477, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304251347811759e-05, + "loss": 3.7633, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303412753060707e-05, + "loss": 3.7548, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025757961900284e-05, + "loss": 3.7649, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3017372014389764e-05, + "loss": 3.7563, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3008986066879244e-05, + "loss": 3.7486, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.3000600119368724e-05, + "loss": 3.7597, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299223055066193e-05, + "loss": 3.7604, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298384460315141e-05, + "loss": 3.759, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297545865564089e-05, + "loss": 3.7476, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296707270813037e-05, + "loss": 3.7604, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295870313942358e-05, + "loss": 3.7693, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295031719191306e-05, + "loss": 3.7537, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294193124440254e-05, + "loss": 3.734, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293354529689202e-05, + "loss": 3.7545, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292517572818524e-05, + "loss": 3.7579, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291678978067472e-05, + "loss": 3.7584, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.29084038331642e-05, + "loss": 3.7606, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290001788565368e-05, + "loss": 3.7515, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289164831694689e-05, + "loss": 3.75, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288326236943637e-05, + "loss": 3.7584, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287487642192585e-05, + "loss": 3.7401, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286649047441533e-05, + "loss": 3.7506, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2858120905708536e-05, + "loss": 3.7502, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.2849734958198016e-05, + "loss": 3.7597, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.2841365389491225e-05, + "loss": 3.7354, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283297944198071e-05, + "loss": 3.7455, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282459349447019e-05, + "loss": 3.7511, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281620754695967e-05, + "loss": 3.7497, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280782159944915e-05, + "loss": 3.7519, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279943565193863e-05, + "loss": 3.7428, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279104970442811e-05, + "loss": 3.7588, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278266375691759e-05, + "loss": 3.757, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277431056701453e-05, + "loss": 3.7448, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276592461950401e-05, + "loss": 3.7583, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275753867199349e-05, + "loss": 3.7454, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274915272448297e-05, + "loss": 3.7551, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274076677697245e-05, + "loss": 3.742, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273238082946193e-05, + "loss": 3.7521, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272399488195141e-05, + "loss": 3.7395, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715608934440896e-05, + "loss": 3.7502, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2707239365734105e-05, + "loss": 3.7475, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.2698853418223585e-05, + "loss": 3.7549, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690467470713065e-05, + "loss": 3.7458, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.2682081523202545e-05, + "loss": 3.7464, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.2673711954495754e-05, + "loss": 3.7319, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.2665326006985234e-05, + "loss": 3.7644, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.2656940059474714e-05, + "loss": 3.7443, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.2648554111964194e-05, + "loss": 3.7546, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.26401845432574e-05, + "loss": 3.7381, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263179859574688e-05, + "loss": 3.7544, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262341264823636e-05, + "loss": 3.7526, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261502670072584e-05, + "loss": 3.7429, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260665713201906e-05, + "loss": 3.745, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259827118450854e-05, + "loss": 3.7501, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258988523699802e-05, + "loss": 3.7503, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.25814992894875e-05, + "loss": 3.7633, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257312972078071e-05, + "loss": 3.7327, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256474377327019e-05, + "loss": 3.7543, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255635782575967e-05, + "loss": 3.7411, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254797187824915e-05, + "loss": 3.7521, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253960230954236e-05, + "loss": 3.7521, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253121636203184e-05, + "loss": 3.7386, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252283041452132e-05, + "loss": 3.7567, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.25144444670108e-05, + "loss": 3.7432, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250605851950028e-05, + "loss": 3.75, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.9179980754852295, + "eval_runtime": 304.4208, + "eval_samples_per_second": 1253.499, + "eval_steps_per_second": 39.173, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.249767257198976e-05, + "loss": 3.7383, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.2489286624479237e-05, + "loss": 3.7395, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.2480900676968716e-05, + "loss": 3.7507, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.247253110826193e-05, + "loss": 3.7473, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.246414516075141e-05, + "loss": 3.7508, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.2455759213240885e-05, + "loss": 3.7395, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.2447373265730365e-05, + "loss": 3.7336, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.243900369702358e-05, + "loss": 3.7354, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.2430617749513054e-05, + "loss": 3.7456, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.2422231802002534e-05, + "loss": 3.7488, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.241384585449202e-05, + "loss": 3.7397, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.240547628578524e-05, + "loss": 3.7456, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.2397106717078446e-05, + "loss": 3.7316, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.2388720769567926e-05, + "loss": 3.735, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.2380334822057406e-05, + "loss": 3.7355, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.2371948874546886e-05, + "loss": 3.7217, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7374, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.2355193358329575e-05, + "loss": 3.7247, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.2346807410819055e-05, + "loss": 3.7301, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233842146330853e-05, + "loss": 3.7655, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.233003551579801e-05, + "loss": 3.7334, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.232164956828749e-05, + "loss": 3.7357, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.2313263620776975e-05, + "loss": 3.7387, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.2304877673266455e-05, + "loss": 3.7445, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.2296508104559664e-05, + "loss": 3.7225, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.2288122157049144e-05, + "loss": 3.7331, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.2279736209538624e-05, + "loss": 3.7366, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.227136664083183e-05, + "loss": 3.7246, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.226298069332131e-05, + "loss": 3.727, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.225459474581079e-05, + "loss": 3.726, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.224620879830027e-05, + "loss": 3.7355, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.223783922959348e-05, + "loss": 3.739, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.222945328208296e-05, + "loss": 3.7331, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.222106733457244e-05, + "loss": 3.7323, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.221268138706193e-05, + "loss": 3.7342, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.220431181835514e-05, + "loss": 3.74, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.219592587084462e-05, + "loss": 3.7237, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.21875399233341e-05, + "loss": 3.7429, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.217915397582358e-05, + "loss": 3.7149, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.2170784407116787e-05, + "loss": 3.7347, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.2162398459606267e-05, + "loss": 3.7161, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.2154012512095746e-05, + "loss": 3.7476, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.2145626564585226e-05, + "loss": 3.7302, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.2137256995878436e-05, + "loss": 3.7339, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.2128871048367915e-05, + "loss": 3.7336, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.2120485100857395e-05, + "loss": 3.7328, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.211209915334688e-05, + "loss": 3.7324, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.210372958464009e-05, + "loss": 3.7237, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.209534363712957e-05, + "loss": 3.7078, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.208695768961905e-05, + "loss": 3.7438, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.207858812091226e-05, + "loss": 3.7259, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.207020217340174e-05, + "loss": 3.7392, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.206181622589122e-05, + "loss": 3.7195, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.20534302783807e-05, + "loss": 3.7253, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.204506070967391e-05, + "loss": 3.7132, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.203667476216339e-05, + "loss": 3.7327, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.202828881465287e-05, + "loss": 3.7288, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.201990286714235e-05, + "loss": 3.7349, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.2011516919631836e-05, + "loss": 3.7346, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.2003130972121316e-05, + "loss": 3.7169, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.1994745024610796e-05, + "loss": 3.7207, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.1986359077100276e-05, + "loss": 3.7349, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.1977989508393485e-05, + "loss": 3.7136, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.1969603560882965e-05, + "loss": 3.7205, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.1961217613372445e-05, + "loss": 3.7248, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.1952831665861925e-05, + "loss": 3.73, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.1944462097155134e-05, + "loss": 3.7081, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.1936076149644614e-05, + "loss": 3.7145, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.1927690202134094e-05, + "loss": 3.7158, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.1919304254623574e-05, + "loss": 3.7224, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.191093468591679e-05, + "loss": 3.7284, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.190254873840627e-05, + "loss": 3.7231, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.189416279089575e-05, + "loss": 3.7263, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188577684338523e-05, + "loss": 3.7176, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.187740727467844e-05, + "loss": 3.7408, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186902132716792e-05, + "loss": 3.7136, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.18606353796574e-05, + "loss": 3.7288, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.185224943214688e-05, + "loss": 3.7225, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.184387986344009e-05, + "loss": 3.7203, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.183549391592957e-05, + "loss": 3.7277, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.182710796841905e-05, + "loss": 3.7251, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.181872202090853e-05, + "loss": 3.7207, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.181035245220174e-05, + "loss": 3.7274, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.180196650469122e-05, + "loss": 3.7103, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.17935805571807e-05, + "loss": 3.7213, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.178521098847391e-05, + "loss": 3.7201, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.177682504096339e-05, + "loss": 3.7272, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.176843909345287e-05, + "loss": 3.7166, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.176005314594235e-05, + "loss": 3.7113, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.175168357723556e-05, + "loss": 3.7191, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.174329762972504e-05, + "loss": 3.7236, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.173491168221452e-05, + "loss": 3.7207, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.1726525734704e-05, + "loss": 3.7084, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.171815616599721e-05, + "loss": 3.7225, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.170977021848669e-05, + "loss": 3.7301, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.170138427097618e-05, + "loss": 3.7184, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.169299832346566e-05, + "loss": 3.6988, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.1684628754758866e-05, + "loss": 3.7167, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.1676242807248346e-05, + "loss": 3.7132, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.1667856859737826e-05, + "loss": 3.7245, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.1659470912227306e-05, + "loss": 3.7251, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.1651101343520515e-05, + "loss": 3.712, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.1642715396009995e-05, + "loss": 3.7099, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.1634329448499475e-05, + "loss": 3.7224, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.1625943500988955e-05, + "loss": 3.7041, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.1617573932282164e-05, + "loss": 3.7158, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.1609187984771644e-05, + "loss": 3.7076, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160080203726113e-05, + "loss": 3.725, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.159241608975061e-05, + "loss": 3.6986, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.1584030142240084e-05, + "loss": 3.7052, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.1575644194729564e-05, + "loss": 3.7102, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.1567258247219044e-05, + "loss": 3.7182, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.1558872299708523e-05, + "loss": 3.7089, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.155050273100173e-05, + "loss": 3.7056, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.154211678349121e-05, + "loss": 3.7182, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.153373083598069e-05, + "loss": 3.718, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.152536126727391e-05, + "loss": 3.709, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.151697531976338e-05, + "loss": 3.7242, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.150858937225287e-05, + "loss": 3.7094, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.150020342474235e-05, + "loss": 3.7138, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.149181747723183e-05, + "loss": 3.7088, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.148343152972131e-05, + "loss": 3.7129, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.147504558221079e-05, + "loss": 3.703, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.146665963470027e-05, + "loss": 3.7119, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.145829006599348e-05, + "loss": 3.7168, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.144990411848296e-05, + "loss": 3.7148, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.144151817097244e-05, + "loss": 3.708, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.143313222346192e-05, + "loss": 3.7105, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.1424762654755126e-05, + "loss": 3.696, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.1416376707244606e-05, + "loss": 3.7248, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.1407990759734086e-05, + "loss": 3.7083, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.1399604812223566e-05, + "loss": 3.7174, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.139123524351678e-05, + "loss": 3.7037, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.138284929600626e-05, + "loss": 3.7228, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.137446334849574e-05, + "loss": 3.7107, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.136607740098522e-05, + "loss": 3.7066, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.135770783227843e-05, + "loss": 3.7084, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.134932188476791e-05, + "loss": 3.7135, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.134093593725739e-05, + "loss": 3.7119, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.133254998974687e-05, + "loss": 3.7253, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.132418042104008e-05, + "loss": 3.6978, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.131581085233329e-05, + "loss": 3.7162, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.1307424904822776e-05, + "loss": 3.7058, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.1299038957312256e-05, + "loss": 3.7155, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.1290653009801736e-05, + "loss": 3.7118, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.1282267062291215e-05, + "loss": 3.7055, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.1273881114780695e-05, + "loss": 3.7174, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.1265495167270175e-05, + "loss": 3.7072, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.1257109219759655e-05, + "loss": 3.7146, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 3.9083821773529053, + "eval_runtime": 305.2198, + "eval_samples_per_second": 1250.217, + "eval_steps_per_second": 39.07, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.1248739651052864e-05, + "loss": 3.7073, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240353703542344e-05, + "loss": 3.7011, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231967756031824e-05, + "loss": 3.7131, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1223581808521304e-05, + "loss": 3.7124, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215195861010784e-05, + "loss": 3.7195, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206809913500264e-05, + "loss": 3.6999, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1198423965989744e-05, + "loss": 3.6964, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.1190038018479224e-05, + "loss": 3.6972, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118166844977244e-05, + "loss": 3.7121, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117328250226192e-05, + "loss": 3.7133, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116489655475139e-05, + "loss": 3.6983, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115651060724087e-05, + "loss": 3.7099, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114815741733782e-05, + "loss": 3.7011, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.11397714698273e-05, + "loss": 3.697, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113138552231678e-05, + "loss": 3.6981, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112299957480626e-05, + "loss": 3.6926, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111463000609947e-05, + "loss": 3.6998, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110624405858895e-05, + "loss": 3.6942, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109785811107843e-05, + "loss": 3.6934, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108947216356791e-05, + "loss": 3.7261, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.1081086216057394e-05, + "loss": 3.703, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107270026854687e-05, + "loss": 3.6974, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106431432103635e-05, + "loss": 3.7016, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105592837352583e-05, + "loss": 3.7067, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104755880481904e-05, + "loss": 3.6897, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1039172857308516e-05, + "loss": 3.7018, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030786909797996e-05, + "loss": 3.7014, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1022400962287476e-05, + "loss": 3.6922, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1014031393580685e-05, + "loss": 3.6902, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005645446070165e-05, + "loss": 3.6921, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997259498559645e-05, + "loss": 3.7015, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098888992985286e-05, + "loss": 3.7052, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098050398234234e-05, + "loss": 3.6982, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097211803483182e-05, + "loss": 3.6968, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.09637320873213e-05, + "loss": 3.6995, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0955362518614516e-05, + "loss": 3.7036, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094697657110399e-05, + "loss": 3.6965, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093859062359347e-05, + "loss": 3.7025, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093020467608295e-05, + "loss": 3.6852, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092183510737616e-05, + "loss": 3.699, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091344915986564e-05, + "loss": 3.6843, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090506321235512e-05, + "loss": 3.7106, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.08966772648446e-05, + "loss": 3.6981, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0888307696137814e-05, + "loss": 3.6982, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.0879921748627294e-05, + "loss": 3.7017, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871535801116774e-05, + "loss": 3.6958, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0863149853606254e-05, + "loss": 3.6981, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085478028489946e-05, + "loss": 3.6897, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084639433738894e-05, + "loss": 3.6694, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083800838987842e-05, + "loss": 3.7117, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082963882117163e-05, + "loss": 3.6902, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082125287366111e-05, + "loss": 3.7063, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081286692615059e-05, + "loss": 3.6886, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080448097864007e-05, + "loss": 3.6909, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079611140993329e-05, + "loss": 3.6763, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078772546242277e-05, + "loss": 3.7, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077933951491225e-05, + "loss": 3.6952, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077095356740173e-05, + "loss": 3.6989, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076256761989121e-05, + "loss": 3.7044, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075418167238069e-05, + "loss": 3.6816, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074579572487017e-05, + "loss": 3.6884, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073740977735965e-05, + "loss": 3.701, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072904020865286e-05, + "loss": 3.684, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072065426114234e-05, + "loss": 3.6841, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071226831363182e-05, + "loss": 3.6918, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.07038823661213e-05, + "loss": 3.6943, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.0695512797414506e-05, + "loss": 3.6778, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068712684990399e-05, + "loss": 3.6832, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067874090239347e-05, + "loss": 3.6779, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067035495488295e-05, + "loss": 3.6906, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066198538617616e-05, + "loss": 3.694, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065359943866564e-05, + "loss": 3.6915, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064521349115512e-05, + "loss": 3.6889, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.06368275436446e-05, + "loss": 3.6881, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062845797493781e-05, + "loss": 3.7046, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.062007202742729e-05, + "loss": 3.6789, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061168607991677e-05, + "loss": 3.6986, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060330013240625e-05, + "loss": 3.6879, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059493056369946e-05, + "loss": 3.6836, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0586560994992675e-05, + "loss": 3.6976, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578175047482155e-05, + "loss": 3.6917, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569789099971635e-05, + "loss": 3.688, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0561403152461115e-05, + "loss": 3.6936, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.0553017204950595e-05, + "loss": 3.679, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0544631257440075e-05, + "loss": 3.6863, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.0536245309929555e-05, + "loss": 3.6855, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.0527875741222764e-05, + "loss": 3.6955, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0519489793712244e-05, + "loss": 3.6839, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0511103846201724e-05, + "loss": 3.684, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0502717898691204e-05, + "loss": 3.6812, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049434832998441e-05, + "loss": 3.6914, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048597876127763e-05, + "loss": 3.69, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047759281376711e-05, + "loss": 3.6766, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046920686625659e-05, + "loss": 3.6917, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046082091874607e-05, + "loss": 3.6962, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045243497123555e-05, + "loss": 3.6855, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044404902372503e-05, + "loss": 3.6663, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043566307621451e-05, + "loss": 3.685, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042727712870399e-05, + "loss": 3.6792, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.04189075599972e-05, + "loss": 3.6929, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041052161248668e-05, + "loss": 3.6913, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040213566497616e-05, + "loss": 3.6817, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039374971746564e-05, + "loss": 3.6807, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.0385380148758853e-05, + "loss": 3.6827, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.0376994201248333e-05, + "loss": 3.6776, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036862463254154e-05, + "loss": 3.682, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036023868503102e-05, + "loss": 3.6741, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.03518527375205e-05, + "loss": 3.6954, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034346679000998e-05, + "loss": 3.6662, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033508084249946e-05, + "loss": 3.6736, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032669489498894e-05, + "loss": 3.6782, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0318308947478415e-05, + "loss": 3.6881, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.0309922999967895e-05, + "loss": 3.6762, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030155343126111e-05, + "loss": 3.6773, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029316748375059e-05, + "loss": 3.6879, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028478153624007e-05, + "loss": 3.6886, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027639558872955e-05, + "loss": 3.6723, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026802602002277e-05, + "loss": 3.6905, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025964007251224e-05, + "loss": 3.6814, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025125412500172e-05, + "loss": 3.6807, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.02428681774912e-05, + "loss": 3.6786, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023448222998068e-05, + "loss": 3.6773, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022609628247016e-05, + "loss": 3.6747, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021771033495964e-05, + "loss": 3.683, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020934076625285e-05, + "loss": 3.6854, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020095481874233e-05, + "loss": 3.6813, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019256887123181e-05, + "loss": 3.6772, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018418292372129e-05, + "loss": 3.6788, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017579697621077e-05, + "loss": 3.6639, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167411028700256e-05, + "loss": 3.6964, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0159025081189736e-05, + "loss": 3.6763, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.0150639133679216e-05, + "loss": 3.6841, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.0142269564972425e-05, + "loss": 3.6712, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.0133883617461905e-05, + "loss": 3.6894, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0125497669951385e-05, + "loss": 3.6807, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.0117111722440865e-05, + "loss": 3.6758, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.0108742153734074e-05, + "loss": 3.6782, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0100356206223554e-05, + "loss": 3.6785, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091970258713034e-05, + "loss": 3.68, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.0083584311202513e-05, + "loss": 3.7011, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007521474249572e-05, + "loss": 3.6625, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006684517378894e-05, + "loss": 3.6884, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005845922627842e-05, + "loss": 3.6741, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.00500732787679e-05, + "loss": 3.683, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004168733125738e-05, + "loss": 3.6783, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003330138374686e-05, + "loss": 3.6797, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002491543623634e-05, + "loss": 3.6856, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001652948872582e-05, + "loss": 3.6778, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.00081435412153e-05, + "loss": 3.6816, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.9016835689544678, + "eval_runtime": 305.1503, + "eval_samples_per_second": 1250.502, + "eval_steps_per_second": 39.079, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.999977397250851e-05, + "loss": 3.6777, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999138802499799e-05, + "loss": 3.6708, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998300207748747e-05, + "loss": 3.6817, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997461612997695e-05, + "loss": 3.679, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996626294007389e-05, + "loss": 3.689, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995787699256337e-05, + "loss": 3.6692, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994949104505285e-05, + "loss": 3.6686, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.994110509754233e-05, + "loss": 3.6695, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.993271915003181e-05, + "loss": 3.6788, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992433320252129e-05, + "loss": 3.6831, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991594725501077e-05, + "loss": 3.6684, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990756130750025e-05, + "loss": 3.6776, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989919173879346e-05, + "loss": 3.6737, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989080579128294e-05, + "loss": 3.6654, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988241984377242e-05, + "loss": 3.6695, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.98740338962619e-05, + "loss": 3.659, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.986566432755512e-05, + "loss": 3.6686, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.9857278380044597e-05, + "loss": 3.662, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.9848892432534077e-05, + "loss": 3.664, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.984050648502355e-05, + "loss": 3.6933, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.983212053751303e-05, + "loss": 3.6753, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.982373459000251e-05, + "loss": 3.6694, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981534864249199e-05, + "loss": 3.6709, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.980696269498147e-05, + "loss": 3.6772, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.979859312627468e-05, + "loss": 3.6559, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.979020717876416e-05, + "loss": 3.6719, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.978182123125364e-05, + "loss": 3.6732, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.977343528374312e-05, + "loss": 3.6604, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.9765065715036334e-05, + "loss": 3.6579, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.9756679767525814e-05, + "loss": 3.6628, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.9748293820015294e-05, + "loss": 3.6695, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.9739924251308503e-05, + "loss": 3.6764, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973153830379798e-05, + "loss": 3.6682, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.972315235628746e-05, + "loss": 3.6695, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971476640877694e-05, + "loss": 3.6717, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970639684007015e-05, + "loss": 3.6721, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.969801089255963e-05, + "loss": 3.6672, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.968962494504911e-05, + "loss": 3.6717, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968123899753859e-05, + "loss": 3.6542, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967286942883181e-05, + "loss": 3.6697, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.966448348132129e-05, + "loss": 3.658, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.96561139126145e-05, + "loss": 3.6789, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964772796510398e-05, + "loss": 3.67, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.963934201759346e-05, + "loss": 3.6673, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963095607008294e-05, + "loss": 3.6738, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.962257012257242e-05, + "loss": 3.6665, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.96141841750619e-05, + "loss": 3.6729, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.960579822755138e-05, + "loss": 3.6616, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.959741228004086e-05, + "loss": 3.6353, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.9589042711334066e-05, + "loss": 3.6791, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.9580673142627275e-05, + "loss": 3.6616, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957228719511676e-05, + "loss": 3.679, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956390124760624e-05, + "loss": 3.6604, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955551530009572e-05, + "loss": 3.6596, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954714573138893e-05, + "loss": 3.6499, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953875978387841e-05, + "loss": 3.6662, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953037383636789e-05, + "loss": 3.6706, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952198788885737e-05, + "loss": 3.6678, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951360194134685e-05, + "loss": 3.6771, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950521599383633e-05, + "loss": 3.6574, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949683004632581e-05, + "loss": 3.6551, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948844409881529e-05, + "loss": 3.673, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.94800745301085e-05, + "loss": 3.6538, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947168858259798e-05, + "loss": 3.6561, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946330263508746e-05, + "loss": 3.6596, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945491668757694e-05, + "loss": 3.6677, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.9446547118870155e-05, + "loss": 3.651, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.9438161171359635e-05, + "loss": 3.6546, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.9429775223849115e-05, + "loss": 3.6503, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.9421389276338595e-05, + "loss": 3.6579, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.9413019707631804e-05, + "loss": 3.6671, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.9404633760121284e-05, + "loss": 3.6582, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.9396247812610764e-05, + "loss": 3.6629, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.938787824390397e-05, + "loss": 3.6588, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937949229639345e-05, + "loss": 3.6802, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937110634888293e-05, + "loss": 3.652, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936273678017615e-05, + "loss": 3.6681, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935435083266563e-05, + "loss": 3.6618, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934596488515511e-05, + "loss": 3.6557, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933757893764459e-05, + "loss": 3.6683, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932919299013407e-05, + "loss": 3.6653, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932082342142728e-05, + "loss": 3.6621, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.931243747391676e-05, + "loss": 3.6619, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930405152640624e-05, + "loss": 3.6552, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.929566557889572e-05, + "loss": 3.6546, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.92872796313852e-05, + "loss": 3.6596, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.927889368387468e-05, + "loss": 3.6666, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.927050773636415e-05, + "loss": 3.6539, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.926212178885363e-05, + "loss": 3.6545, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925375222014685e-05, + "loss": 3.6534, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.9245366272636333e-05, + "loss": 3.666, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923698032512581e-05, + "loss": 3.6592, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922859437761529e-05, + "loss": 3.6499, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.6626, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.9211838861397976e-05, + "loss": 3.6673, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.9203452913887456e-05, + "loss": 3.6594, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919508334518067e-05, + "loss": 3.6382, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918669739767015e-05, + "loss": 3.6545, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.9178311450159625e-05, + "loss": 3.65, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.9169925502649105e-05, + "loss": 3.664, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.9161539555138585e-05, + "loss": 3.6607, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.915315360762807e-05, + "loss": 3.6607, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.914476766011755e-05, + "loss": 3.6523, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.913638171260703e-05, + "loss": 3.6532, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912801214390024e-05, + "loss": 3.6492, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911964257519345e-05, + "loss": 3.654, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911125662768293e-05, + "loss": 3.6481, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910287068017241e-05, + "loss": 3.6653, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909448473266189e-05, + "loss": 3.6425, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908609878515137e-05, + "loss": 3.6426, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907771283764085e-05, + "loss": 3.6535, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906932689013033e-05, + "loss": 3.653, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.906094094261981e-05, + "loss": 3.654, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.9052571373913025e-05, + "loss": 3.6488, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.9044185426402505e-05, + "loss": 3.6585, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.9035799478891985e-05, + "loss": 3.6633, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.9027413531381465e-05, + "loss": 3.6449, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.9019043962674674e-05, + "loss": 3.659, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.9010658015164154e-05, + "loss": 3.6546, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.9002272067653634e-05, + "loss": 3.6543, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.8993886120143114e-05, + "loss": 3.6533, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898551655143632e-05, + "loss": 3.647, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.89771306039258e-05, + "loss": 3.6468, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896874465641528e-05, + "loss": 3.6537, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.896035870890476e-05, + "loss": 3.6582, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.895197276139424e-05, + "loss": 3.6533, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.894358681388372e-05, + "loss": 3.6518, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.89352008663732e-05, + "loss": 3.6497, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892683129766642e-05, + "loss": 3.6378, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.89184453501559e-05, + "loss": 3.6664, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.891005940264538e-05, + "loss": 3.6466, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890167345513486e-05, + "loss": 3.6629, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889328750762434e-05, + "loss": 3.6419, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.888491793891755e-05, + "loss": 3.6619, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.887653199140703e-05, + "loss": 3.6532, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.886814604389651e-05, + "loss": 3.6479, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.885976009638599e-05, + "loss": 3.6501, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.8851390527679196e-05, + "loss": 3.6528, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.8843004580168676e-05, + "loss": 3.6535, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.8834618632658156e-05, + "loss": 3.6702, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.882623268514764e-05, + "loss": 3.6375, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881786311644085e-05, + "loss": 3.663, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880947716893033e-05, + "loss": 3.6428, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880109122141981e-05, + "loss": 3.6561, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.8792705273909285e-05, + "loss": 3.654, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.8784319326398765e-05, + "loss": 3.6519, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.8775933378888245e-05, + "loss": 3.6573, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876756381018146e-05, + "loss": 3.6551, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.8759177862670934e-05, + "loss": 3.6536, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.898151159286499, + "eval_runtime": 304.0038, + "eval_samples_per_second": 1255.218, + "eval_steps_per_second": 39.226, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8750791915160414e-05, + "loss": 3.6466, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.8742405967649894e-05, + "loss": 3.6446, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873402002013938e-05, + "loss": 3.6537, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872563407262886e-05, + "loss": 3.6529, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871724812511834e-05, + "loss": 3.6603, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6436, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870049260890103e-05, + "loss": 3.6432, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869210666139051e-05, + "loss": 3.6448, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868372071387999e-05, + "loss": 3.6513, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867533476636947e-05, + "loss": 3.6536, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866694881885895e-05, + "loss": 3.6452, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865856287134843e-05, + "loss": 3.6478, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865019330264164e-05, + "loss": 3.65, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864180735513112e-05, + "loss": 3.6376, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.86334214076206e-05, + "loss": 3.6429, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862503546011008e-05, + "loss": 3.6357, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.8616665891403294e-05, + "loss": 3.6392, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8608279943892774e-05, + "loss": 3.638, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.8599893996382254e-05, + "loss": 3.6379, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8591508048871734e-05, + "loss": 3.6614, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.8583122101361214e-05, + "loss": 3.6514, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857475253265442e-05, + "loss": 3.6443, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.85663665851439e-05, + "loss": 3.6456, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855798063763338e-05, + "loss": 3.6513, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854959469012286e-05, + "loss": 3.6296, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854120874261234e-05, + "loss": 3.6445, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853282279510182e-05, + "loss": 3.6493, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852445322639503e-05, + "loss": 3.63, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851606727888452e-05, + "loss": 3.6384, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507681331374e-05, + "loss": 3.6354, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849929538386347e-05, + "loss": 3.6439, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849092581515669e-05, + "loss": 3.6446, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848253986764617e-05, + "loss": 3.6433, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847415392013565e-05, + "loss": 3.6509, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846576797262512e-05, + "loss": 3.6385, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.84573820251146e-05, + "loss": 3.6454, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844899607760408e-05, + "loss": 3.6468, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.84406265088973e-05, + "loss": 3.6407, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843224056138677e-05, + "loss": 3.6306, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842385461387626e-05, + "loss": 3.6434, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841546866636574e-05, + "loss": 3.6316, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840708271885522e-05, + "loss": 3.6527, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.8398713150148426e-05, + "loss": 3.6451, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.8390327202637906e-05, + "loss": 3.6391, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.8381941255127386e-05, + "loss": 3.6485, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.8373555307616866e-05, + "loss": 3.6397, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.8365169360106346e-05, + "loss": 3.6447, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.8356783412595825e-05, + "loss": 3.6426, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.8348413843889035e-05, + "loss": 3.6078, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.8340027896378515e-05, + "loss": 3.6542, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331641948867994e-05, + "loss": 3.6393, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323256001357474e-05, + "loss": 3.6477, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8314870053846954e-05, + "loss": 3.6363, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8306484106336434e-05, + "loss": 3.6359, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829811453762965e-05, + "loss": 3.6248, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828972859011913e-05, + "loss": 3.6407, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828134264260861e-05, + "loss": 3.6447, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827295669509809e-05, + "loss": 3.6417, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826457074758757e-05, + "loss": 3.6549, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825618480007705e-05, + "loss": 3.6329, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824779885256653e-05, + "loss": 3.6251, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823942928385974e-05, + "loss": 3.6512, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823104333634922e-05, + "loss": 3.6287, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.82226573888387e-05, + "loss": 3.6248, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821427144132818e-05, + "loss": 3.6403, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820588549381766e-05, + "loss": 3.6412, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819749954630714e-05, + "loss": 3.6263, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818911359879662e-05, + "loss": 3.6277, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.81807276512861e-05, + "loss": 3.6239, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.8172374461383044e-05, + "loss": 3.6303, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.8163988513872524e-05, + "loss": 3.6428, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8155602566362004e-05, + "loss": 3.6335, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8147216618851484e-05, + "loss": 3.638, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813883067134096e-05, + "loss": 3.6303, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813046110263417e-05, + "loss": 3.6543, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812207515512365e-05, + "loss": 3.6291, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.8113689207613126e-05, + "loss": 3.6447, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810530326010261e-05, + "loss": 3.6321, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809691731259209e-05, + "loss": 3.6311, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808854774388531e-05, + "loss": 3.6416, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808016179637478e-05, + "loss": 3.6449, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807177584886426e-05, + "loss": 3.6344, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806338990135374e-05, + "loss": 3.6399, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805500395384322e-05, + "loss": 3.629, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804663438513643e-05, + "loss": 3.628, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803824843762591e-05, + "loss": 3.6336, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802986249011539e-05, + "loss": 3.6403, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802147654260487e-05, + "loss": 3.6292, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801309059509435e-05, + "loss": 3.6327, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800470464758383e-05, + "loss": 3.6303, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799631870007331e-05, + "loss": 3.6371, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.7987949131366526e-05, + "loss": 3.6373, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.7979563183856006e-05, + "loss": 3.6244, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.7971177236345486e-05, + "loss": 3.6383, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.7962791288834966e-05, + "loss": 3.6367, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7954405341324446e-05, + "loss": 3.6398, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.7946035772617655e-05, + "loss": 3.614, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.7937649825107135e-05, + "loss": 3.6285, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.7929263877596615e-05, + "loss": 3.6275, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.7920877930086095e-05, + "loss": 3.6394, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.7912491982575575e-05, + "loss": 3.6333, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.7904106035065055e-05, + "loss": 3.6368, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.7895720087554535e-05, + "loss": 3.6271, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.7887334140044015e-05, + "loss": 3.6257, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787896457133723e-05, + "loss": 3.6244, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787057862382671e-05, + "loss": 3.6322, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786219267631619e-05, + "loss": 3.6246, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785380672880567e-05, + "loss": 3.6358, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7845420781295144e-05, + "loss": 3.6209, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783705121258836e-05, + "loss": 3.615, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782866526507784e-05, + "loss": 3.6283, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782027931756732e-05, + "loss": 3.6295, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781189337005679e-05, + "loss": 3.6262, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780350742254627e-05, + "loss": 3.6242, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779512147503575e-05, + "loss": 3.635, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778675190632897e-05, + "loss": 3.6389, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777836595881845e-05, + "loss": 3.622, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.776998001130793e-05, + "loss": 3.6315, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776159406379741e-05, + "loss": 3.6335, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775322449509062e-05, + "loss": 3.6276, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.77448385475801e-05, + "loss": 3.63, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773645260006958e-05, + "loss": 3.6217, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772806665255906e-05, + "loss": 3.6249, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7719697083852266e-05, + "loss": 3.6274, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.7711311136341746e-05, + "loss": 3.6332, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.7702925188831226e-05, + "loss": 3.6312, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.7694539241320706e-05, + "loss": 3.6234, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.7686153293810186e-05, + "loss": 3.6272, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.76777837251034e-05, + "loss": 3.6104, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766939777759288e-05, + "loss": 3.6397, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766101183008236e-05, + "loss": 3.624, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765262588257184e-05, + "loss": 3.6404, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764425631386505e-05, + "loss": 3.6184, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763587036635453e-05, + "loss": 3.6349, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762748441884401e-05, + "loss": 3.6337, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761909847133349e-05, + "loss": 3.6215, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761071252382297e-05, + "loss": 3.6265, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760234295511618e-05, + "loss": 3.6249, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759395700760566e-05, + "loss": 3.6351, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758557106009514e-05, + "loss": 3.6419, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757718511258462e-05, + "loss": 3.6141, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7568815543877836e-05, + "loss": 3.6328, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.7560429596367316e-05, + "loss": 3.6231, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.7552043648856796e-05, + "loss": 3.6317, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7543657701346276e-05, + "loss": 3.6261, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7535271753835755e-05, + "loss": 3.6306, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.7526885806325235e-05, + "loss": 3.6288, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.7518516237618445e-05, + "loss": 3.6292, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.7510130290107924e-05, + "loss": 3.6321, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8960113525390625, + "eval_runtime": 304.8101, + "eval_samples_per_second": 1251.898, + "eval_steps_per_second": 39.123, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.7501744342597404e-05, + "loss": 3.6239, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.7493358395086884e-05, + "loss": 3.6198, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.7484988826380093e-05, + "loss": 3.6301, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.7476602878869573e-05, + "loss": 3.6296, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746821693135906e-05, + "loss": 3.6376, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745983098384854e-05, + "loss": 3.6201, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745146141514175e-05, + "loss": 3.6202, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744307546763123e-05, + "loss": 3.6213, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743468952012071e-05, + "loss": 3.6215, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742630357261019e-05, + "loss": 3.6323, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.74179340039034e-05, + "loss": 3.6206, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740954805639288e-05, + "loss": 3.6209, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740117848768609e-05, + "loss": 3.6267, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739279254017557e-05, + "loss": 3.6146, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738440659266505e-05, + "loss": 3.6226, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737602064515453e-05, + "loss": 3.6105, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.7367634697644014e-05, + "loss": 3.6146, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.7359248750133494e-05, + "loss": 3.618, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.7350862802622974e-05, + "loss": 3.6111, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.7342476855112454e-05, + "loss": 3.6364, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733410728640566e-05, + "loss": 3.6329, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732572133889514e-05, + "loss": 3.6193, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731733539138462e-05, + "loss": 3.6233, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7308949443874096e-05, + "loss": 3.6251, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.730057987516731e-05, + "loss": 3.6107, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729219392765679e-05, + "loss": 3.6219, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728380798014627e-05, + "loss": 3.6214, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727542203263575e-05, + "loss": 3.6051, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726703608512523e-05, + "loss": 3.6119, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725866651641845e-05, + "loss": 3.6132, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.725028056890793e-05, + "loss": 3.6249, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.72418946213974e-05, + "loss": 3.6192, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723350867388688e-05, + "loss": 3.6189, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722512272637636e-05, + "loss": 3.6239, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721675315766957e-05, + "loss": 3.6116, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720836721015905e-05, + "loss": 3.6265, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719998126264853e-05, + "loss": 3.6274, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719159531513801e-05, + "loss": 3.611, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718322574643122e-05, + "loss": 3.6141, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.7174839798920705e-05, + "loss": 3.6161, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.7166453851410185e-05, + "loss": 3.6097, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.7158067903899665e-05, + "loss": 3.6267, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.7149681956389145e-05, + "loss": 3.6224, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.7141312387682354e-05, + "loss": 3.6159, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.7132926440171834e-05, + "loss": 3.6233, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.7124540492661314e-05, + "loss": 3.6191, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.7116154545150794e-05, + "loss": 3.6201, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.7107784976444e-05, + "loss": 3.6206, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709939902893348e-05, + "loss": 3.5891, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709101308142296e-05, + "loss": 3.6269, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708262713391244e-05, + "loss": 3.6126, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707424118640192e-05, + "loss": 3.625, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706587161769514e-05, + "loss": 3.617, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705748567018462e-05, + "loss": 3.6104, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.70490997226741e-05, + "loss": 3.6051, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704071377516358e-05, + "loss": 3.6192, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703234420645679e-05, + "loss": 3.6202, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702395825894627e-05, + "loss": 3.6174, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701557231143575e-05, + "loss": 3.6311, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700718636392523e-05, + "loss": 3.6179, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699880041641471e-05, + "loss": 3.5948, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699043084770792e-05, + "loss": 3.6263, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.69820449001974e-05, + "loss": 3.6065, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697365895268688e-05, + "loss": 3.6061, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696527300517636e-05, + "loss": 3.6181, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695688705766584e-05, + "loss": 3.6156, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694851748895905e-05, + "loss": 3.6029, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694013154144853e-05, + "loss": 3.6056, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693174559393801e-05, + "loss": 3.6022, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692335964642749e-05, + "loss": 3.608, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.69149900777207e-05, + "loss": 3.6201, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690660413021018e-05, + "loss": 3.6121, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689821818269966e-05, + "loss": 3.6164, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.688983223518914e-05, + "loss": 3.6062, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688146266648235e-05, + "loss": 3.6285, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687307671897183e-05, + "loss": 3.6103, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686469077146131e-05, + "loss": 3.6217, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685630482395079e-05, + "loss": 3.6071, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.6847935255244006e-05, + "loss": 3.6132, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.6839549307733486e-05, + "loss": 3.6194, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.6831163360222966e-05, + "loss": 3.6214, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.6822777412712446e-05, + "loss": 3.609, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814407844005655e-05, + "loss": 3.6201, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.6806021896495135e-05, + "loss": 3.6001, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.6797635948984615e-05, + "loss": 3.6077, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.6789250001474095e-05, + "loss": 3.6126, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.6780880432767304e-05, + "loss": 3.6199, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.6772494485256784e-05, + "loss": 3.6077, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.6764108537746264e-05, + "loss": 3.6087, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.6755722590235744e-05, + "loss": 3.6086, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674735302152896e-05, + "loss": 3.6135, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673896707401844e-05, + "loss": 3.6164, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673058112650792e-05, + "loss": 3.6034, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.67221951789974e-05, + "loss": 3.6139, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671380923148688e-05, + "loss": 3.6167, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670543966278009e-05, + "loss": 3.6169, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669705371526957e-05, + "loss": 3.5892, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668866776775905e-05, + "loss": 3.6076, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668028182024853e-05, + "loss": 3.606, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667191225154174e-05, + "loss": 3.6157, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666352630403122e-05, + "loss": 3.6155, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.66551403565207e-05, + "loss": 3.6117, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664675440901018e-05, + "loss": 3.6056, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663836846149966e-05, + "loss": 3.6095, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.6629998892792873e-05, + "loss": 3.6045, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662161294528235e-05, + "loss": 3.6083, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.6613226997771827e-05, + "loss": 3.6039, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.6604841050261307e-05, + "loss": 3.6123, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659647148155452e-05, + "loss": 3.6013, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6588085534044e-05, + "loss": 3.5946, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.6579699586533476e-05, + "loss": 3.6022, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.6571313639022955e-05, + "loss": 3.6062, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656294407031617e-05, + "loss": 3.6087, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655455812280565e-05, + "loss": 3.6015, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654617217529513e-05, + "loss": 3.6099, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653778622778461e-05, + "loss": 3.612, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652940028027409e-05, + "loss": 3.6056, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.65210307115673e-05, + "loss": 3.6103, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651264476405678e-05, + "loss": 3.61, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650425881654626e-05, + "loss": 3.6077, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649587286903574e-05, + "loss": 3.6061, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648750330032895e-05, + "loss": 3.5983, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647911735281843e-05, + "loss": 3.6058, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.647073140530791e-05, + "loss": 3.6034, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646234545779739e-05, + "loss": 3.6118, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.6453975889090605e-05, + "loss": 3.6115, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.6445589941580085e-05, + "loss": 3.6017, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.6437203994069565e-05, + "loss": 3.6028, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.6428818046559045e-05, + "loss": 3.5926, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.6420448477852254e-05, + "loss": 3.6168, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.6412062530341734e-05, + "loss": 3.6002, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.6403676582831214e-05, + "loss": 3.6174, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.6395290635320694e-05, + "loss": 3.5999, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.63869210666139e-05, + "loss": 3.6121, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637853511910338e-05, + "loss": 3.6096, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637014917159286e-05, + "loss": 3.5989, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636176322408234e-05, + "loss": 3.6083, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635339365537556e-05, + "loss": 3.6015, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634500770786504e-05, + "loss": 3.6142, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633662176035452e-05, + "loss": 3.6158, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6328235812844e-05, + "loss": 3.6006, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631986624413721e-05, + "loss": 3.6068, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631148029662669e-05, + "loss": 3.6029, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630309434911617e-05, + "loss": 3.6137, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629470840160565e-05, + "loss": 3.6022, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.6286338832898857e-05, + "loss": 3.6148, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277952885388337e-05, + "loss": 3.6005, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.6269566937877816e-05, + "loss": 3.6122, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6261180990367296e-05, + "loss": 3.6052, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.893625020980835, + "eval_runtime": 306.2305, + "eval_samples_per_second": 1246.091, + "eval_steps_per_second": 38.941, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.6252795042856776e-05, + "loss": 3.6003, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624440909534626e-05, + "loss": 3.5976, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623602314783574e-05, + "loss": 3.6057, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622763720032522e-05, + "loss": 3.6121, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.62192512528147e-05, + "loss": 3.6186, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621088168410791e-05, + "loss": 3.5979, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620249573659739e-05, + "loss": 3.5974, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619410978908687e-05, + "loss": 3.5997, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618572384157635e-05, + "loss": 3.6057, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617735427286956e-05, + "loss": 3.6064, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616896832535904e-05, + "loss": 3.5983, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.616058237784852e-05, + "loss": 3.6012, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615221280914173e-05, + "loss": 3.6106, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614382686163122e-05, + "loss": 3.592, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.61354409141207e-05, + "loss": 3.5962, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612705496661018e-05, + "loss": 3.5915, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611866901909966e-05, + "loss": 3.5904, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6110283071589137e-05, + "loss": 3.5982, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610189712407861e-05, + "loss": 3.5953, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609351117656809e-05, + "loss": 3.6104, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.6085141607861306e-05, + "loss": 3.6105, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607675566035078e-05, + "loss": 3.599, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606836971284026e-05, + "loss": 3.6022, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605998376532974e-05, + "loss": 3.6025, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.6051614196622955e-05, + "loss": 3.5871, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.6043228249112435e-05, + "loss": 3.605, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.6034842301601914e-05, + "loss": 3.5987, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.6026456354091394e-05, + "loss": 3.5839, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601808678538461e-05, + "loss": 3.5923, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6009700837874083e-05, + "loss": 3.5941, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.6001314890363563e-05, + "loss": 3.5995, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5992928942853043e-05, + "loss": 3.598, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598455937414625e-05, + "loss": 3.6043, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597617342663573e-05, + "loss": 3.6021, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596778747912521e-05, + "loss": 3.5906, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595940153161469e-05, + "loss": 3.6061, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595103196290791e-05, + "loss": 3.6064, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594264601539739e-05, + "loss": 3.5937, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593426006788687e-05, + "loss": 3.5928, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592587412037635e-05, + "loss": 3.5946, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591750455166956e-05, + "loss": 3.5866, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590911860415904e-05, + "loss": 3.6053, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590073265664852e-05, + "loss": 3.6016, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.5892346709138e-05, + "loss": 3.6012, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.5883977140431206e-05, + "loss": 3.5997, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.5875591192920686e-05, + "loss": 3.5998, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5867205245410166e-05, + "loss": 3.5994, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5858819297899646e-05, + "loss": 3.5989, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.585044972919286e-05, + "loss": 3.571, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584206378168234e-05, + "loss": 3.6051, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583367783417182e-05, + "loss": 3.5919, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.58252918866613e-05, + "loss": 3.6046, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581692231795451e-05, + "loss": 3.5943, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580853637044399e-05, + "loss": 3.5904, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.580015042293347e-05, + "loss": 3.5831, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579176447542295e-05, + "loss": 3.5945, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578339490671616e-05, + "loss": 3.6043, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577500895920564e-05, + "loss": 3.5938, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576662301169512e-05, + "loss": 3.6108, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.57582370641846e-05, + "loss": 3.5954, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.5749867495477816e-05, + "loss": 3.5765, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.5741481547967296e-05, + "loss": 3.6066, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.5733095600456775e-05, + "loss": 3.5906, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.5724709652946255e-05, + "loss": 3.5862, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5716323705435735e-05, + "loss": 3.5944, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5707954136728944e-05, + "loss": 3.5975, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5699568189218424e-05, + "loss": 3.5793, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.5691182241707904e-05, + "loss": 3.5869, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.5682796294197384e-05, + "loss": 3.5798, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.5674426725490593e-05, + "loss": 3.592, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.5666040777980073e-05, + "loss": 3.5961, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565765483046955e-05, + "loss": 3.5915, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564926888295903e-05, + "loss": 3.5977, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.564089931425225e-05, + "loss": 3.584, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563251336674173e-05, + "loss": 3.6072, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562412741923121e-05, + "loss": 3.591, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561574147172069e-05, + "loss": 3.604, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.56073719030139e-05, + "loss": 3.587, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559898595550338e-05, + "loss": 3.5898, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559060000799286e-05, + "loss": 3.5983, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558221406048234e-05, + "loss": 3.5985, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557384449177555e-05, + "loss": 3.5918, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556545854426503e-05, + "loss": 3.5978, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555707259675451e-05, + "loss": 3.5822, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554868664924399e-05, + "loss": 3.5874, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.55403170805372e-05, + "loss": 3.5885, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553193113302668e-05, + "loss": 3.6008, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552354518551616e-05, + "loss": 3.5871, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551515923800564e-05, + "loss": 3.5876, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550678966929885e-05, + "loss": 3.5906, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549840372178833e-05, + "loss": 3.589, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.549001777427781e-05, + "loss": 3.5945, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548163182676729e-05, + "loss": 3.5834, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.54732622580605e-05, + "loss": 3.5925, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546487631054998e-05, + "loss": 3.6008, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545649036303946e-05, + "loss": 3.5956, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544810441552894e-05, + "loss": 3.5729, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5439734846822157e-05, + "loss": 3.5867, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5431348899311636e-05, + "loss": 3.5827, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.5422962951801116e-05, + "loss": 3.5961, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.5414577004290596e-05, + "loss": 3.5967, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.5406207435583805e-05, + "loss": 3.5903, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5397821488073285e-05, + "loss": 3.5826, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5389435540562765e-05, + "loss": 3.5872, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.5381049593052245e-05, + "loss": 3.5814, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.5372680024345454e-05, + "loss": 3.5883, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.5364294076834934e-05, + "loss": 3.5842, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.5355908129324414e-05, + "loss": 3.5901, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.5347522181813894e-05, + "loss": 3.5849, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533915261310711e-05, + "loss": 3.5726, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533076666559659e-05, + "loss": 3.582, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532238071808607e-05, + "loss": 3.5825, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531399477057555e-05, + "loss": 3.5903, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530562520186876e-05, + "loss": 3.5805, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529723925435824e-05, + "loss": 3.5927, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528885330684772e-05, + "loss": 3.5894, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.52804673593372e-05, + "loss": 3.5879, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527209779063041e-05, + "loss": 3.5899, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526371184311989e-05, + "loss": 3.5881, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525532589560937e-05, + "loss": 3.5879, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524693994809885e-05, + "loss": 3.5859, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.5238570379392064e-05, + "loss": 3.5792, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5230184431881544e-05, + "loss": 3.5862, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.5221798484371024e-05, + "loss": 3.5834, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.5213412536860504e-05, + "loss": 3.5915, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520504296815371e-05, + "loss": 3.5888, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519665702064319e-05, + "loss": 3.5813, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518827107313267e-05, + "loss": 3.5823, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517988512562215e-05, + "loss": 3.575, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517151555691536e-05, + "loss": 3.5939, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516312960940484e-05, + "loss": 3.5858, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515474366189432e-05, + "loss": 3.5991, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.51463577143838e-05, + "loss": 3.5785, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.513798814567702e-05, + "loss": 3.592, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.51296021981665e-05, + "loss": 3.5914, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512121625065598e-05, + "loss": 3.582, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511283030314546e-05, + "loss": 3.5842, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5104460734438666e-05, + "loss": 3.584, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5096074786928146e-05, + "loss": 3.5928, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5087688839417626e-05, + "loss": 3.5964, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.50793028919071e-05, + "loss": 3.5825, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5070933323200315e-05, + "loss": 3.5814, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062547375689795e-05, + "loss": 3.587, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5054161428179275e-05, + "loss": 3.5916, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.5045775480668755e-05, + "loss": 3.5812, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503740591196197e-05, + "loss": 3.5971, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502901996445145e-05, + "loss": 3.583, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502063401694093e-05, + "loss": 3.5943, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.5012248069430404e-05, + "loss": 3.5849, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8941779136657715, + "eval_runtime": 307.0734, + "eval_samples_per_second": 1242.67, + "eval_steps_per_second": 38.834, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.500387850072362e-05, + "loss": 3.5877, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.49954925532131e-05, + "loss": 3.5762, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498710660570257e-05, + "loss": 3.5849, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497872065819205e-05, + "loss": 3.593, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497035108948527e-05, + "loss": 3.5967, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496196514197475e-05, + "loss": 3.5816, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495357919446422e-05, + "loss": 3.5786, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494519324695371e-05, + "loss": 3.5824, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4936823678246925e-05, + "loss": 3.5816, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.4928437730736405e-05, + "loss": 3.5857, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.492005178322588e-05, + "loss": 3.5834, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491166583571536e-05, + "loss": 3.5825, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.4903296267008574e-05, + "loss": 3.5907, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489491031949805e-05, + "loss": 3.5704, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488652437198753e-05, + "loss": 3.5774, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487813842447701e-05, + "loss": 3.5726, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486976885577022e-05, + "loss": 3.5686, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4861382908259696e-05, + "loss": 3.5789, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4852996960749176e-05, + "loss": 3.5732, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484461101323866e-05, + "loss": 3.5895, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483624144453188e-05, + "loss": 3.5929, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482785549702135e-05, + "loss": 3.5811, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481946954951083e-05, + "loss": 3.5834, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481108360200031e-05, + "loss": 3.5858, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480271403329352e-05, + "loss": 3.5648, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.4794328085783e-05, + "loss": 3.5894, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478594213827248e-05, + "loss": 3.5739, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477755619076196e-05, + "loss": 3.5682, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476918662205517e-05, + "loss": 3.5744, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476080067454465e-05, + "loss": 3.5732, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475241472703413e-05, + "loss": 3.5797, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.4744028779523616e-05, + "loss": 3.5773, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4735659210816825e-05, + "loss": 3.5899, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4727273263306305e-05, + "loss": 3.5789, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4718887315795785e-05, + "loss": 3.5731, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4710501368285265e-05, + "loss": 3.5856, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4702131799578474e-05, + "loss": 3.587, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.4693745852067954e-05, + "loss": 3.5757, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.4685359904557434e-05, + "loss": 3.5716, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.4676973957046914e-05, + "loss": 3.5754, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466860438834012e-05, + "loss": 3.57, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.46602184408296e-05, + "loss": 3.5821, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465183249331908e-05, + "loss": 3.5799, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464344654580857e-05, + "loss": 3.5862, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463507697710178e-05, + "loss": 3.583, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462669102959126e-05, + "loss": 3.5796, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461830508208074e-05, + "loss": 3.5802, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460991913457022e-05, + "loss": 3.5784, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460154956586343e-05, + "loss": 3.5531, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459316361835291e-05, + "loss": 3.5858, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458477767084239e-05, + "loss": 3.5757, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457639172333187e-05, + "loss": 3.5858, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456802215462508e-05, + "loss": 3.5738, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455963620711456e-05, + "loss": 3.5749, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455125025960404e-05, + "loss": 3.561, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454286431209352e-05, + "loss": 3.5725, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.453449474338673e-05, + "loss": 3.589, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452610879587621e-05, + "loss": 3.5754, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451772284836569e-05, + "loss": 3.5903, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450933690085517e-05, + "loss": 3.5759, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450096733214838e-05, + "loss": 3.5564, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449258138463786e-05, + "loss": 3.5907, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448419543712734e-05, + "loss": 3.5683, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447580948961682e-05, + "loss": 3.5647, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446743992091003e-05, + "loss": 3.5777, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445905397339951e-05, + "loss": 3.5772, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445066802588899e-05, + "loss": 3.5626, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444228207837847e-05, + "loss": 3.5667, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.4433912509671686e-05, + "loss": 3.5629, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.4425526562161166e-05, + "loss": 3.567, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.4417140614650646e-05, + "loss": 3.5828, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4408754667140126e-05, + "loss": 3.5737, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.4400385098433335e-05, + "loss": 3.577, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.4391999150922815e-05, + "loss": 3.5676, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.4383613203412295e-05, + "loss": 3.5886, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.4375227255901775e-05, + "loss": 3.5745, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.4366857687194984e-05, + "loss": 3.5843, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.4358471739684464e-05, + "loss": 3.5681, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.4350085792173944e-05, + "loss": 3.5716, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.434171622346716e-05, + "loss": 3.5837, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433333027595664e-05, + "loss": 3.5778, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432494432844612e-05, + "loss": 3.5724, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.43165583809356e-05, + "loss": 3.5803, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430817243342508e-05, + "loss": 3.5646, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429978648591456e-05, + "loss": 3.5665, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.429140053840404e-05, + "loss": 3.5706, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428301459089352e-05, + "loss": 3.5806, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427464502218673e-05, + "loss": 3.5686, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.426625907467621e-05, + "loss": 3.571, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425787312716569e-05, + "loss": 3.5707, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424948717965517e-05, + "loss": 3.5709, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424111761094838e-05, + "loss": 3.5762, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4232731663437865e-05, + "loss": 3.5674, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4224345715927345e-05, + "loss": 3.5727, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.4215959768416825e-05, + "loss": 3.5814, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.4207590199710034e-05, + "loss": 3.58, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.4199204252199514e-05, + "loss": 3.5486, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.4190818304688994e-05, + "loss": 3.5693, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.4182432357178473e-05, + "loss": 3.5633, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417406278847168e-05, + "loss": 3.5793, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416567684096116e-05, + "loss": 3.5771, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415729089345064e-05, + "loss": 3.573, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414890494594012e-05, + "loss": 3.5627, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.414053537723333e-05, + "loss": 3.5717, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413214942972282e-05, + "loss": 3.5672, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.41237634822123e-05, + "loss": 3.5686, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411537753470178e-05, + "loss": 3.563, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410700796599499e-05, + "loss": 3.5736, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409862201848447e-05, + "loss": 3.5664, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.409023607097395e-05, + "loss": 3.556, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408185012346343e-05, + "loss": 3.5637, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4073480554756636e-05, + "loss": 3.5621, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4065094607246116e-05, + "loss": 3.5736, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.4056708659735596e-05, + "loss": 3.5614, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404832271222507e-05, + "loss": 3.5737, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.4039953143518285e-05, + "loss": 3.5724, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403156719600777e-05, + "loss": 3.5711, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402318124849725e-05, + "loss": 3.5684, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.4014795300986725e-05, + "loss": 3.573, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400642573227994e-05, + "loss": 3.5726, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399803978476942e-05, + "loss": 3.5667, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.39896538372589e-05, + "loss": 3.5597, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398128426855211e-05, + "loss": 3.5695, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397289832104159e-05, + "loss": 3.5657, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396451237353107e-05, + "loss": 3.5704, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395612642602054e-05, + "loss": 3.5701, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394775685731376e-05, + "loss": 3.5651, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393937090980324e-05, + "loss": 3.5676, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.3931001341096455e-05, + "loss": 3.5584, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.3922615393585935e-05, + "loss": 3.5715, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.3914229446075415e-05, + "loss": 3.569, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.3905843498564895e-05, + "loss": 3.5834, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.3897457551054375e-05, + "loss": 3.5607, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388907160354385e-05, + "loss": 3.5693, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388068565603333e-05, + "loss": 3.5742, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387229970852281e-05, + "loss": 3.5658, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386393013981602e-05, + "loss": 3.5617, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.38555441923055e-05, + "loss": 3.5683, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384715824479498e-05, + "loss": 3.5781, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3838772297284463e-05, + "loss": 3.5775, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383040272857767e-05, + "loss": 3.5676, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382201678106715e-05, + "loss": 3.5624, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381363083355663e-05, + "loss": 3.568, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380524488604611e-05, + "loss": 3.5715, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379687531733932e-05, + "loss": 3.5585, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.37884893698288e-05, + "loss": 3.5849, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.378010342231828e-05, + "loss": 3.5598, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377171747480776e-05, + "loss": 3.5728, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376334790610097e-05, + "loss": 3.5686, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8936355113983154, + "eval_runtime": 306.8629, + "eval_samples_per_second": 1243.523, + "eval_steps_per_second": 38.861, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375496195859045e-05, + "loss": 3.588, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374657601107993e-05, + "loss": 3.5577, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373819006356942e-05, + "loss": 3.565, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.37298041160589e-05, + "loss": 3.5757, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721434547352106e-05, + "loss": 3.5721, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3713048599841586e-05, + "loss": 3.5688, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3704662652331066e-05, + "loss": 3.5601, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696276704820546e-05, + "loss": 3.5595, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3687907136113755e-05, + "loss": 3.5648, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.3679521188603235e-05, + "loss": 3.5704, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.3671135241092715e-05, + "loss": 3.5631, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3662749293582195e-05, + "loss": 3.5714, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.3654379724875404e-05, + "loss": 3.5719, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.3645993777364884e-05, + "loss": 3.5522, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.3637607829854364e-05, + "loss": 3.562, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362922188234385e-05, + "loss": 3.5508, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362083593483333e-05, + "loss": 3.5499, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361244998732281e-05, + "loss": 3.5654, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360406403981229e-05, + "loss": 3.5528, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359567809230177e-05, + "loss": 3.5727, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358730852359498e-05, + "loss": 3.5775, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357892257608446e-05, + "loss": 3.5623, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357053662857394e-05, + "loss": 3.5672, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356215068106342e-05, + "loss": 3.5671, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355378111235663e-05, + "loss": 3.5506, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354539516484611e-05, + "loss": 3.5673, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353700921733559e-05, + "loss": 3.5582, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352862326982507e-05, + "loss": 3.5536, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3520253701118284e-05, + "loss": 3.5594, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.3511867753607764e-05, + "loss": 3.5517, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.3503481806097244e-05, + "loss": 3.5599, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.3495095858586724e-05, + "loss": 3.5615, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348672628987993e-05, + "loss": 3.5714, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347834034236941e-05, + "loss": 3.559, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346995439485889e-05, + "loss": 3.5563, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346156844734837e-05, + "loss": 3.5621, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345319887864158e-05, + "loss": 3.5739, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344481293113106e-05, + "loss": 3.5575, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343642698362054e-05, + "loss": 3.5548, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342804103611002e-05, + "loss": 3.5572, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341967146740324e-05, + "loss": 3.556, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341128551989272e-05, + "loss": 3.5591, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.34028995723822e-05, + "loss": 3.5646, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339451362487168e-05, + "loss": 3.5657, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338614405616489e-05, + "loss": 3.5625, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337775810865437e-05, + "loss": 3.5603, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336937216114385e-05, + "loss": 3.5618, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336098621363333e-05, + "loss": 3.562, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3352616644926536e-05, + "loss": 3.5393, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3344230697416016e-05, + "loss": 3.5661, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3335844749905496e-05, + "loss": 3.5596, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3327458802394976e-05, + "loss": 3.566, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331908923368819e-05, + "loss": 3.5545, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331070328617767e-05, + "loss": 3.5562, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330231733866715e-05, + "loss": 3.5514, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.3293931391156625e-05, + "loss": 3.5501, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328556182244984e-05, + "loss": 3.5684, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327717587493932e-05, + "loss": 3.5572, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.32687899274288e-05, + "loss": 3.5782, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.3260403979918274e-05, + "loss": 3.5547, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325203441121149e-05, + "loss": 3.5434, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324364846370097e-05, + "loss": 3.572, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323526251619045e-05, + "loss": 3.554, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322687656867993e-05, + "loss": 3.5466, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218506999973145e-05, + "loss": 3.5533, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3210121052462625e-05, + "loss": 3.5634, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.32017351049521e-05, + "loss": 3.5427, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319334915744158e-05, + "loss": 3.5519, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184979588734794e-05, + "loss": 3.5451, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176593641224274e-05, + "loss": 3.5463, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316820769371375e-05, + "loss": 3.5682, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315982174620323e-05, + "loss": 3.5551, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315145217749644e-05, + "loss": 3.5576, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314306622998592e-05, + "loss": 3.5498, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.31346802824754e-05, + "loss": 3.5692, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312629433496488e-05, + "loss": 3.5564, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.31179247662581e-05, + "loss": 3.567, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310953881874757e-05, + "loss": 3.5522, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310115287123705e-05, + "loss": 3.5533, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309278330253027e-05, + "loss": 3.5643, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308439735501975e-05, + "loss": 3.558, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307601140750922e-05, + "loss": 3.5564, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.30676254599987e-05, + "loss": 3.5626, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305923951248818e-05, + "loss": 3.5533, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305085356497766e-05, + "loss": 3.5464, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304246761746714e-05, + "loss": 3.552, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303408166995662e-05, + "loss": 3.5636, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302571210124984e-05, + "loss": 3.5557, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301732615373932e-05, + "loss": 3.5541, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.30089402062288e-05, + "loss": 3.5538, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300055425871828e-05, + "loss": 3.55, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.2992184690011486e-05, + "loss": 3.5574, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2983798742500966e-05, + "loss": 3.5537, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2975412794990446e-05, + "loss": 3.5548, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2967026847479926e-05, + "loss": 3.5621, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.2958657278773135e-05, + "loss": 3.5631, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.2950271331262615e-05, + "loss": 3.534, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2941885383752095e-05, + "loss": 3.5507, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.2933499436241575e-05, + "loss": 3.5493, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292512986753479e-05, + "loss": 3.559, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291674392002427e-05, + "loss": 3.5612, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290835797251375e-05, + "loss": 3.5546, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289997202500323e-05, + "loss": 3.545, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289160245629644e-05, + "loss": 3.5538, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288321650878592e-05, + "loss": 3.5522, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.28748305612754e-05, + "loss": 3.5502, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286644461376488e-05, + "loss": 3.5478, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285807504505809e-05, + "loss": 3.557, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284968909754757e-05, + "loss": 3.5483, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284130315003705e-05, + "loss": 3.5397, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283291720252653e-05, + "loss": 3.5503, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2824547633819744e-05, + "loss": 3.5393, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2816161686309224e-05, + "loss": 3.5565, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.2807775738798704e-05, + "loss": 3.5502, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279940617009191e-05, + "loss": 3.5525, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279102022258139e-05, + "loss": 3.5566, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278263427507087e-05, + "loss": 3.5561, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277424832756035e-05, + "loss": 3.5527, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276587875885356e-05, + "loss": 3.5535, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275749281134304e-05, + "loss": 3.5567, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274910686383252e-05, + "loss": 3.5474, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274073729512573e-05, + "loss": 3.5396, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273235134761521e-05, + "loss": 3.5533, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.27239654001047e-05, + "loss": 3.5516, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271557945259418e-05, + "loss": 3.5525, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270719350508366e-05, + "loss": 3.5508, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269880755757314e-05, + "loss": 3.5515, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.269042161006262e-05, + "loss": 3.5505, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268205204135583e-05, + "loss": 3.5416, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267366609384531e-05, + "loss": 3.5468, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266528014633479e-05, + "loss": 3.5561, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2656894198824267e-05, + "loss": 3.5662, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648508251313747e-05, + "loss": 3.5415, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2640138682606956e-05, + "loss": 3.5476, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2631752735096436e-05, + "loss": 3.5605, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2623366787585916e-05, + "loss": 3.5474, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.2614980840075395e-05, + "loss": 3.5455, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260659489256488e-05, + "loss": 3.5482, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.2598208945054355e-05, + "loss": 3.5628, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.2589822997543835e-05, + "loss": 3.5598, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.2581437050033315e-05, + "loss": 3.5496, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257306748132653e-05, + "loss": 3.5439, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.2564681533816004e-05, + "loss": 3.5531, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.2556295586305484e-05, + "loss": 3.5549, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.2547909638794964e-05, + "loss": 3.5416, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253954007008817e-05, + "loss": 3.5667, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253115412257765e-05, + "loss": 3.5465, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252276817506713e-05, + "loss": 3.5565, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251438222755662e-05, + "loss": 3.5512, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.895479679107666, + "eval_runtime": 304.5478, + "eval_samples_per_second": 1252.976, + "eval_steps_per_second": 39.156, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250601265884983e-05, + "loss": 3.5539, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249762671133931e-05, + "loss": 3.5403, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248924076382879e-05, + "loss": 3.5489, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248085481631827e-05, + "loss": 3.5598, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247248524761148e-05, + "loss": 3.5556, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246409930010096e-05, + "loss": 3.5512, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245571335259044e-05, + "loss": 3.5464, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244732740507992e-05, + "loss": 3.5451, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243895783637313e-05, + "loss": 3.5454, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243057188886261e-05, + "loss": 3.5529, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242218594135209e-05, + "loss": 3.5481, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2413799993841574e-05, + "loss": 3.5558, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240543042513478e-05, + "loss": 3.5532, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239704447762426e-05, + "loss": 3.5349, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238865853011374e-05, + "loss": 3.5464, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238027258260322e-05, + "loss": 3.5324, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237190301389643e-05, + "loss": 3.5346, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236351706638591e-05, + "loss": 3.5456, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235513111887539e-05, + "loss": 3.5371, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234674517136487e-05, + "loss": 3.5542, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233837560265808e-05, + "loss": 3.5626, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.232998965514756e-05, + "loss": 3.5447, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232160370763704e-05, + "loss": 3.5483, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231321776012653e-05, + "loss": 3.5502, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.2304848191419736e-05, + "loss": 3.537, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.2296462243909216e-05, + "loss": 3.5535, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.2288076296398696e-05, + "loss": 3.5388, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.2279690348888176e-05, + "loss": 3.5408, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.2271320780181385e-05, + "loss": 3.5393, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2262934832670865e-05, + "loss": 3.5349, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.2254548885160345e-05, + "loss": 3.5414, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.2246179316453554e-05, + "loss": 3.5468, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.2237793368943034e-05, + "loss": 3.5548, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.2229407421432514e-05, + "loss": 3.5436, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2221021473921994e-05, + "loss": 3.537, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221265190521521e-05, + "loss": 3.5436, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220426595770469e-05, + "loss": 3.5596, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219588001019417e-05, + "loss": 3.5382, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218749406268365e-05, + "loss": 3.5405, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217912449397686e-05, + "loss": 3.5397, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217073854646634e-05, + "loss": 3.5365, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216236897775955e-05, + "loss": 3.5437, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215398303024903e-05, + "loss": 3.5483, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214559708273851e-05, + "loss": 3.5527, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213721113522799e-05, + "loss": 3.5463, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212882518771747e-05, + "loss": 3.5445, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212043924020695e-05, + "loss": 3.5439, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211205329269643e-05, + "loss": 3.5505, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2103667345185915e-05, + "loss": 3.5175, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2095297776479124e-05, + "loss": 3.5466, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.2086911828968604e-05, + "loss": 3.5465, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.2078525881458084e-05, + "loss": 3.5489, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.2070139933947564e-05, + "loss": 3.5388, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206177036524077e-05, + "loss": 3.5358, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205338441773025e-05, + "loss": 3.5398, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204499847021973e-05, + "loss": 3.5344, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203661252270921e-05, + "loss": 3.5529, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202824295400242e-05, + "loss": 3.541, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.20198570064919e-05, + "loss": 3.5587, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201147105898138e-05, + "loss": 3.5402, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.200308511147087e-05, + "loss": 3.5248, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199471554276408e-05, + "loss": 3.5542, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198632959525356e-05, + "loss": 3.5343, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197794364774304e-05, + "loss": 3.5338, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.196955770023252e-05, + "loss": 3.54, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1961188131525726e-05, + "loss": 3.5451, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1952802184015206e-05, + "loss": 3.5262, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944416236504686e-05, + "loss": 3.5357, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1936030288994166e-05, + "loss": 3.5317, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1927660720287375e-05, + "loss": 3.5321, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1919274772776855e-05, + "loss": 3.5485, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.1910888825266335e-05, + "loss": 3.5407, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190250287775582e-05, + "loss": 3.5413, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189413330904903e-05, + "loss": 3.5362, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188574736153851e-05, + "loss": 3.5515, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187736141402799e-05, + "loss": 3.5383, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186897546651747e-05, + "loss": 3.5495, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186060589781068e-05, + "loss": 3.5387, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185221995030016e-05, + "loss": 3.5375, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184385038159337e-05, + "loss": 3.5471, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183546443408285e-05, + "loss": 3.5438, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182707848657233e-05, + "loss": 3.5418, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181869253906181e-05, + "loss": 3.5465, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.181030659155129e-05, + "loss": 3.5417, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1801920644040776e-05, + "loss": 3.5251, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1793534696530256e-05, + "loss": 3.5352, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178514874901973e-05, + "loss": 3.549, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1776779180312945e-05, + "loss": 3.5383, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1768393232802425e-05, + "loss": 3.5368, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.1760007285291905e-05, + "loss": 3.538, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175162133778138e-05, + "loss": 3.5359, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.1743251769074594e-05, + "loss": 3.5393, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.1734865821564074e-05, + "loss": 3.5375, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172647987405355e-05, + "loss": 3.5436, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171809392654303e-05, + "loss": 3.5392, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170972435783624e-05, + "loss": 3.5505, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170133841032573e-05, + "loss": 3.5171, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.16929524628152e-05, + "loss": 3.5382, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168456651530468e-05, + "loss": 3.5339, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.16761969465979e-05, + "loss": 3.544, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166781099908738e-05, + "loss": 3.5412, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165942505157685e-05, + "loss": 3.5404, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.165103910406633e-05, + "loss": 3.5279, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164266953535955e-05, + "loss": 3.5392, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163428358784902e-05, + "loss": 3.5369, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.16258976403385e-05, + "loss": 3.5313, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161751169282798e-05, + "loss": 3.5302, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.1609142124121196e-05, + "loss": 3.5388, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.1600756176610676e-05, + "loss": 3.5405, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.1592370229100156e-05, + "loss": 3.5213, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.1583984281589636e-05, + "loss": 3.5355, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157561471288285e-05, + "loss": 3.5247, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.1567228765372325e-05, + "loss": 3.541, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.1558842817861805e-05, + "loss": 3.53, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.1550456870351285e-05, + "loss": 3.535, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.1542087301644494e-05, + "loss": 3.5395, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1533701354133974e-05, + "loss": 3.5403, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.1525315406623454e-05, + "loss": 3.5337, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.1516929459112934e-05, + "loss": 3.5383, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150855989040615e-05, + "loss": 3.5417, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.150017394289563e-05, + "loss": 3.53, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.1491804374188846e-05, + "loss": 3.5248, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.1483418426678326e-05, + "loss": 3.5393, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.14750324791678e-05, + "loss": 3.5387, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146664653165728e-05, + "loss": 3.5361, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145826058414676e-05, + "loss": 3.5342, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.144987463663624e-05, + "loss": 3.535, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144148868912572e-05, + "loss": 3.5336, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143311912041893e-05, + "loss": 3.525, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142473317290841e-05, + "loss": 3.5295, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141634722539789e-05, + "loss": 3.545, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.1407961277887374e-05, + "loss": 3.5489, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.1399575330376854e-05, + "loss": 3.5297, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.1391205761670063e-05, + "loss": 3.532, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1382819814159543e-05, + "loss": 3.54, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.1374433866649023e-05, + "loss": 3.5316, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.13660479191385e-05, + "loss": 3.5307, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135766197162798e-05, + "loss": 3.5365, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134927602411746e-05, + "loss": 3.5473, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134089007660694e-05, + "loss": 3.541, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133250412909642e-05, + "loss": 3.5346, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132413456038963e-05, + "loss": 3.5276, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131574861287911e-05, + "loss": 3.5387, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130736266536859e-05, + "loss": 3.5382, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129897671785807e-05, + "loss": 3.5264, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.129060714915129e-05, + "loss": 3.5533, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128222120164077e-05, + "loss": 3.5316, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127383525413025e-05, + "loss": 3.5404, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126544930661973e-05, + "loss": 3.5337, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.896214246749878, + "eval_runtime": 304.2635, + "eval_samples_per_second": 1254.146, + "eval_steps_per_second": 39.193, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125707973791294e-05, + "loss": 3.5245, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124869379040242e-05, + "loss": 3.53, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.12403078428919e-05, + "loss": 3.5332, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123192189538138e-05, + "loss": 3.5429, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.1223552326674586e-05, + "loss": 3.5419, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.1215166379164066e-05, + "loss": 3.5382, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.1206780431653546e-05, + "loss": 3.528, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.1198394484143026e-05, + "loss": 3.5303, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.119002491543624e-05, + "loss": 3.5303, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118163896792572e-05, + "loss": 3.5384, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.11732530204152e-05, + "loss": 3.5336, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116486707290468e-05, + "loss": 3.5376, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115649750419789e-05, + "loss": 3.5398, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114811155668737e-05, + "loss": 3.5216, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113972560917685e-05, + "loss": 3.5278, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113133966166633e-05, + "loss": 3.5141, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112297009295954e-05, + "loss": 3.5206, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111458414544902e-05, + "loss": 3.5297, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.11061981979385e-05, + "loss": 3.5224, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109781225042798e-05, + "loss": 3.5321, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.1089442681721195e-05, + "loss": 3.5465, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.1081056734210675e-05, + "loss": 3.5314, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.1072670786700155e-05, + "loss": 3.5303, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106428483918963e-05, + "loss": 3.5361, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.1055915270482844e-05, + "loss": 3.5263, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1047529322972324e-05, + "loss": 3.532, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1039143375461804e-05, + "loss": 3.5198, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.103075742795128e-05, + "loss": 3.5308, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102238785924449e-05, + "loss": 3.5265, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101400191173397e-05, + "loss": 3.5172, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100561596422345e-05, + "loss": 3.5309, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099723001671293e-05, + "loss": 3.5258, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098886044800615e-05, + "loss": 3.5382, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098047450049563e-05, + "loss": 3.5326, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.09720885529851e-05, + "loss": 3.5208, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096370260547458e-05, + "loss": 3.5271, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.09553330367678e-05, + "loss": 3.5444, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094694708925728e-05, + "loss": 3.5219, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093856114174675e-05, + "loss": 3.5267, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.093017519423623e-05, + "loss": 3.5228, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092180562552945e-05, + "loss": 3.5229, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.0913436056822656e-05, + "loss": 3.5229, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.0905050109312136e-05, + "loss": 3.5406, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089666416180162e-05, + "loss": 3.5346, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.08882782142911e-05, + "loss": 3.5305, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.0879892266780576e-05, + "loss": 3.5321, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.0871506319270056e-05, + "loss": 3.525, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0863120371759536e-05, + "loss": 3.5366, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.0854734424249016e-05, + "loss": 3.5034, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.0846364855542225e-05, + "loss": 3.5303, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.0837978908031705e-05, + "loss": 3.532, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.0829592960521185e-05, + "loss": 3.5345, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.0821207013010665e-05, + "loss": 3.5247, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0812837444303874e-05, + "loss": 3.5157, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080446787559709e-05, + "loss": 3.5258, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0796081928086576e-05, + "loss": 3.5166, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078769598057605e-05, + "loss": 3.5418, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077931003306553e-05, + "loss": 3.5237, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077092408555501e-05, + "loss": 3.5438, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076253813804449e-05, + "loss": 3.5233, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075415219053397e-05, + "loss": 3.5161, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074576624302345e-05, + "loss": 3.5341, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073739667431666e-05, + "loss": 3.5186, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072901072680614e-05, + "loss": 3.5223, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072062477929562e-05, + "loss": 3.5189, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.07122388317851e-05, + "loss": 3.5334, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070385288427458e-05, + "loss": 3.5106, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069546693676406e-05, + "loss": 3.521, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.0687080989253545e-05, + "loss": 3.5137, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.0678695041743025e-05, + "loss": 3.5166, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.0670325473036234e-05, + "loss": 3.5342, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.0661939525525714e-05, + "loss": 3.5259, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.0653553578015194e-05, + "loss": 3.5223, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.06451840093084e-05, + "loss": 3.5243, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063679806179788e-05, + "loss": 3.5344, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062841211428736e-05, + "loss": 3.526, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.062002616677684e-05, + "loss": 3.5294, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061164021926632e-05, + "loss": 3.526, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.06032542717558e-05, + "loss": 3.5251, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059488470304901e-05, + "loss": 3.5312, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058649875553849e-05, + "loss": 3.5255, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057811280802798e-05, + "loss": 3.5256, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056972686051746e-05, + "loss": 3.5328, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056134091300694e-05, + "loss": 3.5234, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055295496549641e-05, + "loss": 3.5101, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054456901798589e-05, + "loss": 3.5217, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053618307047537e-05, + "loss": 3.5287, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052781350176859e-05, + "loss": 3.5254, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051942755425806e-05, + "loss": 3.5233, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511041606747544e-05, + "loss": 3.5205, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502655659237024e-05, + "loss": 3.5239, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494286090530233e-05, + "loss": 3.5226, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0485900143019713e-05, + "loss": 3.5208, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477514195509193e-05, + "loss": 3.5264, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469128247998673e-05, + "loss": 3.5234, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460758679291885e-05, + "loss": 3.5374, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452372731781365e-05, + "loss": 3.5066, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0443986784270845e-05, + "loss": 3.5183, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435600836760325e-05, + "loss": 3.5223, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427231268053534e-05, + "loss": 3.5238, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0418845320543014e-05, + "loss": 3.5257, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410459373032498e-05, + "loss": 3.5287, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0402073425521978e-05, + "loss": 3.5127, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393703856815187e-05, + "loss": 3.5255, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385317909304667e-05, + "loss": 3.5221, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0376931961794147e-05, + "loss": 3.5163, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0368546014283627e-05, + "loss": 3.5124, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.036017644557684e-05, + "loss": 3.5242, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.035179049806632e-05, + "loss": 3.5269, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.03434045505558e-05, + "loss": 3.5059, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.033501860304528e-05, + "loss": 3.5173, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0326649034338488e-05, + "loss": 3.5102, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318263086827968e-05, + "loss": 3.5236, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.030987713931745e-05, + "loss": 3.5148, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.030149119180693e-05, + "loss": 3.5209, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029312162310014e-05, + "loss": 3.5233, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.028473567558962e-05, + "loss": 3.5267, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.027636610688283e-05, + "loss": 3.5176, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0267980159372313e-05, + "loss": 3.5239, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259594211861793e-05, + "loss": 3.5271, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251208264351273e-05, + "loss": 3.5167, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0242822316840753e-05, + "loss": 3.5099, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234436369330233e-05, + "loss": 3.5218, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0226050421819713e-05, + "loss": 3.5193, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217664474309192e-05, + "loss": 3.5259, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.02092949056024e-05, + "loss": 3.5181, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200908958091885e-05, + "loss": 3.5209, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192523010581365e-05, + "loss": 3.5158, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184153441874574e-05, + "loss": 3.5141, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0175767494364054e-05, + "loss": 3.5115, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167381546853534e-05, + "loss": 3.527, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0158995599343014e-05, + "loss": 3.5347, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150609651832494e-05, + "loss": 3.5189, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142240083125706e-05, + "loss": 3.5138, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0133854135615186e-05, + "loss": 3.5242, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125468188104666e-05, + "loss": 3.52, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0117082240594146e-05, + "loss": 3.5154, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0108696293083626e-05, + "loss": 3.5218, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100310345573106e-05, + "loss": 3.5332, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0091924398062586e-05, + "loss": 3.524, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.008353845055207e-05, + "loss": 3.52, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.007516888184528e-05, + "loss": 3.5141, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.006678293433476e-05, + "loss": 3.5241, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.005839698682424e-05, + "loss": 3.5218, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.005001103931372e-05, + "loss": 3.5102, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.004164147060693e-05, + "loss": 3.5392, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.003325552309641e-05, + "loss": 3.5182, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.002486957558589e-05, + "loss": 3.5238, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.001648362807537e-05, + "loss": 3.5206, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.000811405936858e-05, + "loss": 3.5182, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.8980231285095215, + "eval_runtime": 307.1951, + "eval_samples_per_second": 1242.178, + "eval_steps_per_second": 38.819, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.999972811185806e-05, + "loss": 3.5134, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.999134216434754e-05, + "loss": 3.5156, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9982956216837016e-05, + "loss": 3.5305, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974586648130232e-05, + "loss": 3.522, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966200700619712e-05, + "loss": 3.5241, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957814753109192e-05, + "loss": 3.5101, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.994942880559867e-05, + "loss": 3.5166, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.994104285808815e-05, + "loss": 3.5154, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.993265691057763e-05, + "loss": 3.5258, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.992427096306711e-05, + "loss": 3.5131, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9915901394360318e-05, + "loss": 3.5289, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9907515446849798e-05, + "loss": 3.526, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899129499339277e-05, + "loss": 3.5083, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.989074355182876e-05, + "loss": 3.5121, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.988237398312197e-05, + "loss": 3.5025, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.987398803561145e-05, + "loss": 3.508, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986560208810093e-05, + "loss": 3.5152, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.985721614059041e-05, + "loss": 3.5089, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9848846571883622e-05, + "loss": 3.5164, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840460624373102e-05, + "loss": 3.5337, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832074676862582e-05, + "loss": 3.5154, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823688729352062e-05, + "loss": 3.5169, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.981531916064527e-05, + "loss": 3.5166, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.980693321313475e-05, + "loss": 3.5131, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.979854726562423e-05, + "loss": 3.5163, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790161318113714e-05, + "loss": 3.5061, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9781791749406924e-05, + "loss": 3.5153, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.977342218070014e-05, + "loss": 3.5129, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765036233189613e-05, + "loss": 3.5017, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9756650285679093e-05, + "loss": 3.5178, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748264338168576e-05, + "loss": 3.5122, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9739878390658056e-05, + "loss": 3.5228, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731492443147536e-05, + "loss": 3.5154, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723106495637016e-05, + "loss": 3.5075, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714720548126496e-05, + "loss": 3.5141, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706350979419705e-05, + "loss": 3.5317, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9697965031909185e-05, + "loss": 3.5079, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689579084398668e-05, + "loss": 3.5124, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681193136888148e-05, + "loss": 3.5129, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9672823568181357e-05, + "loss": 3.5042, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664453999474566e-05, + "loss": 3.5104, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9656068051964046e-05, + "loss": 3.5268, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.964768210445353e-05, + "loss": 3.5226, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.963929615694301e-05, + "loss": 3.5129, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.963091020943249e-05, + "loss": 3.5198, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962252426192197e-05, + "loss": 3.5152, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961413831441145e-05, + "loss": 3.5187, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960575236690093e-05, + "loss": 3.4915, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959738279819414e-05, + "loss": 3.5126, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.958901322948735e-05, + "loss": 3.52, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.958062728197683e-05, + "loss": 3.515, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.957224133446631e-05, + "loss": 3.5125, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.956385538695579e-05, + "loss": 3.4996, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555485818249e-05, + "loss": 3.5158, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9547099870738483e-05, + "loss": 3.4997, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9538713923227963e-05, + "loss": 3.5257, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530327975717443e-05, + "loss": 3.5081, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9521942028206923e-05, + "loss": 3.5257, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513556080696403e-05, + "loss": 3.51, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505170133185883e-05, + "loss": 3.505, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9496784185675363e-05, + "loss": 3.5143, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488414616968572e-05, + "loss": 3.5082, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9480028669458055e-05, + "loss": 3.5088, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471642721947535e-05, + "loss": 3.5035, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463256774437015e-05, + "loss": 3.5173, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9454870826926495e-05, + "loss": 3.4987, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446484879415975e-05, + "loss": 3.5068, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.943809893190545e-05, + "loss": 3.4976, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9429712984394932e-05, + "loss": 3.5043, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421343415688148e-05, + "loss": 3.5203, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.941295746817762e-05, + "loss": 3.5133, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.94045715206671e-05, + "loss": 3.5086, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396201951960317e-05, + "loss": 3.5079, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9387816004449797e-05, + "loss": 3.5197, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379430056939273e-05, + "loss": 3.5155, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9371044109428753e-05, + "loss": 3.5114, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9362658161918233e-05, + "loss": 3.5126, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354272214407713e-05, + "loss": 3.5098, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9345902645700922e-05, + "loss": 3.5154, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337516698190402e-05, + "loss": 3.5107, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329130750679885e-05, + "loss": 3.5148, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9320744803169365e-05, + "loss": 3.5198, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312358855658845e-05, + "loss": 3.5104, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9303972908148325e-05, + "loss": 3.4942, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9295586960637805e-05, + "loss": 3.507, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287201013127285e-05, + "loss": 3.5133, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9278831444420494e-05, + "loss": 3.5129, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270445496909978e-05, + "loss": 3.5103, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262059549399458e-05, + "loss": 3.5054, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253673601888938e-05, + "loss": 3.513, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245320411985876e-05, + "loss": 3.5039, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9236934464475356e-05, + "loss": 3.5105, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.922854851696484e-05, + "loss": 3.5109, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.922016256945432e-05, + "loss": 3.5062, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.92117766219438e-05, + "loss": 3.5234, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.920339067443328e-05, + "loss": 3.4968, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.919500472692276e-05, + "loss": 3.4965, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918661877941224e-05, + "loss": 3.5133, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178249210705448e-05, + "loss": 3.512, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.916986326319493e-05, + "loss": 3.5128, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916147731568441e-05, + "loss": 3.5095, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915309136817389e-05, + "loss": 3.4979, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.91447217994671e-05, + "loss": 3.5068, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.913633585195658e-05, + "loss": 3.5133, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.912794990444606e-05, + "loss": 3.501, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.911956395693554e-05, + "loss": 3.4975, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9111194388228753e-05, + "loss": 3.5121, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9102808440718233e-05, + "loss": 3.5112, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9094422493207713e-05, + "loss": 3.4938, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086036545697193e-05, + "loss": 3.4998, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.90776669769904e-05, + "loss": 3.4987, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069281029479885e-05, + "loss": 3.5075, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9060895081969365e-05, + "loss": 3.5017, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052509134458845e-05, + "loss": 3.508, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044139565752054e-05, + "loss": 3.5083, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9035753618241534e-05, + "loss": 3.5139, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027384049534746e-05, + "loss": 3.4998, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9018998102024226e-05, + "loss": 3.5117, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9010612154513706e-05, + "loss": 3.5106, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002226207003186e-05, + "loss": 3.5052, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8993840259492666e-05, + "loss": 3.4936, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985470690785875e-05, + "loss": 3.5076, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977084743275355e-05, + "loss": 3.5062, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.896869879576484e-05, + "loss": 3.5101, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.896031284825432e-05, + "loss": 3.5019, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.89519269007438e-05, + "loss": 3.5112, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.894354095323328e-05, + "loss": 3.5034, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935171384526488e-05, + "loss": 3.5002, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8926785437015968e-05, + "loss": 3.4932, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8918399489505448e-05, + "loss": 3.5163, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8910013541994928e-05, + "loss": 3.5189, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8901627594484404e-05, + "loss": 3.5044, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.889325802577762e-05, + "loss": 3.496, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.88848720782671e-05, + "loss": 3.5153, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887648613075658e-05, + "loss": 3.5032, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8868100183246056e-05, + "loss": 3.5043, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8859714235735536e-05, + "loss": 3.5064, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8851328288225016e-05, + "loss": 3.5144, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8842942340714496e-05, + "loss": 3.5058, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8834572772007705e-05, + "loss": 3.5098, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826186824497185e-05, + "loss": 3.4966, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8817800876986665e-05, + "loss": 3.5097, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.880941492947615e-05, + "loss": 3.507, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.880102898196563e-05, + "loss": 3.4995, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.879264303445511e-05, + "loss": 3.5257, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.878425708694459e-05, + "loss": 3.5025, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.877587113943407e-05, + "loss": 3.5113, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767501570727278e-05, + "loss": 3.5078, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759115623216758e-05, + "loss": 3.5053, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.900068759918213, + "eval_runtime": 303.544, + "eval_samples_per_second": 1257.119, + "eval_steps_per_second": 39.286, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.875072967570624e-05, + "loss": 3.4984, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.874234372819572e-05, + "loss": 3.5062, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.873397415948893e-05, + "loss": 3.5133, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.872558821197841e-05, + "loss": 3.5097, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.871720226446789e-05, + "loss": 3.5139, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.870881631695737e-05, + "loss": 3.4954, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.870043036944685e-05, + "loss": 3.5017, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692044421936333e-05, + "loss": 3.5026, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8683658474425813e-05, + "loss": 3.5114, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675272526915293e-05, + "loss": 3.5011, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8666902958208502e-05, + "loss": 3.5108, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8658517010697982e-05, + "loss": 3.5121, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650131063187462e-05, + "loss": 3.4945, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.864174511567694e-05, + "loss": 3.4972, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633375546970154e-05, + "loss": 3.49, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8624989599459634e-05, + "loss": 3.497, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616603651949114e-05, + "loss": 3.4971, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608217704438588e-05, + "loss": 3.4964, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8599848135731803e-05, + "loss": 3.5022, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591462188221287e-05, + "loss": 3.5206, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583092619514496e-05, + "loss": 3.5012, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574706672003976e-05, + "loss": 3.4983, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566320724493456e-05, + "loss": 3.507, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8557934776982936e-05, + "loss": 3.5018, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549548829472412e-05, + "loss": 3.4988, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541162881961892e-05, + "loss": 3.4933, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532776934451372e-05, + "loss": 3.5013, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524390986940852e-05, + "loss": 3.498, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.851602141823406e-05, + "loss": 3.4841, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850763547072354e-05, + "loss": 3.5073, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499249523213025e-05, + "loss": 3.4928, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8490863575702505e-05, + "loss": 3.5096, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482494006995714e-05, + "loss": 3.5037, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474108059485194e-05, + "loss": 3.4893, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465722111974674e-05, + "loss": 3.505, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457336164464153e-05, + "loss": 3.514, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8448966595757366e-05, + "loss": 3.4911, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440580648246846e-05, + "loss": 3.5036, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432194700736326e-05, + "loss": 3.4967, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8423808753225806e-05, + "loss": 3.491, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.841545556332275e-05, + "loss": 3.4979, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.840706961581223e-05, + "loss": 3.5121, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839868366830171e-05, + "loss": 3.5057, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390297720791187e-05, + "loss": 3.499, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8381911773280667e-05, + "loss": 3.5094, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373525825770147e-05, + "loss": 3.4982, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365139878259627e-05, + "loss": 3.5044, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8356753930749107e-05, + "loss": 3.4824, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834838436204232e-05, + "loss": 3.496, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340014793335535e-05, + "loss": 3.5075, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.833162884582501e-05, + "loss": 3.5058, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.832324289831449e-05, + "loss": 3.4955, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831485695080397e-05, + "loss": 3.4873, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306487382097184e-05, + "loss": 3.5036, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.829810143458666e-05, + "loss": 3.4861, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.828971548707614e-05, + "loss": 3.5094, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.828132953956562e-05, + "loss": 3.499, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.82729435920551e-05, + "loss": 3.5124, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.826455764454458e-05, + "loss": 3.496, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.825617169703406e-05, + "loss": 3.4921, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.824778574952354e-05, + "loss": 3.4961, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239416180816753e-05, + "loss": 3.5022, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231030233306233e-05, + "loss": 3.491, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222644285795713e-05, + "loss": 3.4897, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214258338285193e-05, + "loss": 3.5051, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8205872390774673e-05, + "loss": 3.4909, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197486443264153e-05, + "loss": 3.4872, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189100495753633e-05, + "loss": 3.4881, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180714548243113e-05, + "loss": 3.4916, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172344979536325e-05, + "loss": 3.5033, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8163959032025805e-05, + "loss": 3.5014, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155573084515285e-05, + "loss": 3.4953, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147187137004765e-05, + "loss": 3.4943, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8138817568297974e-05, + "loss": 3.5031, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130431620787458e-05, + "loss": 3.4987, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122045673276938e-05, + "loss": 3.4962, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8113659725766418e-05, + "loss": 3.5028, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105273778255898e-05, + "loss": 3.4951, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8096904209549107e-05, + "loss": 3.5059, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8088518262038587e-05, + "loss": 3.496, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080132314528067e-05, + "loss": 3.5002, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071746367017543e-05, + "loss": 3.4994, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063360419507023e-05, + "loss": 3.4978, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8054974471996503e-05, + "loss": 3.4839, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046588524485983e-05, + "loss": 3.4924, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038202576975463e-05, + "loss": 3.4978, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8029833008268675e-05, + "loss": 3.5026, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021447060758155e-05, + "loss": 3.4971, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013061113247635e-05, + "loss": 3.4895, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004675165737115e-05, + "loss": 3.4984, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.799632197583406e-05, + "loss": 3.4907, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.798793602832354e-05, + "loss": 3.4987, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979550080813017e-05, + "loss": 3.4891, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971164133302497e-05, + "loss": 3.4967, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7962778185791977e-05, + "loss": 3.5057, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954392238281457e-05, + "loss": 3.4955, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946006290770937e-05, + "loss": 3.4785, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937620343260417e-05, + "loss": 3.4977, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.792925077455363e-05, + "loss": 3.4979, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.792086482704311e-05, + "loss": 3.4986, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791247887953259e-05, + "loss": 3.4967, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790409293202207e-05, + "loss": 3.4874, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7895723363315278e-05, + "loss": 3.4889, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887337415804758e-05, + "loss": 3.5003, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787895146829424e-05, + "loss": 3.483, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.787056552078372e-05, + "loss": 3.4902, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.786219595207693e-05, + "loss": 3.4985, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785381000456641e-05, + "loss": 3.4997, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784542405705589e-05, + "loss": 3.4756, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783703810954537e-05, + "loss": 3.4922, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828668540838583e-05, + "loss": 3.4825, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820282593328063e-05, + "loss": 3.4957, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7811896645817543e-05, + "loss": 3.4899, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803510698307023e-05, + "loss": 3.4879, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795141129600232e-05, + "loss": 3.5036, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7786755182089712e-05, + "loss": 3.4985, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778385613382924e-05, + "loss": 3.4871, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7769999665872404e-05, + "loss": 3.4987, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761613718361884e-05, + "loss": 3.4961, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753227770851364e-05, + "loss": 3.4924, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7744841823340844e-05, + "loss": 3.4777, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736472254634057e-05, + "loss": 3.4983, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728086307123536e-05, + "loss": 3.4899, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719700359613016e-05, + "loss": 3.4966, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711314412102496e-05, + "loss": 3.491, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7702944843395705e-05, + "loss": 3.4946, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694558895885185e-05, + "loss": 3.492, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686172948374665e-05, + "loss": 3.4874, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767778700086415e-05, + "loss": 3.4793, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.766940105335363e-05, + "loss": 3.5051, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.766101510584311e-05, + "loss": 3.5018, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765262915833259e-05, + "loss": 3.4921, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644259589625798e-05, + "loss": 3.4882, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7635873642115278e-05, + "loss": 3.4992, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627487694604758e-05, + "loss": 3.4926, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619101747094238e-05, + "loss": 3.4886, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761071579958372e-05, + "loss": 3.4883, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.76023298520732e-05, + "loss": 3.5033, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759394390456268e-05, + "loss": 3.491, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758557433585589e-05, + "loss": 3.503, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757718838834537e-05, + "loss": 3.4836, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756880244083485e-05, + "loss": 3.4972, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560416493324326e-05, + "loss": 3.4935, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552030545813806e-05, + "loss": 3.4859, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543660977107022e-05, + "loss": 3.5104, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535275029596502e-05, + "loss": 3.4914, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.752688908208598e-05, + "loss": 3.4943, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.751850313457546e-05, + "loss": 3.4924, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.751011718706494e-05, + "loss": 3.4935, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.9003090858459473, + "eval_runtime": 302.7595, + "eval_samples_per_second": 1260.377, + "eval_steps_per_second": 39.388, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7501747618358148e-05, + "loss": 3.4862, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493361670847628e-05, + "loss": 3.4925, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7484975723337108e-05, + "loss": 3.4997, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7476589775826588e-05, + "loss": 3.4965, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468203828316068e-05, + "loss": 3.5055, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.745983425960928e-05, + "loss": 3.4807, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.745144831209876e-05, + "loss": 3.4869, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.744306236458824e-05, + "loss": 3.4884, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743467641707772e-05, + "loss": 3.5001, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.74262904695672e-05, + "loss": 3.4897, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741790452205668e-05, + "loss": 3.4966, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.740951857454616e-05, + "loss": 3.498, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401132627035643e-05, + "loss": 3.4819, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7392763058328852e-05, + "loss": 3.4854, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384377110818332e-05, + "loss": 3.475, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7375991163307812e-05, + "loss": 3.4844, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7367605215797292e-05, + "loss": 3.4832, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359235647090505e-05, + "loss": 3.4829, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7350849699579985e-05, + "loss": 3.4861, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7342463752069464e-05, + "loss": 3.508, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334077804558944e-05, + "loss": 3.4881, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7325708235852154e-05, + "loss": 3.4865, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317322288341634e-05, + "loss": 3.4956, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7308936340831113e-05, + "loss": 3.4931, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7300550393320597e-05, + "loss": 3.4821, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292164445810077e-05, + "loss": 3.4797, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7283778498299557e-05, + "loss": 3.4909, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275408929592766e-05, + "loss": 3.4802, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267022982082246e-05, + "loss": 3.4758, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7258637034571726e-05, + "loss": 3.4923, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250251087061206e-05, + "loss": 3.4806, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.724186513955069e-05, + "loss": 3.4947, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233479192040162e-05, + "loss": 3.4891, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225093244529642e-05, + "loss": 3.4784, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7216707297019122e-05, + "loss": 3.4904, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208337728312338e-05, + "loss": 3.5025, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7199951780801815e-05, + "loss": 3.4765, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7191565833291295e-05, + "loss": 3.4914, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718319626458451e-05, + "loss": 3.481, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7174810317073984e-05, + "loss": 3.4819, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166424369563464e-05, + "loss": 3.4819, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158038422052943e-05, + "loss": 3.5001, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7149652474542427e-05, + "loss": 3.4899, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141282905835636e-05, + "loss": 3.4863, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7132896958325116e-05, + "loss": 3.4929, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7124511010814596e-05, + "loss": 3.4839, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116125063304076e-05, + "loss": 3.493, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7107739115793556e-05, + "loss": 3.4726, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7099353168283036e-05, + "loss": 3.4805, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7090983599576248e-05, + "loss": 3.4935, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7082597652065728e-05, + "loss": 3.4889, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074211704555208e-05, + "loss": 3.4835, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7065825757044688e-05, + "loss": 3.4781, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7057456188337897e-05, + "loss": 3.4881, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.704907024082738e-05, + "loss": 3.4731, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.704068429331686e-05, + "loss": 3.4929, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.703229834580634e-05, + "loss": 3.4865, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.702391239829582e-05, + "loss": 3.4969, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.70155264507853e-05, + "loss": 3.4878, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.700714050327478e-05, + "loss": 3.478, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.699875455576426e-05, + "loss": 3.4836, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.699038498705747e-05, + "loss": 3.4873, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6981999039546953e-05, + "loss": 3.4766, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6973613092036433e-05, + "loss": 3.4782, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965227144525913e-05, + "loss": 3.4878, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6956841197015393e-05, + "loss": 3.4791, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6948455249504872e-05, + "loss": 3.4712, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940069301994346e-05, + "loss": 3.4741, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.693168335448383e-05, + "loss": 3.4762, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6923313785777045e-05, + "loss": 3.4918, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6914927838266525e-05, + "loss": 3.4858, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906541890755998e-05, + "loss": 3.4805, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898155943245478e-05, + "loss": 3.4849, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6889786374538694e-05, + "loss": 3.4854, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.688140042702817e-05, + "loss": 3.49, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.687301447951765e-05, + "loss": 3.4827, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686462853200713e-05, + "loss": 3.4916, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856258963300346e-05, + "loss": 3.4868, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.684787301578982e-05, + "loss": 3.4887, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.68394870682793e-05, + "loss": 3.4834, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831101120768783e-05, + "loss": 3.4876, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6822731552062e-05, + "loss": 3.4886, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6814345604551472e-05, + "loss": 3.4856, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.680595965704095e-05, + "loss": 3.4736, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.679757370953043e-05, + "loss": 3.4799, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.678918776201991e-05, + "loss": 3.4847, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.678080181450939e-05, + "loss": 3.487, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772415866998875e-05, + "loss": 3.4868, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764029919488355e-05, + "loss": 3.4737, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6755660350781564e-05, + "loss": 3.4829, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747290782074773e-05, + "loss": 3.4811, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6738904834564253e-05, + "loss": 3.4865, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730518887053736e-05, + "loss": 3.4742, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722132939543216e-05, + "loss": 3.4839, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6713746992032696e-05, + "loss": 3.4938, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6705361044522176e-05, + "loss": 3.4805, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6696975097011656e-05, + "loss": 3.4655, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6688589149501136e-05, + "loss": 3.4853, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680219580794345e-05, + "loss": 3.4864, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.667183363328383e-05, + "loss": 3.4844, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.666344768577331e-05, + "loss": 3.485, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.665506173826279e-05, + "loss": 3.4743, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6646692169555998e-05, + "loss": 3.4751, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638306222045478e-05, + "loss": 3.485, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6629920274534957e-05, + "loss": 3.4729, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6621534327024437e-05, + "loss": 3.4768, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.661316475831765e-05, + "loss": 3.4821, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.660477881080713e-05, + "loss": 3.4876, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.659639286329661e-05, + "loss": 3.4599, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.658800691578609e-05, + "loss": 3.4802, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.65796373470793e-05, + "loss": 3.4701, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6571251399568782e-05, + "loss": 3.4814, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6562865452058262e-05, + "loss": 3.4782, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554479504547742e-05, + "loss": 3.4753, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546093557037222e-05, + "loss": 3.4893, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6537707609526702e-05, + "loss": 3.4862, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.652933804081991e-05, + "loss": 3.4727, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.652095209330939e-05, + "loss": 3.4839, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6512566145798874e-05, + "loss": 3.485, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504180198288354e-05, + "loss": 3.479, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6495794250777834e-05, + "loss": 3.4681, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6487424682071043e-05, + "loss": 3.4846, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479038734560523e-05, + "loss": 3.4786, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6470652787050003e-05, + "loss": 3.4818, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.646226683953948e-05, + "loss": 3.4814, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.645388089202896e-05, + "loss": 3.4838, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.644549494451844e-05, + "loss": 3.472, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.643710899700792e-05, + "loss": 3.4725, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642873942830113e-05, + "loss": 3.469, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6420353480790612e-05, + "loss": 3.4909, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6411967533280092e-05, + "loss": 3.4855, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6403581585769572e-05, + "loss": 3.4825, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.639521201706278e-05, + "loss": 3.4757, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.638682606955226e-05, + "loss": 3.4871, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.637844012204174e-05, + "loss": 3.4836, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.637005417453122e-05, + "loss": 3.475, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6361684605824434e-05, + "loss": 3.4793, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6353298658313914e-05, + "loss": 3.4877, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6344912710803393e-05, + "loss": 3.4782, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6336526763292873e-05, + "loss": 3.4901, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328140815782353e-05, + "loss": 3.4726, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6319754868271833e-05, + "loss": 3.4827, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311368920761313e-05, + "loss": 3.4764, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6302999352054526e-05, + "loss": 3.4731, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6294613404544006e-05, + "loss": 3.4972, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286227457033486e-05, + "loss": 3.4777, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6277841509522966e-05, + "loss": 3.4823, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6269455562012446e-05, + "loss": 3.4803, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6261069614501926e-05, + "loss": 3.4789, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.9031765460968018, + "eval_runtime": 302.4088, + "eval_samples_per_second": 1261.838, + "eval_steps_per_second": 39.433, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6252683666991406e-05, + "loss": 3.4724, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244297719480885e-05, + "loss": 3.4793, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6235928150774098e-05, + "loss": 3.4851, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227542203263578e-05, + "loss": 3.4833, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219156255753058e-05, + "loss": 3.4919, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6210770308242538e-05, + "loss": 3.4691, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202384360732018e-05, + "loss": 3.4781, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6193998413221494e-05, + "loss": 3.4681, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6185612465710974e-05, + "loss": 3.492, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177226518200454e-05, + "loss": 3.4731, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6168856949493663e-05, + "loss": 3.4842, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160471001983143e-05, + "loss": 3.4828, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152085054472623e-05, + "loss": 3.4752, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6143699106962107e-05, + "loss": 3.4651, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135329538255316e-05, + "loss": 3.47, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6126943590744796e-05, + "loss": 3.4664, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6118557643234276e-05, + "loss": 3.4742, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110171695723756e-05, + "loss": 3.4724, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6101802127016968e-05, + "loss": 3.4717, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093416179506448e-05, + "loss": 3.4911, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085030231995928e-05, + "loss": 3.4787, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6076660663289137e-05, + "loss": 3.4717, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068274715778617e-05, + "loss": 3.4831, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6059888768268097e-05, + "loss": 3.4814, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051502820757577e-05, + "loss": 3.4696, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.604311687324706e-05, + "loss": 3.4672, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603473092573654e-05, + "loss": 3.4818, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.602636135702975e-05, + "loss": 3.463, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601797540951923e-05, + "loss": 3.4669, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.600958946200871e-05, + "loss": 3.4746, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.600120351449819e-05, + "loss": 3.4704, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5992833945791402e-05, + "loss": 3.4812, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598444799828088e-05, + "loss": 3.4733, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597606205077036e-05, + "loss": 3.468, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596767610325984e-05, + "loss": 3.4779, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.595929015574932e-05, + "loss": 3.4887, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.59509042082388e-05, + "loss": 3.4669, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594251826072828e-05, + "loss": 3.4779, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934148692021494e-05, + "loss": 3.462, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5925762744510974e-05, + "loss": 3.4773, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917376797000454e-05, + "loss": 3.4638, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5908990849489934e-05, + "loss": 3.4886, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5900604901979414e-05, + "loss": 3.4773, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892218954468894e-05, + "loss": 3.474, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5883833006958374e-05, + "loss": 3.4819, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5875447059447854e-05, + "loss": 3.4722, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867077490741066e-05, + "loss": 3.479, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5858691543230546e-05, + "loss": 3.4639, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850321974523755e-05, + "loss": 3.4648, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5841936027013235e-05, + "loss": 3.482, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5833550079502715e-05, + "loss": 3.4741, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825164131992195e-05, + "loss": 3.4747, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.581677818448168e-05, + "loss": 3.4626, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580839223697115e-05, + "loss": 3.4744, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800022668264367e-05, + "loss": 3.4612, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5791636720753847e-05, + "loss": 3.4797, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783250773243327e-05, + "loss": 3.4741, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5774864825732804e-05, + "loss": 3.486, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766478878222284e-05, + "loss": 3.4761, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758092930711764e-05, + "loss": 3.4686, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5749706983201244e-05, + "loss": 3.4661, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741337414494453e-05, + "loss": 3.4775, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5732951466983933e-05, + "loss": 3.4657, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724565519473416e-05, + "loss": 3.4661, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716179571962896e-05, + "loss": 3.4734, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5707793624452376e-05, + "loss": 3.4711, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5699407676941856e-05, + "loss": 3.4585, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691021729431336e-05, + "loss": 3.4607, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5682635781920816e-05, + "loss": 3.463, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674282592017758e-05, + "loss": 3.4806, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5665896644507238e-05, + "loss": 3.473, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5657510696996717e-05, + "loss": 3.4678, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649124749486197e-05, + "loss": 3.4754, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5640738801975677e-05, + "loss": 3.4704, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632352854465157e-05, + "loss": 3.4815, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5623966906954637e-05, + "loss": 3.4621, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.561559733824785e-05, + "loss": 3.4836, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.560721139073733e-05, + "loss": 3.4683, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559882544322681e-05, + "loss": 3.4754, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.559043949571629e-05, + "loss": 3.4742, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558205354820577e-05, + "loss": 3.4705, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.557368397949898e-05, + "loss": 3.4789, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565298031988462e-05, + "loss": 3.4718, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5556912084477942e-05, + "loss": 3.4612, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548526136967422e-05, + "loss": 3.4675, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540140189456902e-05, + "loss": 3.4681, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5531754241946382e-05, + "loss": 3.4791, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523368294435862e-05, + "loss": 3.4739, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.551498234692534e-05, + "loss": 3.4618, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5506612778218554e-05, + "loss": 3.4725, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498243209511763e-05, + "loss": 3.465, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5489857262001243e-05, + "loss": 3.4724, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481471314490723e-05, + "loss": 3.4636, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473085366980203e-05, + "loss": 3.4723, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5464699419469683e-05, + "loss": 3.4824, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.545631347195916e-05, + "loss": 3.4658, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5447943903252376e-05, + "loss": 3.4565, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5439557955741856e-05, + "loss": 3.4731, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431172008231336e-05, + "loss": 3.4664, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542278606072081e-05, + "loss": 3.4775, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414400113210292e-05, + "loss": 3.4688, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406014165699772e-05, + "loss": 3.4639, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5397628218189252e-05, + "loss": 3.4664, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5389242270678732e-05, + "loss": 3.4748, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538087270197194e-05, + "loss": 3.4563, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537248675446142e-05, + "loss": 3.4671, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.53641008069509e-05, + "loss": 3.4694, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5355731238244113e-05, + "loss": 3.4756, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347345290733593e-05, + "loss": 3.447, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5338959343223073e-05, + "loss": 3.4676, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5330573395712553e-05, + "loss": 3.4643, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322203827005762e-05, + "loss": 3.4633, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5313817879495246e-05, + "loss": 3.4678, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305431931984726e-05, + "loss": 3.4617, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297045984474206e-05, + "loss": 3.4787, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5288676415767415e-05, + "loss": 3.4707, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.528030684706063e-05, + "loss": 3.4624, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5271920899550107e-05, + "loss": 3.4712, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5263534952039587e-05, + "loss": 3.4726, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255149004529067e-05, + "loss": 3.4682, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5246763057018547e-05, + "loss": 3.452, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238393488311756e-05, + "loss": 3.4743, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230007540801236e-05, + "loss": 3.4623, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5221621593290716e-05, + "loss": 3.4686, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.52132356457802e-05, + "loss": 3.4678, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.520486607707341e-05, + "loss": 3.4748, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.519648012956289e-05, + "loss": 3.4665, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.518809418205237e-05, + "loss": 3.4585, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.517970823454185e-05, + "loss": 3.4604, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171322287031328e-05, + "loss": 3.4751, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5162936339520808e-05, + "loss": 3.4732, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.515456677081402e-05, + "loss": 3.4714, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.51461808233035e-05, + "loss": 3.4641, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.513779487579298e-05, + "loss": 3.4734, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.512940892828246e-05, + "loss": 3.4674, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.512102298077194e-05, + "loss": 3.4625, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511265341206515e-05, + "loss": 3.4664, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104267464554633e-05, + "loss": 3.471, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5095881517044113e-05, + "loss": 3.471, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087495569533593e-05, + "loss": 3.4778, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079109622023073e-05, + "loss": 3.4598, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5070723674512553e-05, + "loss": 3.4727, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062354105805762e-05, + "loss": 3.4636, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5053968158295242e-05, + "loss": 3.4628, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5045582210784725e-05, + "loss": 3.4805, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037196263274205e-05, + "loss": 3.4677, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5028810315763685e-05, + "loss": 3.4695, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020440747056894e-05, + "loss": 3.4651, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012054799546374e-05, + "loss": 3.4708, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.9033446311950684, + "eval_runtime": 304.9045, + "eval_samples_per_second": 1251.51, + "eval_steps_per_second": 39.111, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.5003668852035854e-05, + "loss": 3.4651, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.4995282904525334e-05, + "loss": 3.4697, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4986913335818547e-05, + "loss": 3.4717, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4978527388308027e-05, + "loss": 3.4699, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4970141440797503e-05, + "loss": 3.4826, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4961755493286983e-05, + "loss": 3.4564, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4953369545776463e-05, + "loss": 3.4635, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4944983598265946e-05, + "loss": 3.4573, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4936597650755426e-05, + "loss": 3.4754, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4928211703244906e-05, + "loss": 3.4666, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4919842134538115e-05, + "loss": 3.4666, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4911456187027595e-05, + "loss": 3.4672, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4903070239517075e-05, + "loss": 3.4634, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4894684292006555e-05, + "loss": 3.4545, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4886314723299768e-05, + "loss": 3.4633, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4877928775789248e-05, + "loss": 3.4509, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4869542828278728e-05, + "loss": 3.4628, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4861173259571937e-05, + "loss": 3.4598, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4852787312061417e-05, + "loss": 3.4573, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4844401364550897e-05, + "loss": 3.4866, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.483601541704038e-05, + "loss": 3.4616, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4827629469529857e-05, + "loss": 3.4618, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4819243522019337e-05, + "loss": 3.4689, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4810857574508816e-05, + "loss": 3.4651, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4802471626998296e-05, + "loss": 3.4609, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.479410205829151e-05, + "loss": 3.4543, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.478571611078099e-05, + "loss": 3.4694, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.47773465420742e-05, + "loss": 3.4486, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.476896059456368e-05, + "loss": 3.4552, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4760574647053158e-05, + "loss": 3.458, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4752188699542638e-05, + "loss": 3.4582, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.474381913083585e-05, + "loss": 3.4702, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.473543318332533e-05, + "loss": 3.4641, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.472704723581481e-05, + "loss": 3.4594, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.471866128830429e-05, + "loss": 3.4647, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.471027534079377e-05, + "loss": 3.4741, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470188939328325e-05, + "loss": 3.4563, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.469350344577273e-05, + "loss": 3.4664, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4685133877065943e-05, + "loss": 3.4508, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4676747929555422e-05, + "loss": 3.4643, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4668361982044902e-05, + "loss": 3.45, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4659976034534382e-05, + "loss": 3.4777, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.4651590087023862e-05, + "loss": 3.465, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464322051831707e-05, + "loss": 3.462, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.4634834570806555e-05, + "loss": 3.469, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4626448623296035e-05, + "loss": 3.4615, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461806267578551e-05, + "loss": 3.4652, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.460967672827499e-05, + "loss": 3.4536, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4601307159568204e-05, + "loss": 3.451, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4592921212057684e-05, + "loss": 3.473, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4584535264547164e-05, + "loss": 3.4587, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4576149317036644e-05, + "loss": 3.4626, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.4567763369526124e-05, + "loss": 3.4537, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4559377422015604e-05, + "loss": 3.4623, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551007853308813e-05, + "loss": 3.451, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4542621905798293e-05, + "loss": 3.4654, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4534235958287773e-05, + "loss": 3.4607, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4525850010777256e-05, + "loss": 3.4754, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4517464063266736e-05, + "loss": 3.4631, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4509078115756216e-05, + "loss": 3.4541, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4500692168245692e-05, + "loss": 3.4592, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4492322599538905e-05, + "loss": 3.4628, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4483936652028385e-05, + "loss": 3.4515, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4475550704517865e-05, + "loss": 3.4568, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4467164757007345e-05, + "loss": 3.4578, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4458778809496825e-05, + "loss": 3.4607, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4450392861986305e-05, + "loss": 3.4456, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442006914475785e-05, + "loss": 3.4522, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4433620966965265e-05, + "loss": 3.45, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.442526777706221e-05, + "loss": 3.4665, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.441688182955169e-05, + "loss": 3.4607, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4408495882041166e-05, + "loss": 3.4574, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4400109934530646e-05, + "loss": 3.4611, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4391723987020126e-05, + "loss": 3.4582, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4383338039509606e-05, + "loss": 3.4728, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4374952091999086e-05, + "loss": 3.4498, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4366566144488566e-05, + "loss": 3.4688, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.435819657578178e-05, + "loss": 3.4612, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4349810628271258e-05, + "loss": 3.4606, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4341424680760738e-05, + "loss": 3.4641, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333038733250218e-05, + "loss": 3.4609, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4324669164543427e-05, + "loss": 3.4643, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.431628321703291e-05, + "loss": 3.4596, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.430789726952239e-05, + "loss": 3.4462, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.429951132201187e-05, + "loss": 3.4577, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4291125374501347e-05, + "loss": 3.4559, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4282739426990827e-05, + "loss": 3.4651, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4274353479480307e-05, + "loss": 3.4605, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4265967531969787e-05, + "loss": 3.4507, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4257597963263e-05, + "loss": 3.4605, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4249228394556212e-05, + "loss": 3.4536, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4240842447045692e-05, + "loss": 3.4631, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.423245649953517e-05, + "loss": 3.4473, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.422407055202465e-05, + "loss": 3.4613, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.421568460451413e-05, + "loss": 3.4755, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4207298657003612e-05, + "loss": 3.4526, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.419892908829682e-05, + "loss": 3.4392, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.41905431407863e-05, + "loss": 3.4606, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.418215719327578e-05, + "loss": 3.4591, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.417377124576526e-05, + "loss": 3.4623, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.416538529825474e-05, + "loss": 3.461, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.415699935074422e-05, + "loss": 3.4501, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4148613403233704e-05, + "loss": 3.4555, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.414022745572318e-05, + "loss": 3.4608, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4131857887016393e-05, + "loss": 3.447, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4123471939505873e-05, + "loss": 3.4542, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411508599199535e-05, + "loss": 3.4567, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4106700044484833e-05, + "loss": 3.4651, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4098330475778045e-05, + "loss": 3.4366, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4089944528267525e-05, + "loss": 3.4558, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4081574959560734e-05, + "loss": 3.4493, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4073189012050214e-05, + "loss": 3.4559, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4064803064539694e-05, + "loss": 3.4519, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4056417117029174e-05, + "loss": 3.4519, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4048047548322387e-05, + "loss": 3.4614, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4039661600811867e-05, + "loss": 3.4638, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4031275653301347e-05, + "loss": 3.4496, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4022889705790823e-05, + "loss": 3.4598, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4014503758280303e-05, + "loss": 3.4562, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.400613418957352e-05, + "loss": 3.4592, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3997748242063e-05, + "loss": 3.443, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3989362294552476e-05, + "loss": 3.4618, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3980976347041956e-05, + "loss": 3.4458, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3972590399531435e-05, + "loss": 3.4589, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3964204452020915e-05, + "loss": 3.4503, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3955834883314128e-05, + "loss": 3.4643, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3947448935803608e-05, + "loss": 3.4577, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3939062988293088e-05, + "loss": 3.447, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3930677040782568e-05, + "loss": 3.4446, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3922291093272048e-05, + "loss": 3.4666, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3913905145761528e-05, + "loss": 3.4555, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3905535577054737e-05, + "loss": 3.46, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.389714962954422e-05, + "loss": 3.4512, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.38887636820337e-05, + "loss": 3.4599, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.388037773452318e-05, + "loss": 3.4591, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3871991787012657e-05, + "loss": 3.4511, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386362221830587e-05, + "loss": 3.4518, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385523627079535e-05, + "loss": 3.4613, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384685032328483e-05, + "loss": 3.4596, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.383846437577431e-05, + "loss": 3.4664, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.383007842826379e-05, + "loss": 3.4453, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.382169248075327e-05, + "loss": 3.4587, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.381330653324275e-05, + "loss": 3.4512, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3804936964535958e-05, + "loss": 3.4541, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.379655101702544e-05, + "loss": 3.4639, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.378816506951492e-05, + "loss": 3.4511, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.37797791220044e-05, + "loss": 3.4639, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.377139317449388e-05, + "loss": 3.4475, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.376300722698336e-05, + "loss": 3.4644, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.9063405990600586, + "eval_runtime": 304.6618, + "eval_samples_per_second": 1252.507, + "eval_steps_per_second": 39.142, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3754621279472838e-05, + "loss": 3.4453, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374625171076605e-05, + "loss": 3.4587, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373786576325553e-05, + "loss": 3.4585, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.372947981574501e-05, + "loss": 3.4592, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.372109386823449e-05, + "loss": 3.4699, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.371270792072397e-05, + "loss": 3.4471, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370432197321345e-05, + "loss": 3.4482, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369593602570293e-05, + "loss": 3.4452, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3687566456996142e-05, + "loss": 3.4644, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679180509485622e-05, + "loss": 3.4589, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3670794561975102e-05, + "loss": 3.4532, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3662408614464582e-05, + "loss": 3.4589, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.365403904575779e-05, + "loss": 3.4455, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.364565309824727e-05, + "loss": 3.4431, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.363726715073675e-05, + "loss": 3.4503, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3628881203226235e-05, + "loss": 3.4386, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3620495255715715e-05, + "loss": 3.4501, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612125687008924e-05, + "loss": 3.4455, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3603739739498404e-05, + "loss": 3.445, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3595353791987884e-05, + "loss": 3.4795, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3586967844477364e-05, + "loss": 3.4485, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3578581896966843e-05, + "loss": 3.4515, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570195949456323e-05, + "loss": 3.4573, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3561810001945803e-05, + "loss": 3.4563, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3553440433239016e-05, + "loss": 3.4434, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545054485728492e-05, + "loss": 3.4468, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3536668538217972e-05, + "loss": 3.454, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528282590707452e-05, + "loss": 3.4375, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3519896643196936e-05, + "loss": 3.442, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3511510695686416e-05, + "loss": 3.4437, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3503124748175896e-05, + "loss": 3.4509, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3494755179469105e-05, + "loss": 3.4518, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486369231958585e-05, + "loss": 3.4513, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3477983284448065e-05, + "loss": 3.451, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3469597336937545e-05, + "loss": 3.4523, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3461211389427025e-05, + "loss": 3.4583, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3452825441916504e-05, + "loss": 3.4454, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3444455873209717e-05, + "loss": 3.4563, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436069925699197e-05, + "loss": 3.4375, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3427683978188673e-05, + "loss": 3.457, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419298030678153e-05, + "loss": 3.4347, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3410912083167637e-05, + "loss": 3.4689, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3402526135657117e-05, + "loss": 3.4538, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394156566950326e-05, + "loss": 3.4505, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3385770619439806e-05, + "loss": 3.4581, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3377384671929286e-05, + "loss": 3.4532, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3368998724418766e-05, + "loss": 3.4523, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3360612776908246e-05, + "loss": 3.4389, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3352243208201458e-05, + "loss": 3.4331, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3343857260690938e-05, + "loss": 3.4642, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3335471313180418e-05, + "loss": 3.4467, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327085365669898e-05, + "loss": 3.4539, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3318699418159375e-05, + "loss": 3.4429, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3310313470648858e-05, + "loss": 3.4494, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.330194390194207e-05, + "loss": 3.4397, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329355795443155e-05, + "loss": 3.4526, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285172006921027e-05, + "loss": 3.4467, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3276786059410507e-05, + "loss": 3.4616, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3268400111899987e-05, + "loss": 3.4568, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260014164389467e-05, + "loss": 3.439, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3251628216878947e-05, + "loss": 3.4477, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.324325864817216e-05, + "loss": 3.4541, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.323487270066164e-05, + "loss": 3.4398, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322648675315112e-05, + "loss": 3.446, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.32181008056406e-05, + "loss": 3.4488, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.320971485813008e-05, + "loss": 3.4489, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.320132891061956e-05, + "loss": 3.4347, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319295934191277e-05, + "loss": 3.4412, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318457339440225e-05, + "loss": 3.437, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317618744689173e-05, + "loss": 3.4538, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3167801499381208e-05, + "loss": 3.4468, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3159415551870688e-05, + "loss": 3.4441, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3151029604360168e-05, + "loss": 3.4532, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3142660035653384e-05, + "loss": 3.4429, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.313427408814286e-05, + "loss": 3.4612, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.312588814063234e-05, + "loss": 3.4373, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.311750219312182e-05, + "loss": 3.455, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.310913262441503e-05, + "loss": 3.4497, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3100746676904513e-05, + "loss": 3.4473, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3092360729393993e-05, + "loss": 3.4556, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3083974781883473e-05, + "loss": 3.4496, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.307560521317668e-05, + "loss": 3.4536, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.306721926566616e-05, + "loss": 3.4504, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.305883331815564e-05, + "loss": 3.435, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.305044737064512e-05, + "loss": 3.449, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3042061423134605e-05, + "loss": 3.4423, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3033675475624085e-05, + "loss": 3.4536, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025289528113565e-05, + "loss": 3.4451, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.301690358060304e-05, + "loss": 3.439, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3008534011896254e-05, + "loss": 3.449, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000164443189466e-05, + "loss": 3.4481, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2991778495678946e-05, + "loss": 3.4476, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2983392548168426e-05, + "loss": 3.4374, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975006600657906e-05, + "loss": 3.4502, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2966620653147386e-05, + "loss": 3.4609, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958234705636863e-05, + "loss": 3.4443, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2949865136930075e-05, + "loss": 3.4269, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2941479189419555e-05, + "loss": 3.4497, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.293309324190904e-05, + "loss": 3.4457, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2924707294398515e-05, + "loss": 3.4491, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2916321346887995e-05, + "loss": 3.4517, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2907935399377475e-05, + "loss": 3.4431, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2899549451866955e-05, + "loss": 3.4423, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891163504356435e-05, + "loss": 3.4498, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2882793935649647e-05, + "loss": 3.4341, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2874407988139127e-05, + "loss": 3.4449, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866022040628607e-05, + "loss": 3.442, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2857636093118087e-05, + "loss": 3.4524, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2849266524411296e-05, + "loss": 3.4283, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2840880576900776e-05, + "loss": 3.4383, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.283251100819399e-05, + "loss": 3.443, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282412506068347e-05, + "loss": 3.4442, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281573911317295e-05, + "loss": 3.4412, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280735316566243e-05, + "loss": 3.4378, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279896721815191e-05, + "loss": 3.4537, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279058127064139e-05, + "loss": 3.4508, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278219532313087e-05, + "loss": 3.4356, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277382575442408e-05, + "loss": 3.451, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276543980691356e-05, + "loss": 3.4406, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.275705385940304e-05, + "loss": 3.4497, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2748667911892518e-05, + "loss": 3.4361, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274029834318573e-05, + "loss": 3.4445, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2731912395675213e-05, + "loss": 3.435, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.272352644816469e-05, + "loss": 3.4491, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.271514050065417e-05, + "loss": 3.4417, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2706770931947382e-05, + "loss": 3.4507, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2698384984436862e-05, + "loss": 3.4443, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.268999903692634e-05, + "loss": 3.4414, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2681613089415822e-05, + "loss": 3.4285, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2673227141905302e-05, + "loss": 3.4588, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2664841194394782e-05, + "loss": 3.4419, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2656455246884262e-05, + "loss": 3.4498, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.264808567817747e-05, + "loss": 3.4377, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.263969973066695e-05, + "loss": 3.452, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.263131378315643e-05, + "loss": 3.4453, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2622927835645914e-05, + "loss": 3.4396, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2614541888135394e-05, + "loss": 3.4419, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606172319428603e-05, + "loss": 3.4484, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2597786371918083e-05, + "loss": 3.4453, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2589400424407563e-05, + "loss": 3.4613, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581014476897043e-05, + "loss": 3.4292, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2572628529386523e-05, + "loss": 3.45, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2564242581876003e-05, + "loss": 3.4351, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2555856634365483e-05, + "loss": 3.4459, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2547487065658696e-05, + "loss": 3.4488, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539101118148172e-05, + "loss": 3.4383, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2530715170637652e-05, + "loss": 3.4534, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2522329223127132e-05, + "loss": 3.4418, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2513943275616616e-05, + "loss": 3.4495, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.9083900451660156, + "eval_runtime": 307.1074, + "eval_samples_per_second": 1242.533, + "eval_steps_per_second": 38.83, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2505557328106095e-05, + "loss": 3.4398, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2497187759399305e-05, + "loss": 3.4433, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2488801811888785e-05, + "loss": 3.4498, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2480415864378264e-05, + "loss": 3.4463, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472029916867744e-05, + "loss": 3.4537, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2463660348160957e-05, + "loss": 3.4411, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2455274400650437e-05, + "loss": 3.4307, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2446888453139917e-05, + "loss": 3.4382, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2438502505629397e-05, + "loss": 3.4487, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430116558118877e-05, + "loss": 3.449, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2421730610608353e-05, + "loss": 3.4417, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2413344663097837e-05, + "loss": 3.4492, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2404958715587317e-05, + "loss": 3.4308, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2396605525684258e-05, + "loss": 3.4344, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2388219578173738e-05, + "loss": 3.4406, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2379833630663218e-05, + "loss": 3.4274, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2371447683152698e-05, + "loss": 3.441, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.236307811444591e-05, + "loss": 3.4296, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.235469216693539e-05, + "loss": 3.4334, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.234630621942487e-05, + "loss": 3.4662, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233792027191435e-05, + "loss": 3.4361, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2329534324403827e-05, + "loss": 3.4387, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2321148376893307e-05, + "loss": 3.4441, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2312762429382787e-05, + "loss": 3.4499, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2304392860676e-05, + "loss": 3.4253, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.229600691316548e-05, + "loss": 3.4361, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.228762096565496e-05, + "loss": 3.4409, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.227923501814444e-05, + "loss": 3.4323, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.227084907063392e-05, + "loss": 3.4343, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.22624631231234e-05, + "loss": 3.432, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.225407717561288e-05, + "loss": 3.4411, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.224570760690609e-05, + "loss": 3.4446, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.223732165939557e-05, + "loss": 3.4392, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.222893571188505e-05, + "loss": 3.4392, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.222054976437453e-05, + "loss": 3.4383, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2212163816864008e-05, + "loss": 3.4475, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220377786935349e-05, + "loss": 3.4342, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2195408300646704e-05, + "loss": 3.4518, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.218702235313618e-05, + "loss": 3.4256, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.217863640562566e-05, + "loss": 3.4443, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.217025045811514e-05, + "loss": 3.4241, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216186451060462e-05, + "loss": 3.4566, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.21534785630941e-05, + "loss": 3.4387, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2145108994387313e-05, + "loss": 3.442, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2136723046876793e-05, + "loss": 3.4455, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2128337099366273e-05, + "loss": 3.4426, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2119951151855753e-05, + "loss": 3.4452, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2111565204345233e-05, + "loss": 3.4308, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2103195635638445e-05, + "loss": 3.42, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2094809688127925e-05, + "loss": 3.4542, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2086423740617405e-05, + "loss": 3.4326, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2078037793106885e-05, + "loss": 3.4476, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.206965184559636e-05, + "loss": 3.4303, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.206126589808584e-05, + "loss": 3.4371, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2052896329379054e-05, + "loss": 3.4255, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2044510381868534e-05, + "loss": 3.4421, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2036124434358014e-05, + "loss": 3.4404, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2027738486847494e-05, + "loss": 3.4464, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2019352539336974e-05, + "loss": 3.444, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2010966591826454e-05, + "loss": 3.4282, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2002580644315934e-05, + "loss": 3.4344, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1994211075609146e-05, + "loss": 3.4479, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1985825128098626e-05, + "loss": 3.4268, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1977439180588106e-05, + "loss": 3.4345, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1969053233077586e-05, + "loss": 3.4356, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1960683664370795e-05, + "loss": 3.443, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1952297716860275e-05, + "loss": 3.4238, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1943911769349755e-05, + "loss": 3.4296, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193552582183924e-05, + "loss": 3.4294, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1927156253132447e-05, + "loss": 3.4339, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1918770305621927e-05, + "loss": 3.4377, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1910384358111407e-05, + "loss": 3.4352, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1901998410600887e-05, + "loss": 3.4417, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1893612463090364e-05, + "loss": 3.432, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885226515579847e-05, + "loss": 3.454, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1876840568069327e-05, + "loss": 3.4264, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.186847099936254e-05, + "loss": 3.4442, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1860085051852016e-05, + "loss": 3.4373, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1851699104341496e-05, + "loss": 3.4343, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1843313156830976e-05, + "loss": 3.4443, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1834927209320456e-05, + "loss": 3.4385, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.182655764061367e-05, + "loss": 3.4352, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.181817169310315e-05, + "loss": 3.438, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.180978574559263e-05, + "loss": 3.4256, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180139979808211e-05, + "loss": 3.4355, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179301385057159e-05, + "loss": 3.4336, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.17846442818648e-05, + "loss": 3.4446, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.177625833435428e-05, + "loss": 3.4353, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.176787238684376e-05, + "loss": 3.4277, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.175948643933324e-05, + "loss": 3.4351, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.175111687062645e-05, + "loss": 3.4398, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174273092311593e-05, + "loss": 3.436, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173434497560541e-05, + "loss": 3.4248, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1725959028094893e-05, + "loss": 3.4386, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1717573080584373e-05, + "loss": 3.448, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.170918713307385e-05, + "loss": 3.4344, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1700817564367062e-05, + "loss": 3.4176, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1692431616856542e-05, + "loss": 3.4365, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168404566934602e-05, + "loss": 3.4294, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1675659721835502e-05, + "loss": 3.4412, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1667273774324982e-05, + "loss": 3.4403, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1658887826814462e-05, + "loss": 3.4294, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1650501879303942e-05, + "loss": 3.4301, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1642115931793422e-05, + "loss": 3.4384, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163374636308663e-05, + "loss": 3.4238, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162536041557611e-05, + "loss": 3.4332, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1616974468065594e-05, + "loss": 3.4276, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1608588520555074e-05, + "loss": 3.4453, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1600218951848283e-05, + "loss": 3.419, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1591833004337763e-05, + "loss": 3.4232, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1583463435630972e-05, + "loss": 3.4293, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1575077488120456e-05, + "loss": 3.4388, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1566691540609936e-05, + "loss": 3.4253, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1558305593099416e-05, + "loss": 3.4289, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1549919645588896e-05, + "loss": 3.4373, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1541533698078376e-05, + "loss": 3.4396, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1533147750567852e-05, + "loss": 3.4254, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1524778181861065e-05, + "loss": 3.4423, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1516392234350548e-05, + "loss": 3.4297, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1508006286840024e-05, + "loss": 3.4344, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1499620339329504e-05, + "loss": 3.4293, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1491250770622717e-05, + "loss": 3.4334, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1482864823112197e-05, + "loss": 3.4246, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1474478875601677e-05, + "loss": 3.4347, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1466092928091157e-05, + "loss": 3.4361, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.145772335938437e-05, + "loss": 3.4354, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.144933741187385e-05, + "loss": 3.4321, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1440951464363326e-05, + "loss": 3.4317, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1432565516852806e-05, + "loss": 3.4188, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1424179569342286e-05, + "loss": 3.4458, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1415793621831766e-05, + "loss": 3.4314, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140740767432125e-05, + "loss": 3.4381, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1399038105614458e-05, + "loss": 3.4286, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1390652158103938e-05, + "loss": 3.4454, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1382266210593418e-05, + "loss": 3.4314, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1373880263082898e-05, + "loss": 3.4288, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1365494315572378e-05, + "loss": 3.4308, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.135712474686559e-05, + "loss": 3.4339, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.134873879935507e-05, + "loss": 3.4344, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.134035285184455e-05, + "loss": 3.4499, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.133196690433403e-05, + "loss": 3.4192, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1323580956823507e-05, + "loss": 3.4362, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.131521138811672e-05, + "loss": 3.4281, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1306825440606203e-05, + "loss": 3.4357, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.129843949309568e-05, + "loss": 3.4339, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.129005354558516e-05, + "loss": 3.4299, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.128166759807464e-05, + "loss": 3.4395, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127329802936785e-05, + "loss": 3.4312, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126491208185733e-05, + "loss": 3.4367, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.9119153022766113, + "eval_runtime": 306.371, + "eval_samples_per_second": 1245.519, + "eval_steps_per_second": 38.923, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.125652613434681e-05, + "loss": 3.4322, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124814018683629e-05, + "loss": 3.4267, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1239770618129504e-05, + "loss": 3.4369, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.123138467061898e-05, + "loss": 3.4365, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.122299872310846e-05, + "loss": 3.4451, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.121461277559794e-05, + "loss": 3.4265, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1206226828087424e-05, + "loss": 3.4214, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1197840880576904e-05, + "loss": 3.4245, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1189471311870113e-05, + "loss": 3.4413, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181085364359593e-05, + "loss": 3.4412, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1172699416849073e-05, + "loss": 3.4277, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1164313469338553e-05, + "loss": 3.4381, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1155927521828033e-05, + "loss": 3.4241, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1147541574317513e-05, + "loss": 3.423, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139155626806993e-05, + "loss": 3.4263, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1130769679296473e-05, + "loss": 3.4208, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1122400110589685e-05, + "loss": 3.4267, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111401416307916e-05, + "loss": 3.421, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110562821556864e-05, + "loss": 3.4205, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1097242268058125e-05, + "loss": 3.4536, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1088872699351334e-05, + "loss": 3.4281, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1080503130644546e-05, + "loss": 3.4244, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072117183134026e-05, + "loss": 3.4312, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1063731235623506e-05, + "loss": 3.4369, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1055345288112986e-05, + "loss": 3.4182, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.10469757194062e-05, + "loss": 3.4285, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103858977189568e-05, + "loss": 3.4295, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.103020382438516e-05, + "loss": 3.424, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1021817876874635e-05, + "loss": 3.4181, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1013431929364115e-05, + "loss": 3.4205, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1005045981853595e-05, + "loss": 3.4311, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0996676413146808e-05, + "loss": 3.4323, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0988290465636288e-05, + "loss": 3.4271, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0979904518125768e-05, + "loss": 3.4265, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0971518570615248e-05, + "loss": 3.427, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963132623104728e-05, + "loss": 3.4326, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0954746675594207e-05, + "loss": 3.4275, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094637710688742e-05, + "loss": 3.4352, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.09379911593769e-05, + "loss": 3.4168, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.092960521186638e-05, + "loss": 3.4305, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.092121926435586e-05, + "loss": 3.4149, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0912833316845336e-05, + "loss": 3.4425, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0904447369334816e-05, + "loss": 3.4308, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896061421824296e-05, + "loss": 3.4277, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0887691853117512e-05, + "loss": 3.4378, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.087930590560699e-05, + "loss": 3.4297, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.087091995809647e-05, + "loss": 3.4308, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.086253401058595e-05, + "loss": 3.4224, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.085414806307543e-05, + "loss": 3.4028, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084577849436864e-05, + "loss": 3.4444, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.083739254685812e-05, + "loss": 3.422, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.08290065993476e-05, + "loss": 3.4361, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.082062065183708e-05, + "loss": 3.4218, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.081223470432656e-05, + "loss": 3.4248, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.080386513561977e-05, + "loss": 3.4122, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079547918810925e-05, + "loss": 3.4315, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787093240598733e-05, + "loss": 3.4289, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0778707293088213e-05, + "loss": 3.4324, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0770321345577693e-05, + "loss": 3.4372, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.076193539806717e-05, + "loss": 3.416, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.075354945055665e-05, + "loss": 3.4244, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0745179881849862e-05, + "loss": 3.4371, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0736793934339342e-05, + "loss": 3.4162, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0728407986828822e-05, + "loss": 3.4205, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720022039318302e-05, + "loss": 3.4243, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0711636091807782e-05, + "loss": 3.428, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.070326652310099e-05, + "loss": 3.415, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.069488057559047e-05, + "loss": 3.4199, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.068649462807995e-05, + "loss": 3.4159, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0678108680569434e-05, + "loss": 3.4246, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0669722733058914e-05, + "loss": 3.4279, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0661336785548394e-05, + "loss": 3.4256, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0652950838037874e-05, + "loss": 3.4271, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0644581269331083e-05, + "loss": 3.4251, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0636195321820563e-05, + "loss": 3.44, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0627809374310043e-05, + "loss": 3.4153, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0619423426799527e-05, + "loss": 3.4361, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611053858092736e-05, + "loss": 3.4251, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0602667910582216e-05, + "loss": 3.4195, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0594281963071696e-05, + "loss": 3.4364, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0585896015561172e-05, + "loss": 3.4288, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0577526446854388e-05, + "loss": 3.4259, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569140499343868e-05, + "loss": 3.4278, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0560754551833348e-05, + "loss": 3.4145, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0552368604322825e-05, + "loss": 3.4237, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0543982656812305e-05, + "loss": 3.4222, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0535596709301784e-05, + "loss": 3.4356, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0527210761791264e-05, + "loss": 3.4215, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0518841193084477e-05, + "loss": 3.422, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0510455245573957e-05, + "loss": 3.4169, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502069298063437e-05, + "loss": 3.4275, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0493683350552917e-05, + "loss": 3.4277, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0485297403042397e-05, + "loss": 3.4145, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0476927834335606e-05, + "loss": 3.4291, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046854188682509e-05, + "loss": 3.4333, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.046015593931457e-05, + "loss": 3.4243, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.045176999180405e-05, + "loss": 3.4084, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.044338404429353e-05, + "loss": 3.4244, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0434998096783006e-05, + "loss": 3.4171, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0426612149272486e-05, + "loss": 3.43, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0418226201761966e-05, + "loss": 3.4274, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.040985663305518e-05, + "loss": 3.4195, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0401470685544658e-05, + "loss": 3.4208, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393084738034138e-05, + "loss": 3.4211, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0384698790523618e-05, + "loss": 3.4176, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0376329221816827e-05, + "loss": 3.4232, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036794327430631e-05, + "loss": 3.4148, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.035955732679579e-05, + "loss": 3.4337, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.035117137928527e-05, + "loss": 3.4068, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034280181057848e-05, + "loss": 3.4133, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033441586306796e-05, + "loss": 3.4182, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032602991555744e-05, + "loss": 3.4264, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031764396804692e-05, + "loss": 3.4137, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.03092580205364e-05, + "loss": 3.4186, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0300872073025882e-05, + "loss": 3.4263, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029250250431909e-05, + "loss": 3.4298, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028411655680857e-05, + "loss": 3.4135, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027573060929805e-05, + "loss": 3.4277, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026734466178753e-05, + "loss": 3.4235, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0258975093080744e-05, + "loss": 3.421, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0250589145570224e-05, + "loss": 3.4183, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0242203198059704e-05, + "loss": 3.4199, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0233817250549184e-05, + "loss": 3.4173, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.022543130303866e-05, + "loss": 3.4252, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.021704535552814e-05, + "loss": 3.4257, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0208675786821353e-05, + "loss": 3.423, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0200289839310833e-05, + "loss": 3.4204, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0191903891800313e-05, + "loss": 3.4194, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0183517944289793e-05, + "loss": 3.4088, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0175131996779273e-05, + "loss": 3.4373, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0166746049268753e-05, + "loss": 3.4173, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0158376480561965e-05, + "loss": 3.4258, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0149990533051445e-05, + "loss": 3.4155, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0141604585540925e-05, + "loss": 3.4325, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0133218638030405e-05, + "loss": 3.4208, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0124832690519885e-05, + "loss": 3.4161, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0116446743009365e-05, + "loss": 3.4214, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108077174302574e-05, + "loss": 3.4205, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0099691226792057e-05, + "loss": 3.4213, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0091305279281537e-05, + "loss": 3.4435, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0082919331771014e-05, + "loss": 3.4062, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0074549763064226e-05, + "loss": 3.4293, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0066163815553706e-05, + "loss": 3.4167, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0057777868043186e-05, + "loss": 3.4257, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0049391920532666e-05, + "loss": 3.4211, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041005973022146e-05, + "loss": 3.4232, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0032620025511626e-05, + "loss": 3.427, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.002425045680484e-05, + "loss": 3.42, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0015864509294315e-05, + "loss": 3.4234, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.913802146911621, + "eval_runtime": 302.641, + "eval_samples_per_second": 1260.87, + "eval_steps_per_second": 39.403, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0007478561783795e-05, + "loss": 3.4196, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9999092614273275e-05, + "loss": 3.4191, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9990723045566488e-05, + "loss": 3.4264, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9982337098055967e-05, + "loss": 3.424, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9973951150545447e-05, + "loss": 3.4349, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9965565203034927e-05, + "loss": 3.4158, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9957179255524407e-05, + "loss": 3.4116, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9948793308013887e-05, + "loss": 3.4165, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.99404237393071e-05, + "loss": 3.4253, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993203779179658e-05, + "loss": 3.4287, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992365184428606e-05, + "loss": 3.4154, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991526589677554e-05, + "loss": 3.425, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990687994926502e-05, + "loss": 3.4159, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989851038055823e-05, + "loss": 3.4111, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9890124433047712e-05, + "loss": 3.4173, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9881738485537192e-05, + "loss": 3.408, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.987335253802667e-05, + "loss": 3.4145, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986498296931988e-05, + "loss": 3.4082, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985659702180936e-05, + "loss": 3.4113, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984821107429884e-05, + "loss": 3.4389, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.983982512678832e-05, + "loss": 3.4222, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.98314391792778e-05, + "loss": 3.4174, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.982305323176728e-05, + "loss": 3.4198, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981466728425676e-05, + "loss": 3.4254, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.980629771554997e-05, + "loss": 3.4024, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.979791176803945e-05, + "loss": 3.4211, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.978952582052893e-05, + "loss": 3.4207, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9781139873018413e-05, + "loss": 3.4091, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9772753925507893e-05, + "loss": 3.4047, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9764367977997373e-05, + "loss": 3.4119, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.975598203048685e-05, + "loss": 3.4195, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9747612461780062e-05, + "loss": 3.4247, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9739226514269542e-05, + "loss": 3.4165, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9730840566759022e-05, + "loss": 3.4181, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9722454619248502e-05, + "loss": 3.4163, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9714068671737982e-05, + "loss": 3.4207, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9705682724227462e-05, + "loss": 3.4168, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.969731315552067e-05, + "loss": 3.4229, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.968892720801015e-05, + "loss": 3.4034, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.968054126049963e-05, + "loss": 3.4181, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9672155312989114e-05, + "loss": 3.4083, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9663769365478594e-05, + "loss": 3.4282, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9655383417968074e-05, + "loss": 3.4217, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9647013849261283e-05, + "loss": 3.4155, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9638627901750763e-05, + "loss": 3.427, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9630241954240243e-05, + "loss": 3.4161, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9621856006729723e-05, + "loss": 3.4245, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9613470059219206e-05, + "loss": 3.4105, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9605100490512416e-05, + "loss": 3.39, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9596714543001896e-05, + "loss": 3.4325, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9588328595491375e-05, + "loss": 3.4117, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9579942647980852e-05, + "loss": 3.429, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9571556700470335e-05, + "loss": 3.4114, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9563170752959815e-05, + "loss": 3.4105, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9554801184253028e-05, + "loss": 3.4045, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9546415236742504e-05, + "loss": 3.417, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9538029289231984e-05, + "loss": 3.4223, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9529643341721464e-05, + "loss": 3.4187, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9521257394210944e-05, + "loss": 3.4297, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9512871446700424e-05, + "loss": 3.4085, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9504485499189908e-05, + "loss": 3.4086, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9496115930483117e-05, + "loss": 3.4271, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9487729982972597e-05, + "loss": 3.4064, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9479344035462077e-05, + "loss": 3.4111, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9470958087951557e-05, + "loss": 3.4105, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.946258851924477e-05, + "loss": 3.4211, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.945420257173425e-05, + "loss": 3.4026, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.944581662422373e-05, + "loss": 3.4092, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943743067671321e-05, + "loss": 3.4044, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9429061108006418e-05, + "loss": 3.4109, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9420675160495898e-05, + "loss": 3.4193, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9412289212985378e-05, + "loss": 3.4095, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940390326547486e-05, + "loss": 3.416, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9395517317964338e-05, + "loss": 3.4123, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9387131370453818e-05, + "loss": 3.4326, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9378745422943298e-05, + "loss": 3.4059, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9370359475432778e-05, + "loss": 3.4237, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936198990672599e-05, + "loss": 3.4153, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935360395921547e-05, + "loss": 3.4083, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934521801170495e-05, + "loss": 3.4233, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933683206419443e-05, + "loss": 3.4202, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.932846249548764e-05, + "loss": 3.4147, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.932007654797712e-05, + "loss": 3.416, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.93116906004666e-05, + "loss": 3.4078, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9303304652956082e-05, + "loss": 3.4075, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9294918705445562e-05, + "loss": 3.4119, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9286532757935042e-05, + "loss": 3.4235, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.927814681042452e-05, + "loss": 3.4102, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.926977724171773e-05, + "loss": 3.4122, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.926139129420721e-05, + "loss": 3.4097, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.925300534669669e-05, + "loss": 3.4192, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924461939918617e-05, + "loss": 3.4157, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.923623345167565e-05, + "loss": 3.4041, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.922784750416513e-05, + "loss": 3.4194, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.921946155665461e-05, + "loss": 3.4226, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.921107560914409e-05, + "loss": 3.4154, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.92027060404373e-05, + "loss": 3.3968, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9194320092926783e-05, + "loss": 3.4145, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9185934145416263e-05, + "loss": 3.4053, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9177548197905743e-05, + "loss": 3.4185, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.916916225039522e-05, + "loss": 3.4149, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.91607763028847e-05, + "loss": 3.4163, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.915239035537418e-05, + "loss": 3.4081, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.914400440786366e-05, + "loss": 3.4095, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9135634839156872e-05, + "loss": 3.4081, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9127248891646352e-05, + "loss": 3.4102, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9118862944135832e-05, + "loss": 3.4036, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9110476996625312e-05, + "loss": 3.4239, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.910210742791852e-05, + "loss": 3.3984, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9093737859211737e-05, + "loss": 3.3997, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9085351911701217e-05, + "loss": 3.4114, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9076965964190694e-05, + "loss": 3.4107, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9068580016680174e-05, + "loss": 3.4081, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9060194069169654e-05, + "loss": 3.4071, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9051808121659133e-05, + "loss": 3.4152, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9043422174148613e-05, + "loss": 3.4209, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9035036226638093e-05, + "loss": 3.4016, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9026666657931306e-05, + "loss": 3.414, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9018280710420786e-05, + "loss": 3.4133, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9009894762910266e-05, + "loss": 3.4134, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9001508815399746e-05, + "loss": 3.4096, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8993139246692955e-05, + "loss": 3.4051, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8984753299182438e-05, + "loss": 3.4058, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8976367351671918e-05, + "loss": 3.4137, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8967981404161398e-05, + "loss": 3.4141, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8959611835454607e-05, + "loss": 3.4112, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8951225887944087e-05, + "loss": 3.4119, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8942839940433567e-05, + "loss": 3.4097, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8934453992923047e-05, + "loss": 3.3971, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8926068045412527e-05, + "loss": 3.4223, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.891769847670574e-05, + "loss": 3.403, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.890931252919522e-05, + "loss": 3.4218, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.89009265816847e-05, + "loss": 3.4029, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8892540634174176e-05, + "loss": 3.4231, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8884171065467392e-05, + "loss": 3.4098, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8875785117956872e-05, + "loss": 3.4067, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886739917044635e-05, + "loss": 3.4107, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.885901322293583e-05, + "loss": 3.4122, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8850627275425308e-05, + "loss": 3.4145, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.884225770671852e-05, + "loss": 3.4292, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8833871759208e-05, + "loss": 3.3981, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882548581169748e-05, + "loss": 3.4211, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.881709986418696e-05, + "loss": 3.4039, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.880871391667644e-05, + "loss": 3.4118, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.880034434796965e-05, + "loss": 3.4113, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.879195840045913e-05, + "loss": 3.41, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.878357245294861e-05, + "loss": 3.4165, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8775186505438093e-05, + "loss": 3.413, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8766800557927573e-05, + "loss": 3.4104, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.91489315032959, + "eval_runtime": 302.5496, + "eval_samples_per_second": 1261.251, + "eval_steps_per_second": 39.415, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8758414610417053e-05, + "loss": 3.4051, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8750045041710262e-05, + "loss": 3.4101, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8741659094199742e-05, + "loss": 3.4129, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8733273146689222e-05, + "loss": 3.4126, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8724887199178702e-05, + "loss": 3.4229, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8716501251668182e-05, + "loss": 3.4062, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8708115304157662e-05, + "loss": 3.4029, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8699729356647142e-05, + "loss": 3.4065, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8691359787940354e-05, + "loss": 3.4153, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.868297384042983e-05, + "loss": 3.4143, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8674587892919314e-05, + "loss": 3.4094, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8666201945408794e-05, + "loss": 3.4101, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8657815997898274e-05, + "loss": 3.4074, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8649446429191483e-05, + "loss": 3.3995, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8641060481680963e-05, + "loss": 3.4058, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8632674534170443e-05, + "loss": 3.3977, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8624288586659923e-05, + "loss": 3.4005, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8615919017953135e-05, + "loss": 3.3996, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8607533070442615e-05, + "loss": 3.4035, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8599147122932095e-05, + "loss": 3.4244, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8590761175421575e-05, + "loss": 3.414, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8582375227911055e-05, + "loss": 3.4077, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8573989280400532e-05, + "loss": 3.4089, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8565603332890015e-05, + "loss": 3.4138, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8557233764183228e-05, + "loss": 3.3923, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8548847816672708e-05, + "loss": 3.4095, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8540461869162184e-05, + "loss": 3.4093, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8532075921651664e-05, + "loss": 3.3946, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8523689974141144e-05, + "loss": 3.4007, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8515304026630624e-05, + "loss": 3.4001, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8506918079120107e-05, + "loss": 3.4072, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8498548510413317e-05, + "loss": 3.4083, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8490162562902796e-05, + "loss": 3.4068, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8481776615392276e-05, + "loss": 3.4141, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8473390667881756e-05, + "loss": 3.4011, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8465004720371236e-05, + "loss": 3.4123, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8456618772860716e-05, + "loss": 3.412, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8448232825350196e-05, + "loss": 3.4083, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.843986325664341e-05, + "loss": 3.3956, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.843147730913289e-05, + "loss": 3.4066, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8423091361622365e-05, + "loss": 3.3975, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8414705414111845e-05, + "loss": 3.4164, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8406319466601325e-05, + "loss": 3.4106, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.839793351909081e-05, + "loss": 3.4025, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8389563950384018e-05, + "loss": 3.4173, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8381178002873498e-05, + "loss": 3.4058, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8372792055362978e-05, + "loss": 3.4111, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8364406107852457e-05, + "loss": 3.4089, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835603653914567e-05, + "loss": 3.3731, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834765059163515e-05, + "loss": 3.4232, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.833926464412463e-05, + "loss": 3.4011, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.833087869661411e-05, + "loss": 3.4134, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832249274910359e-05, + "loss": 3.4026, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831410680159307e-05, + "loss": 3.4024, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830573723288628e-05, + "loss": 3.3922, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8297351285375762e-05, + "loss": 3.4077, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8288965337865242e-05, + "loss": 3.4086, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8280579390354722e-05, + "loss": 3.407, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.82721934428442e-05, + "loss": 3.423, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826380749533368e-05, + "loss": 3.3991, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825542154782316e-05, + "loss": 3.3943, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824705197911637e-05, + "loss": 3.4198, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.823866603160585e-05, + "loss": 3.395, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.823028008409533e-05, + "loss": 3.3935, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.822189413658481e-05, + "loss": 3.4073, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821350818907429e-05, + "loss": 3.4058, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.82051386203675e-05, + "loss": 3.3952, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819675267285698e-05, + "loss": 3.3972, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8188366725346463e-05, + "loss": 3.3938, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8179997156639672e-05, + "loss": 3.399, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8171611209129152e-05, + "loss": 3.4122, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8163225261618632e-05, + "loss": 3.401, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8154839314108112e-05, + "loss": 3.4057, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8146453366597592e-05, + "loss": 3.4007, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8138067419087072e-05, + "loss": 3.4227, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8129681471576552e-05, + "loss": 3.3973, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8121311902869765e-05, + "loss": 3.4142, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8112925955359245e-05, + "loss": 3.4012, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8104540007848724e-05, + "loss": 3.4008, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.80961540603382e-05, + "loss": 3.4114, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.808776811282768e-05, + "loss": 3.4127, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8079398544120897e-05, + "loss": 3.4027, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8071012596610377e-05, + "loss": 3.4083, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8062626649099853e-05, + "loss": 3.397, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8054240701589333e-05, + "loss": 3.3961, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8045854754078813e-05, + "loss": 3.4019, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8037468806568293e-05, + "loss": 3.4119, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8029082859057773e-05, + "loss": 3.3969, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8020696911547257e-05, + "loss": 3.403, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8012343721644198e-05, + "loss": 3.4016, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8003957774133675e-05, + "loss": 3.4034, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7995571826623155e-05, + "loss": 3.4058, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7987185879112635e-05, + "loss": 3.3943, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.797881631040585e-05, + "loss": 3.4081, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7970430362895327e-05, + "loss": 3.408, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7962044415384807e-05, + "loss": 3.409, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7953658467874287e-05, + "loss": 3.3843, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7945272520363767e-05, + "loss": 3.4017, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793690295165698e-05, + "loss": 3.3965, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792851700414646e-05, + "loss": 3.4109, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.792013105663594e-05, + "loss": 3.4031, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.791174510912542e-05, + "loss": 3.4064, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.79033591616149e-05, + "loss": 3.3993, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.789497321410438e-05, + "loss": 3.3956, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7886587266593856e-05, + "loss": 3.3945, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787820131908334e-05, + "loss": 3.4044, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.786983175037655e-05, + "loss": 3.3956, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7861445802866028e-05, + "loss": 3.405, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7853059855355508e-05, + "loss": 3.394, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.784469028664872e-05, + "loss": 3.3856, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.78363043391382e-05, + "loss": 3.3993, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782791839162768e-05, + "loss": 3.4006, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.781953244411716e-05, + "loss": 3.395, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.781114649660664e-05, + "loss": 3.3966, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780276054909612e-05, + "loss": 3.408, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779439098038933e-05, + "loss": 3.4108, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.778600503287881e-05, + "loss": 3.3931, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.777761908536829e-05, + "loss": 3.4035, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7769233137857773e-05, + "loss": 3.4039, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7760863569150982e-05, + "loss": 3.4014, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7752477621640462e-05, + "loss": 3.4024, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7744091674129942e-05, + "loss": 3.3921, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7735705726619422e-05, + "loss": 3.3989, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7727336157912634e-05, + "loss": 3.4005, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7718950210402114e-05, + "loss": 3.4049, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7710564262891594e-05, + "loss": 3.4031, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7702178315381074e-05, + "loss": 3.3974, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7693792367870554e-05, + "loss": 3.3992, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7685422799163763e-05, + "loss": 3.3858, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7677036851653243e-05, + "loss": 3.4134, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7668650904142726e-05, + "loss": 3.3948, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7660264956632206e-05, + "loss": 3.4147, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7651895387925415e-05, + "loss": 3.3898, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7643509440414895e-05, + "loss": 3.4102, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7635123492904375e-05, + "loss": 3.4038, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7626737545393855e-05, + "loss": 3.3945, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7618351597883335e-05, + "loss": 3.4022, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7609982029176548e-05, + "loss": 3.3974, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7601596081666028e-05, + "loss": 3.4067, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7593210134155508e-05, + "loss": 3.4139, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7584824186644984e-05, + "loss": 3.3885, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7576438239134464e-05, + "loss": 3.4054, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7568052291623948e-05, + "loss": 3.3973, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7559682722917157e-05, + "loss": 3.4014, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7551296775406637e-05, + "loss": 3.4014, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7542910827896117e-05, + "loss": 3.4048, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7534524880385597e-05, + "loss": 3.4023, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.752615531167881e-05, + "loss": 3.4032, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.751776936416829e-05, + "loss": 3.403, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.916233539581299, + "eval_runtime": 301.8253, + "eval_samples_per_second": 1264.278, + "eval_steps_per_second": 39.51, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.750938341665777e-05, + "loss": 3.397, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.750099746914725e-05, + "loss": 3.3955, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.749261152163673e-05, + "loss": 3.4024, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7484241952929938e-05, + "loss": 3.4055, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7475856005419418e-05, + "loss": 3.4107, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.74674700579089e-05, + "loss": 3.396, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.745908411039838e-05, + "loss": 3.3934, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.745069816288786e-05, + "loss": 3.3973, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7442312215377338e-05, + "loss": 3.3997, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.743394264667055e-05, + "loss": 3.4089, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.742555669916003e-05, + "loss": 3.3966, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741717075164951e-05, + "loss": 3.3968, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.740878480413899e-05, + "loss": 3.399, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7400415235432203e-05, + "loss": 3.3891, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7392029287921683e-05, + "loss": 3.3962, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7383643340411162e-05, + "loss": 3.3888, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.737525739290064e-05, + "loss": 3.3883, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.736687144539012e-05, + "loss": 3.3936, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7358501876683335e-05, + "loss": 3.3881, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735011592917281e-05, + "loss": 3.4123, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734172998166229e-05, + "loss": 3.4074, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.733334403415177e-05, + "loss": 3.3962, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.732495808664125e-05, + "loss": 3.3983, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.731657213913073e-05, + "loss": 3.3996, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7308202570423944e-05, + "loss": 3.3874, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7299816622913424e-05, + "loss": 3.3985, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7291430675402904e-05, + "loss": 3.3952, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7283044727892384e-05, + "loss": 3.3839, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7274658780381864e-05, + "loss": 3.3897, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.726627283287134e-05, + "loss": 3.3897, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.725788688536082e-05, + "loss": 3.4022, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7249517316654036e-05, + "loss": 3.3958, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7241131369143516e-05, + "loss": 3.3958, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7232745421632992e-05, + "loss": 3.4024, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7224359474122472e-05, + "loss": 3.3891, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7215973526611952e-05, + "loss": 3.4027, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7207587579101432e-05, + "loss": 3.403, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7199201631590912e-05, + "loss": 3.3923, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7190832062884125e-05, + "loss": 3.3903, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7182446115373605e-05, + "loss": 3.3926, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7174060167863085e-05, + "loss": 3.3883, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7165674220352565e-05, + "loss": 3.4048, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7157288272842045e-05, + "loss": 3.4012, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.714890232533152e-05, + "loss": 3.3949, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7140532756624737e-05, + "loss": 3.4055, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7132146809114217e-05, + "loss": 3.3971, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7123760861603697e-05, + "loss": 3.3979, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7115374914093174e-05, + "loss": 3.398, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7107005345386386e-05, + "loss": 3.3661, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7098619397875866e-05, + "loss": 3.4098, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709023345036535e-05, + "loss": 3.389, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7081847502854826e-05, + "loss": 3.403, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7073461555344306e-05, + "loss": 3.3938, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7065075607833786e-05, + "loss": 3.391, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7056706039126995e-05, + "loss": 3.3828, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7048320091616475e-05, + "loss": 3.3963, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7039934144105958e-05, + "loss": 3.399, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7031548196595438e-05, + "loss": 3.3945, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7023162249084918e-05, + "loss": 3.4104, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7014776301574398e-05, + "loss": 3.3973, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7006390354063878e-05, + "loss": 3.3761, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6998020785357087e-05, + "loss": 3.4057, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6989634837846567e-05, + "loss": 3.3869, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.698124889033605e-05, + "loss": 3.3867, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.697286294282553e-05, + "loss": 3.3965, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6964476995315007e-05, + "loss": 3.3947, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.695610742660822e-05, + "loss": 3.385, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.69477214790977e-05, + "loss": 3.3873, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.693933553158718e-05, + "loss": 3.3826, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.693094958407666e-05, + "loss": 3.3891, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692256363656614e-05, + "loss": 3.3989, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691417768905562e-05, + "loss": 3.3921, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.69057917415451e-05, + "loss": 3.3947, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6897422172838308e-05, + "loss": 3.3886, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6889036225327788e-05, + "loss": 3.4092, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6880650277817268e-05, + "loss": 3.3879, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687226433030675e-05, + "loss": 3.4047, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686389476159996e-05, + "loss": 3.388, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.685550881408944e-05, + "loss": 3.3928, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.684712286657892e-05, + "loss": 3.4009, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.68387369190684e-05, + "loss": 3.4023, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6830367350361613e-05, + "loss": 3.3907, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6821981402851093e-05, + "loss": 3.3994, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6813595455340573e-05, + "loss": 3.38, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6805209507830053e-05, + "loss": 3.3889, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6796823560319533e-05, + "loss": 3.3894, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.678843761280901e-05, + "loss": 3.4031, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.678005166529849e-05, + "loss": 3.3892, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6771665717787973e-05, + "loss": 3.3912, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6763312527884914e-05, + "loss": 3.3926, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6754926580374394e-05, + "loss": 3.3896, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6746540632863874e-05, + "loss": 3.3978, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6738154685353354e-05, + "loss": 3.3836, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6729785116646567e-05, + "loss": 3.3961, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6721399169136047e-05, + "loss": 3.3998, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6713013221625527e-05, + "loss": 3.3991, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6704627274115006e-05, + "loss": 3.3721, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6696257705408216e-05, + "loss": 3.3915, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6687871757897696e-05, + "loss": 3.3879, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6679485810387175e-05, + "loss": 3.3979, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6671099862876655e-05, + "loss": 3.3956, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6662713915366135e-05, + "loss": 3.3942, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6654327967855615e-05, + "loss": 3.3875, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6645942020345095e-05, + "loss": 3.3906, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6637556072834575e-05, + "loss": 3.3856, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6629186504127788e-05, + "loss": 3.3923, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6620800556617268e-05, + "loss": 3.3857, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6612414609106748e-05, + "loss": 3.3952, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6604028661596228e-05, + "loss": 3.3834, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6595659092889437e-05, + "loss": 3.3771, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.658728952418265e-05, + "loss": 3.3849, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.657890357667213e-05, + "loss": 3.3878, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.657051762916161e-05, + "loss": 3.3886, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.656213168165109e-05, + "loss": 3.3872, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.655374573414057e-05, + "loss": 3.3928, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654535978663005e-05, + "loss": 3.3949, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653697383911953e-05, + "loss": 3.3891, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652860427041274e-05, + "loss": 3.3928, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.652021832290222e-05, + "loss": 3.3932, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.65118323753917e-05, + "loss": 3.393, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650344642788118e-05, + "loss": 3.3894, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.649507685917439e-05, + "loss": 3.3805, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.648669091166387e-05, + "loss": 3.3896, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.647830496415335e-05, + "loss": 3.3883, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.646991901664283e-05, + "loss": 3.3943, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6461549447936043e-05, + "loss": 3.3988, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6453163500425523e-05, + "loss": 3.3853, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6444777552915003e-05, + "loss": 3.3885, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6436391605404483e-05, + "loss": 3.3773, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.642800565789396e-05, + "loss": 3.4012, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6419619710383443e-05, + "loss": 3.383, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6411250141676655e-05, + "loss": 3.4043, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6402864194166135e-05, + "loss": 3.3848, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639447824665561e-05, + "loss": 3.398, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638609229914509e-05, + "loss": 3.3931, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.637770635163457e-05, + "loss": 3.3821, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.636932040412405e-05, + "loss": 3.3932, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6360950835417264e-05, + "loss": 3.3848, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6352564887906744e-05, + "loss": 3.3998, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6344178940396224e-05, + "loss": 3.3999, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6335792992885704e-05, + "loss": 3.3848, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6327407045375184e-05, + "loss": 3.388, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6319021097864664e-05, + "loss": 3.3885, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6310651529157876e-05, + "loss": 3.3954, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6302265581647356e-05, + "loss": 3.3839, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6293879634136836e-05, + "loss": 3.4003, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6285493686626316e-05, + "loss": 3.3848, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6277107739115793e-05, + "loss": 3.3951, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6268721791605273e-05, + "loss": 3.3885, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.9170782566070557, + "eval_runtime": 301.7679, + "eval_samples_per_second": 1264.518, + "eval_steps_per_second": 39.517, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6260352222898485e-05, + "loss": 3.3835, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6251982654191697e-05, + "loss": 3.3847, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6243596706681177e-05, + "loss": 3.3894, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6235210759170657e-05, + "loss": 3.396, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6226824811660137e-05, + "loss": 3.4035, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.621845524295335e-05, + "loss": 3.3865, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.621006929544283e-05, + "loss": 3.3852, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.620168334793231e-05, + "loss": 3.3877, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.619329740042179e-05, + "loss": 3.3917, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6184911452911266e-05, + "loss": 3.394, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617654188420448e-05, + "loss": 3.3856, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616815593669396e-05, + "loss": 3.3879, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.615976998918344e-05, + "loss": 3.3922, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615138404167292e-05, + "loss": 3.3789, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.61429980941624e-05, + "loss": 3.381, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613461214665188e-05, + "loss": 3.3779, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612622619914136e-05, + "loss": 3.3753, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.611784025163084e-05, + "loss": 3.3857, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.610947068292405e-05, + "loss": 3.3816, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.610108473541353e-05, + "loss": 3.3962, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609269878790301e-05, + "loss": 3.3965, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608431284039249e-05, + "loss": 3.3853, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6075926892881967e-05, + "loss": 3.3883, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6067540945371447e-05, + "loss": 3.3899, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.605917137666466e-05, + "loss": 3.3747, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6050785429154143e-05, + "loss": 3.392, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604239948164362e-05, + "loss": 3.3852, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.60340135341331e-05, + "loss": 3.3742, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602562758662258e-05, + "loss": 3.3798, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601724163911206e-05, + "loss": 3.3829, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.600885569160154e-05, + "loss": 3.3855, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6000486122894752e-05, + "loss": 3.3856, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5992100175384232e-05, + "loss": 3.3911, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5983714227873712e-05, + "loss": 3.3879, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5975328280363192e-05, + "loss": 3.3794, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5966942332852672e-05, + "loss": 3.3933, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.595855638534215e-05, + "loss": 3.3925, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.595017043783163e-05, + "loss": 3.3819, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5941800869124844e-05, + "loss": 3.3815, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5933414921614324e-05, + "loss": 3.3831, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.59250289741038e-05, + "loss": 3.3746, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591664302659328e-05, + "loss": 3.394, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.590825707908276e-05, + "loss": 3.3901, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.589987113157224e-05, + "loss": 3.3886, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5891501562865453e-05, + "loss": 3.3906, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5883115615354933e-05, + "loss": 3.389, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5874729667844413e-05, + "loss": 3.3892, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5866343720333893e-05, + "loss": 3.3853, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5857974151627102e-05, + "loss": 3.3619, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5849588204116582e-05, + "loss": 3.3968, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5841202256606062e-05, + "loss": 3.3787, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5832816309095545e-05, + "loss": 3.3933, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5824430361585025e-05, + "loss": 3.3839, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5816044414074505e-05, + "loss": 3.38, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5807674845367714e-05, + "loss": 3.3739, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5799288897857194e-05, + "loss": 3.3815, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5790902950346674e-05, + "loss": 3.3926, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5782517002836154e-05, + "loss": 3.3819, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5774131055325634e-05, + "loss": 3.4015, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5765745107815114e-05, + "loss": 3.383, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5757359160304594e-05, + "loss": 3.3675, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5748973212794074e-05, + "loss": 3.3949, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5740603644087283e-05, + "loss": 3.3813, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5732217696576766e-05, + "loss": 3.3766, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5723831749066246e-05, + "loss": 3.3839, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5715445801555726e-05, + "loss": 3.3876, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5707076232848935e-05, + "loss": 3.3722, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5698690285338415e-05, + "loss": 3.3794, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5690304337827895e-05, + "loss": 3.3717, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5681918390317375e-05, + "loss": 3.3816, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5673548821610588e-05, + "loss": 3.3861, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5665162874100068e-05, + "loss": 3.3806, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5656776926589548e-05, + "loss": 3.3866, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5648390979079028e-05, + "loss": 3.3765, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5640005031568508e-05, + "loss": 3.3952, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5631619084057984e-05, + "loss": 3.3813, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.56232495153512e-05, + "loss": 3.3958, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561486356784068e-05, + "loss": 3.3792, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560647762033016e-05, + "loss": 3.3788, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5598091672819637e-05, + "loss": 3.3901, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5589705725309117e-05, + "loss": 3.3906, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.558133615660233e-05, + "loss": 3.3841, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.557295020909181e-05, + "loss": 3.3889, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.556456426158129e-05, + "loss": 3.3721, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555617831407077e-05, + "loss": 3.3764, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.554780874536398e-05, + "loss": 3.3794, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5539422797853458e-05, + "loss": 3.3944, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5531036850342938e-05, + "loss": 3.3772, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.552265090283242e-05, + "loss": 3.3803, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.55142649553219e-05, + "loss": 3.3841, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550587900781138e-05, + "loss": 3.3777, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.549750943910459e-05, + "loss": 3.3862, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.548912349159407e-05, + "loss": 3.3752, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548073754408355e-05, + "loss": 3.3819, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547235159657303e-05, + "loss": 3.3933, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5463965649062513e-05, + "loss": 3.3871, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5455596080355723e-05, + "loss": 3.3644, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5447210132845203e-05, + "loss": 3.3791, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5438824185334682e-05, + "loss": 3.3754, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5430438237824162e-05, + "loss": 3.3884, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.542205229031364e-05, + "loss": 3.3868, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5413666342803122e-05, + "loss": 3.3846, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5405280395292602e-05, + "loss": 3.3765, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5396894447782082e-05, + "loss": 3.3807, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.538852487907529e-05, + "loss": 3.3744, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.538013893156477e-05, + "loss": 3.3833, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.537175298405425e-05, + "loss": 3.3761, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.536336703654373e-05, + "loss": 3.3828, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5354981089033215e-05, + "loss": 3.3781, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5346611520326424e-05, + "loss": 3.3658, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5338225572815904e-05, + "loss": 3.3775, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5329839625305384e-05, + "loss": 3.3737, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5321453677794864e-05, + "loss": 3.3813, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5313067730284343e-05, + "loss": 3.375, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5304681782773823e-05, + "loss": 3.3855, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5296312214067036e-05, + "loss": 3.3811, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5287926266556516e-05, + "loss": 3.3829, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5279540319045996e-05, + "loss": 3.3793, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5271154371535472e-05, + "loss": 3.3811, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5262784802828685e-05, + "loss": 3.3814, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5254398855318167e-05, + "loss": 3.3786, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5246012907807645e-05, + "loss": 3.3722, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5237626960297125e-05, + "loss": 3.3807, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5229257391590337e-05, + "loss": 3.3789, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5220871444079817e-05, + "loss": 3.3838, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5212485496569295e-05, + "loss": 3.3822, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5204099549058775e-05, + "loss": 3.377, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5195713601548255e-05, + "loss": 3.3754, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.518734403284147e-05, + "loss": 3.3698, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5178958085330946e-05, + "loss": 3.3881, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5170572137820426e-05, + "loss": 3.378, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5162186190309908e-05, + "loss": 3.3954, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5153800242799388e-05, + "loss": 3.3723, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5145430674092598e-05, + "loss": 3.3873, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5137044726582078e-05, + "loss": 3.3834, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5128658779071558e-05, + "loss": 3.3742, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5120272831561038e-05, + "loss": 3.3784, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5111903262854249e-05, + "loss": 3.3775, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5103517315343729e-05, + "loss": 3.3873, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5095131367833209e-05, + "loss": 3.3896, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.508674542032269e-05, + "loss": 3.3766, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.507835947281217e-05, + "loss": 3.3741, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.506997352530165e-05, + "loss": 3.3806, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5061603956594861e-05, + "loss": 3.3837, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5053218009084341e-05, + "loss": 3.3732, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5044832061573821e-05, + "loss": 3.3897, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.50364461140633e-05, + "loss": 3.3756, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5028076545356512e-05, + "loss": 3.385, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5019690597845992e-05, + "loss": 3.3782, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.9194915294647217, + "eval_runtime": 302.4309, + "eval_samples_per_second": 1261.746, + "eval_steps_per_second": 39.43, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5011304650335472e-05, + "loss": 3.3811, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.500291870282495e-05, + "loss": 3.3739, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.499453275531443e-05, + "loss": 3.3804, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4986163186607644e-05, + "loss": 3.3864, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4977777239097124e-05, + "loss": 3.3919, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4969391291586601e-05, + "loss": 3.3792, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4961005344076083e-05, + "loss": 3.3754, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4952619396565562e-05, + "loss": 3.3782, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4944233449055042e-05, + "loss": 3.3807, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4935863880348253e-05, + "loss": 3.381, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4927477932837733e-05, + "loss": 3.3785, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4919091985327213e-05, + "loss": 3.3781, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4910706037816693e-05, + "loss": 3.3853, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4902336469109904e-05, + "loss": 3.3659, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4893950521599384e-05, + "loss": 3.3715, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4885564574088864e-05, + "loss": 3.369, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4877178626578345e-05, + "loss": 3.3641, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4868792679067825e-05, + "loss": 3.3754, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4860423110361034e-05, + "loss": 3.3703, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4852037162850516e-05, + "loss": 3.3856, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4843651215339996e-05, + "loss": 3.3865, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4835265267829476e-05, + "loss": 3.3755, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4826895699122687e-05, + "loss": 3.377, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4818509751612167e-05, + "loss": 3.3806, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4810123804101647e-05, + "loss": 3.3617, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4801737856591127e-05, + "loss": 3.3856, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4793368287884337e-05, + "loss": 3.3711, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4784982340373817e-05, + "loss": 3.3668, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4776596392863299e-05, + "loss": 3.373, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4768210445352776e-05, + "loss": 3.3684, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4759824497842256e-05, + "loss": 3.3769, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.475145492913547e-05, + "loss": 3.3735, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.474306898162495e-05, + "loss": 3.3871, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4734683034114426e-05, + "loss": 3.3752, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4726297086603908e-05, + "loss": 3.3689, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4717911139093388e-05, + "loss": 3.382, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4709525191582868e-05, + "loss": 3.383, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4701139244072348e-05, + "loss": 3.3726, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4692769675365559e-05, + "loss": 3.3688, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4684383727855039e-05, + "loss": 3.3729, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4675997780344519e-05, + "loss": 3.3674, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4667611832834e-05, + "loss": 3.3816, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.465922588532348e-05, + "loss": 3.3785, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4650839937812957e-05, + "loss": 3.3846, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4642470369106171e-05, + "loss": 3.3806, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4634084421595651e-05, + "loss": 3.376, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.462569847408513e-05, + "loss": 3.3789, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4617312526574609e-05, + "loss": 3.3753, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4608942957867822e-05, + "loss": 3.3508, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4600557010357302e-05, + "loss": 3.3846, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4592171062846781e-05, + "loss": 3.3707, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.458378511533626e-05, + "loss": 3.3819, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.457539916782574e-05, + "loss": 3.3715, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.456701322031522e-05, + "loss": 3.374, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.455864365160843e-05, + "loss": 3.3613, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.455025770409791e-05, + "loss": 3.3698, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4541871756587392e-05, + "loss": 3.3852, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4533485809076872e-05, + "loss": 3.3716, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4525099861566352e-05, + "loss": 3.3892, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4516713914055832e-05, + "loss": 3.3739, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4508327966545312e-05, + "loss": 3.3559, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.449994201903479e-05, + "loss": 3.3901, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4491572450328003e-05, + "loss": 3.3684, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4483186502817484e-05, + "loss": 3.3653, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4474800555306964e-05, + "loss": 3.3749, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.446641460779644e-05, + "loss": 3.3758, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4458045039089655e-05, + "loss": 3.3651, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4449659091579135e-05, + "loss": 3.3669, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4441273144068611e-05, + "loss": 3.3637, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4432887196558093e-05, + "loss": 3.3676, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4424517627851306e-05, + "loss": 3.3801, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4416131680340786e-05, + "loss": 3.3713, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4407745732830264e-05, + "loss": 3.375, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4399359785319744e-05, + "loss": 3.3664, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4390973837809224e-05, + "loss": 3.3884, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4382587890298704e-05, + "loss": 3.3716, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4374201942788185e-05, + "loss": 3.3837, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4365832374081394e-05, + "loss": 3.3686, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4357446426570876e-05, + "loss": 3.3699, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4349060479060356e-05, + "loss": 3.3829, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4340674531549836e-05, + "loss": 3.3787, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4332288584039316e-05, + "loss": 3.3726, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4323919015332527e-05, + "loss": 3.3804, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4315533067822007e-05, + "loss": 3.3631, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4307147120311487e-05, + "loss": 3.3657, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4298761172800967e-05, + "loss": 3.3702, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4290391604094177e-05, + "loss": 3.381, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4282005656583657e-05, + "loss": 3.3699, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4273619709073139e-05, + "loss": 3.372, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4265233761562616e-05, + "loss": 3.3732, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4256847814052096e-05, + "loss": 3.3698, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.424847824534531e-05, + "loss": 3.3753, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.424009229783479e-05, + "loss": 3.3668, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4231706350324266e-05, + "loss": 3.373, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4223320402813748e-05, + "loss": 3.3832, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4214934455303228e-05, + "loss": 3.3814, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.420656488659644e-05, + "loss": 3.3501, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4198178939085919e-05, + "loss": 3.3724, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4189792991575399e-05, + "loss": 3.365, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4181407044064878e-05, + "loss": 3.3789, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4173021096554358e-05, + "loss": 3.3784, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.416465152784757e-05, + "loss": 3.3729, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.415626558033705e-05, + "loss": 3.3634, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4147879632826531e-05, + "loss": 3.373, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.413949368531601e-05, + "loss": 3.3674, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.413110773780549e-05, + "loss": 3.3694, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.412272179029497e-05, + "loss": 3.3644, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4114335842784449e-05, + "loss": 3.3751, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4105949895273929e-05, + "loss": 3.367, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4097596705370872e-05, + "loss": 3.3568, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4089210757860352e-05, + "loss": 3.3671, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4080824810349832e-05, + "loss": 3.3602, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4072438862839312e-05, + "loss": 3.3726, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4064052915328794e-05, + "loss": 3.3626, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.405566696781827e-05, + "loss": 3.3762, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4047297399111485e-05, + "loss": 3.3732, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4038911451600964e-05, + "loss": 3.3736, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4030525504090444e-05, + "loss": 3.3667, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4022139556579923e-05, + "loss": 3.3729, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4013769987873135e-05, + "loss": 3.3748, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4005384040362615e-05, + "loss": 3.366, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3996998092852095e-05, + "loss": 3.3596, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3988612145341573e-05, + "loss": 3.371, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3980242576634786e-05, + "loss": 3.3698, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3971856629124266e-05, + "loss": 3.3743, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3963470681613744e-05, + "loss": 3.3707, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3955084734103224e-05, + "loss": 3.3668, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3946698786592704e-05, + "loss": 3.369, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3938329217885918e-05, + "loss": 3.3603, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3929943270375395e-05, + "loss": 3.3749, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3921557322864875e-05, + "loss": 3.3692, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3913171375354356e-05, + "loss": 3.3867, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3904801806647569e-05, + "loss": 3.3633, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3896415859137047e-05, + "loss": 3.3716, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3888029911626527e-05, + "loss": 3.3757, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3879643964116007e-05, + "loss": 3.3676, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3871258016605487e-05, + "loss": 3.3638, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3862888447898698e-05, + "loss": 3.3693, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3854502500388178e-05, + "loss": 3.38, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3846116552877658e-05, + "loss": 3.3796, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.383773060536714e-05, + "loss": 3.3706, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.382934465785662e-05, + "loss": 3.364, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.38209587103461e-05, + "loss": 3.369, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.381258914163931e-05, + "loss": 3.3735, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.380420319412879e-05, + "loss": 3.3605, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.379581724661827e-05, + "loss": 3.3852, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.378743129910775e-05, + "loss": 3.363, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3779045351597228e-05, + "loss": 3.3759, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3770659404086708e-05, + "loss": 3.3693, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.919734001159668, + "eval_runtime": 301.9672, + "eval_samples_per_second": 1263.684, + "eval_steps_per_second": 39.491, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3762273456576188e-05, + "loss": 3.3893, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3753903887869399e-05, + "loss": 3.3644, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3745517940358879e-05, + "loss": 3.3672, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3737131992848359e-05, + "loss": 3.3779, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.372874604533784e-05, + "loss": 3.3746, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.372037647663105e-05, + "loss": 3.3735, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3711990529120531e-05, + "loss": 3.3643, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3703604581610011e-05, + "loss": 3.3641, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3695218634099491e-05, + "loss": 3.3695, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3686832686588971e-05, + "loss": 3.3755, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3678463117882182e-05, + "loss": 3.3672, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3670077170371662e-05, + "loss": 3.3754, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3661691222861142e-05, + "loss": 3.3697, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3653305275350622e-05, + "loss": 3.3544, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3644935706643832e-05, + "loss": 3.3666, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3636549759133312e-05, + "loss": 3.3546, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3628163811622794e-05, + "loss": 3.3527, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3619777864112274e-05, + "loss": 3.3682, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3611391916601754e-05, + "loss": 3.3584, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3603005969091232e-05, + "loss": 3.3775, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3594620021580712e-05, + "loss": 3.3766, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3586250452873925e-05, + "loss": 3.3646, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3577864505363403e-05, + "loss": 3.3683, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3569478557852883e-05, + "loss": 3.3704, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3561092610342363e-05, + "loss": 3.3545, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3552706662831843e-05, + "loss": 3.3733, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3544337094125054e-05, + "loss": 3.3614, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3535951146614534e-05, + "loss": 3.3603, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3527565199104013e-05, + "loss": 3.3636, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3519179251593495e-05, + "loss": 3.3555, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3510793304082975e-05, + "loss": 3.365, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3502423735376186e-05, + "loss": 3.3651, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3494037787865666e-05, + "loss": 3.3752, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3485651840355146e-05, + "loss": 3.3634, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3477265892844626e-05, + "loss": 3.36, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3468879945334106e-05, + "loss": 3.3664, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3460493997823584e-05, + "loss": 3.3761, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3452108050313064e-05, + "loss": 3.3637, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3443738481606278e-05, + "loss": 3.359, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3435352534095758e-05, + "loss": 3.361, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3426966586585235e-05, + "loss": 3.3602, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3418580639074715e-05, + "loss": 3.3655, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3410194691564196e-05, + "loss": 3.3722, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3401808744053676e-05, + "loss": 3.3718, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3393439175346887e-05, + "loss": 3.369, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3385053227836367e-05, + "loss": 3.3667, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3376667280325847e-05, + "loss": 3.3672, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3368281332815327e-05, + "loss": 3.3674, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3359911764108538e-05, + "loss": 3.3454, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3351525816598018e-05, + "loss": 3.3735, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3343139869087498e-05, + "loss": 3.3634, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.333475392157698e-05, + "loss": 3.3705, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3326367974066459e-05, + "loss": 3.3589, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3317982026555939e-05, + "loss": 3.363, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.330961245784915e-05, + "loss": 3.3592, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.330122651033863e-05, + "loss": 3.3536, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.329284056282811e-05, + "loss": 3.3771, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.328445461531759e-05, + "loss": 3.3599, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3276068667807068e-05, + "loss": 3.3859, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3267682720296548e-05, + "loss": 3.361, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3259296772786028e-05, + "loss": 3.3491, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.325091082527551e-05, + "loss": 3.3795, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3242541256568719e-05, + "loss": 3.3618, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3234155309058199e-05, + "loss": 3.3559, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.322576936154768e-05, + "loss": 3.3591, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.321738341403716e-05, + "loss": 3.3706, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3209013845330371e-05, + "loss": 3.3518, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3200627897819851e-05, + "loss": 3.3593, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3192241950309331e-05, + "loss": 3.3555, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3183856002798811e-05, + "loss": 3.3526, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3175486434092022e-05, + "loss": 3.3728, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3167100486581502e-05, + "loss": 3.3608, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3158714539070982e-05, + "loss": 3.363, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3150328591560462e-05, + "loss": 3.3574, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3141942644049943e-05, + "loss": 3.3771, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.313355669653942e-05, + "loss": 3.3622, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3125187127832634e-05, + "loss": 3.3737, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3116801180322114e-05, + "loss": 3.3594, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3108415232811594e-05, + "loss": 3.3591, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3100029285301072e-05, + "loss": 3.3718, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3091643337790552e-05, + "loss": 3.3663, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3083273769083765e-05, + "loss": 3.3635, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3074887821573243e-05, + "loss": 3.37, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3066501874062723e-05, + "loss": 3.3588, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3058115926552203e-05, + "loss": 3.3534, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3049729979041683e-05, + "loss": 3.3615, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3041344031531164e-05, + "loss": 3.3721, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3032958084020644e-05, + "loss": 3.3617, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3024572136510124e-05, + "loss": 3.3598, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3016202567803335e-05, + "loss": 3.3642, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3007832999096544e-05, + "loss": 3.358, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.2999447051586026e-05, + "loss": 3.3631, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2991061104075506e-05, + "loss": 3.3613, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2982675156564986e-05, + "loss": 3.3621, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2974305587858196e-05, + "loss": 3.3684, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2965919640347676e-05, + "loss": 3.3717, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2957533692837156e-05, + "loss": 3.3405, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2949147745326636e-05, + "loss": 3.3624, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2940761797816118e-05, + "loss": 3.3556, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2932375850305598e-05, + "loss": 3.3688, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2924006281598807e-05, + "loss": 3.3665, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2915620334088289e-05, + "loss": 3.3611, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2907234386577769e-05, + "loss": 3.3525, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2898848439067249e-05, + "loss": 3.3618, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.289047887036046e-05, + "loss": 3.3597, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.288209292284994e-05, + "loss": 3.3593, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.287370697533942e-05, + "loss": 3.353, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2865321027828898e-05, + "loss": 3.3642, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2856935080318378e-05, + "loss": 3.3565, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.284856551161159e-05, + "loss": 3.3478, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.284017956410107e-05, + "loss": 3.3595, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2831793616590548e-05, + "loss": 3.3458, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2823407669080028e-05, + "loss": 3.3629, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2815021721569508e-05, + "loss": 3.3592, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.280663577405899e-05, + "loss": 3.3617, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2798266205352199e-05, + "loss": 3.3652, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.278988025784168e-05, + "loss": 3.3669, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.278149431033116e-05, + "loss": 3.3563, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.277310836282064e-05, + "loss": 3.3612, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2764738794113851e-05, + "loss": 3.3648, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2756352846603331e-05, + "loss": 3.3547, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2747966899092811e-05, + "loss": 3.3487, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2739580951582291e-05, + "loss": 3.3618, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2731195004071773e-05, + "loss": 3.3589, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2722825435364982e-05, + "loss": 3.3618, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2714439487854462e-05, + "loss": 3.3598, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2706053540343943e-05, + "loss": 3.3589, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2697667592833423e-05, + "loss": 3.3585, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2689298024126634e-05, + "loss": 3.3519, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2680912076616114e-05, + "loss": 3.3571, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2672526129105594e-05, + "loss": 3.3639, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2664140181595074e-05, + "loss": 3.376, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2655770612888285e-05, + "loss": 3.3499, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2647384665377765e-05, + "loss": 3.3601, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2638998717867245e-05, + "loss": 3.3701, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2630612770356726e-05, + "loss": 3.3559, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2622226822846203e-05, + "loss": 3.3544, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2613857254139415e-05, + "loss": 3.3578, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2605471306628897e-05, + "loss": 3.3719, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2597085359118377e-05, + "loss": 3.3692, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2588699411607854e-05, + "loss": 3.3587, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2580313464097335e-05, + "loss": 3.3532, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2571943895390548e-05, + "loss": 3.3618, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2563557947880026e-05, + "loss": 3.3639, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2555172000369506e-05, + "loss": 3.3497, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2546786052858986e-05, + "loss": 3.375, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2538400105348466e-05, + "loss": 3.3555, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2530030536641677e-05, + "loss": 3.3643, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2521644589131157e-05, + "loss": 3.3588, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9216277599334717, + "eval_runtime": 307.8353, + "eval_samples_per_second": 1239.595, + "eval_steps_per_second": 38.738, + "step": 2289600 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.4855460838912512e+18, + "trial_name": null, + "trial_params": null +}