diff --git "a/checkpoint-2594880/trainer_state.json" "b/checkpoint-2594880/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2594880/trainer_state.json" @@ -0,0 +1,30705 @@ +{ + "best_metric": 3.86417293548584, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/3/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2594880, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9613, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8339, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.2109, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.0062, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8426, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7432, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6318, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5712, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4912, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4285, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3855, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3466, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.3034, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2471, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.2143, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1748, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1393, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.1181, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0901, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.058, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0471, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 5.0125, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9945, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9666, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9558, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.9259, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.9074, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8931, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8721, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8469, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.842, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.8308, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.8162, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7985, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7952, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7685, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7618, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7329, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7346, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.7207, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.7176, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.7052, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.7026, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6832, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6759, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6692, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6532, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6615, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.6353, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.6231, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6346, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.6118, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.6059, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.585, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5971, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5731, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.6011, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.565, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5783, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5685, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5436, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5362, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5417, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.5256, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5186, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.536, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.5204, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.5067, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4903, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4887, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.5002, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.5, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.49, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4871, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4841, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4779, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4645, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.463, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4578, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4467, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4489, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4486, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4504, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4323, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4128, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4326, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4276, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4264, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.4162, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.4187, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.4077, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3976, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.4022, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3986, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.4049, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.4033, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 4.3976, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.3773, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.3796, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.3823, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3795, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.37, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3676, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3571, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3719, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3425, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3551, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3543, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3446, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3427, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3478, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.337, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.343, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.3389, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3308, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.333, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3387, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.3284, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.3176, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.3227, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.3245, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.3158, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.3047, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.3122, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.3176, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.3069, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.3023, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2953, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2986, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2934, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.3059, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2984, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2776, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2877, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2918, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.2836, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2898, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2744, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2834, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2869, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2753, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2707, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2722, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2612, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.26, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2728, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2535, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2583, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2611, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2578, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.220180988311768, + "eval_runtime": 302.6371, + "eval_samples_per_second": 1260.886, + "eval_steps_per_second": 39.404, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2403, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2417, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2581, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2436, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2538, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2272, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2454, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.2313, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2303, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.232, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2331, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2345, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.2182, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.2164, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.2129, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.2115, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.21, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.2128, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.2085, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.2334, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.206, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.2123, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.2057, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.2113, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.2003, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1999, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1976, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1897, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1765, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1925, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1908, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1949, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1859, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1886, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.1785, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1776, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1654, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1733, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1702, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.1703, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.169, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1775, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1668, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1676, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.169, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1552, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1664, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.154, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.1464, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1648, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.149, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1468, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.1398, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.1479, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1315, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.1612, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1378, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1526, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.151, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1301, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1265, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1371, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.1266, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.1214, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1401, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.1358, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.1225, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.1159, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.1183, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816419816256029e-05, + "loss": 4.1304, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815581221504977e-05, + "loss": 4.1289, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.128, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.1283, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813067075132194e-05, + "loss": 4.128, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812228480381141e-05, + "loss": 4.1292, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.1117, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.1226, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809714334008359e-05, + "loss": 4.1171, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808875739257306e-05, + "loss": 4.1062, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.1167, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807198549755203e-05, + "loss": 4.1175, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063615928845243e-05, + "loss": 4.122, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055229981334717e-05, + "loss": 4.1038, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046844033824197e-05, + "loss": 4.0931, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.8038458086313677e-05, + "loss": 4.1094, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.1072, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021702570096366e-05, + "loss": 4.111, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013316622585846e-05, + "loss": 4.1045, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004930675075325e-05, + "loss": 4.1022, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996561106368535e-05, + "loss": 4.1029, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.0905, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979789211347494e-05, + "loss": 4.0981, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797140326383698e-05, + "loss": 4.0988, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796303369513019e-05, + "loss": 4.1067, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.1104, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.1027, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793787585259863e-05, + "loss": 4.0891, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792950628389184e-05, + "loss": 4.0907, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792112033638132e-05, + "loss": 4.0939, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.79127343888708e-05, + "loss": 4.1012, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790434844136028e-05, + "loss": 4.087, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789596249384976e-05, + "loss": 4.0865, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788759292514297e-05, + "loss": 4.08, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787920697763245e-05, + "loss": 4.0988, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870821030121935e-05, + "loss": 4.0684, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862435082611415e-05, + "loss": 4.0835, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854065513904624e-05, + "loss": 4.0878, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.077, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.0771, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.0888, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.0769, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812135776352024e-05, + "loss": 4.0805, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803749828841504e-05, + "loss": 4.0846, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779538026013471e-05, + "loss": 4.0742, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778699431262419e-05, + "loss": 4.0827, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777860836511367e-05, + "loss": 4.0886, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777023879640689e-05, + "loss": 4.0785, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.0689, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.075, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774508095387533e-05, + "loss": 4.0752, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773669500636481e-05, + "loss": 4.0692, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772830905885429e-05, + "loss": 4.0645, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771992311134377e-05, + "loss": 4.0662, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771153716383325e-05, + "loss": 4.0819, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0659, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0678, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0595, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0621, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.7669640183888106e-05, + "loss": 4.0604, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.7661254236377586e-05, + "loss": 4.0757, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765286828886707e-05, + "loss": 4.0708, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0498, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763611277264976e-05, + "loss": 4.0574, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762772682513924e-05, + "loss": 4.0661, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761934087762872e-05, + "loss": 4.0621, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.0686, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760258536141141e-05, + "loss": 4.0543, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759419941390089e-05, + "loss": 4.0614, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758581346639037e-05, + "loss": 4.0664, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577427518879844e-05, + "loss": 4.0571, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756905795017306e-05, + "loss": 4.056, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756067200266254e-05, + "loss": 4.0567, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755228605515202e-05, + "loss": 4.0496, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543916486445236e-05, + "loss": 4.0487, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535530538934716e-05, + "loss": 4.0614, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527144591424196e-05, + "loss": 4.0436, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751875864391367e-05, + "loss": 4.0497, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751037269640315e-05, + "loss": 4.0536, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502003127696365e-05, + "loss": 4.0491, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.049336910247803, + "eval_runtime": 302.6955, + "eval_samples_per_second": 1260.643, + "eval_steps_per_second": 39.396, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0332, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0386, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.0556, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.0374, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0554, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 4.0324, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0484, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0305, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0414, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418143652591164e-05, + "loss": 4.0365, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409757705080644e-05, + "loss": 4.0367, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.045, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739303494647079e-05, + "loss": 4.0259, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738464899896027e-05, + "loss": 4.0282, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737626305144975e-05, + "loss": 4.0239, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736787710393923e-05, + "loss": 4.0221, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735949115642871e-05, + "loss": 4.0258, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.73511052089182e-05, + "loss": 4.0289, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734271926140768e-05, + "loss": 4.0229, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733433331389716e-05, + "loss": 4.0484, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 4.0264, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.0341, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 4.0254, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0319, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 4.0227, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284050386441496e-05, + "loss": 4.0212, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275664438930976e-05, + "loss": 4.0228, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267278491420456e-05, + "loss": 4.0148, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 4.0023, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 4.0164, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 4.0261, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 4.0201, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722536513267159e-05, + "loss": 4.0196, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721697918516107e-05, + "loss": 4.0199, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720860961645428e-05, + "loss": 4.0096, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720022366894376e-05, + "loss": 4.0091, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 4.0029, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718345177392272e-05, + "loss": 4.0039, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.71750658264122e-05, + "loss": 4.0026, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716667987890168e-05, + "loss": 4.0053, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158293931391154e-05, + "loss": 4.0057, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 4.0155, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714153841517385e-05, + "loss": 4.0029, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 4.0071, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 4.0105, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9933, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108011003935505e-05, + "loss": 4.0071, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709962505642498e-05, + "loss": 4.0004, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091255487718194e-05, + "loss": 3.9879, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082869540207674e-05, + "loss": 4.0056, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074483592697154e-05, + "loss": 3.9965, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706609764518663e-05, + "loss": 3.9932, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705771169767611e-05, + "loss": 3.9901, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704932575016559e-05, + "loss": 3.9935, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.70409561814588e-05, + "loss": 3.9755, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703257023394828e-05, + "loss": 4.0045, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702418428643776e-05, + "loss": 3.9888, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701579833892724e-05, + "loss": 4.0, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700741239141672e-05, + "loss": 4.0026, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9831, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699065687519941e-05, + "loss": 3.9771, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698227092768889e-05, + "loss": 3.9922, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697388498017837e-05, + "loss": 3.9791, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9728, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9952, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9924, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9768, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.9702, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9749, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9854, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9875, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9834, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.9916, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.9852, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.992, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864900420149076e-05, + "loss": 3.9739, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.9804, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9821, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9677, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.979, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9858, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9861, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9699, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797829218868645e-05, + "loss": 3.9568, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9748, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9691, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9803, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764301807630294e-05, + "loss": 3.9727, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755915860119774e-05, + "loss": 3.9695, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674754629141298e-05, + "loss": 3.97, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673916034390246e-05, + "loss": 3.9602, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673077439639194e-05, + "loss": 3.9676, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672238844888143e-05, + "loss": 3.9679, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671400250137091e-05, + "loss": 3.9802, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.9835, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.9736, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668886103764308e-05, + "loss": 3.9567, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668047509013256e-05, + "loss": 3.9659, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667208914262204e-05, + "loss": 3.9659, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9742, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.961, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9624, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663856173138369e-05, + "loss": 3.9544, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663017578387317e-05, + "loss": 3.9742, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621806215166383e-05, + "loss": 3.9441, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613420267655863e-05, + "loss": 3.9626, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660503432014534e-05, + "loss": 3.9561, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659664837263482e-05, + "loss": 3.9587, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.9521, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657987647761378e-05, + "loss": 3.9656, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.9607, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656312096139647e-05, + "loss": 3.9545, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655473501388595e-05, + "loss": 3.964, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654634906637543e-05, + "loss": 3.9496, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653796311886491e-05, + "loss": 3.9676, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652959355015812e-05, + "loss": 3.9713, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212076026476e-05, + "loss": 3.9564, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651282165513708e-05, + "loss": 3.9535, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9537, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9563, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648768019140926e-05, + "loss": 3.9484, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647929424389874e-05, + "loss": 3.95, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647090829638822e-05, + "loss": 3.9476, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.64625223488777e-05, + "loss": 3.9646, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.9523, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445766832660386e-05, + "loss": 3.9512, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437380885149866e-05, + "loss": 3.9431, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.9492, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642060899012882e-05, + "loss": 3.9432, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9615, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.9581, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395467526401e-05, + "loss": 3.9406, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.9377, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378695631379955e-05, + "loss": 3.9534, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9484, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.9592, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353537788848395e-05, + "loss": 3.9377, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345151841337874e-05, + "loss": 3.9535, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.9509, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9502, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320010377610043e-05, + "loss": 3.9466, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.9454, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9399, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9409, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.62864829663717e-05, + "loss": 3.9497, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627809701886118e-05, + "loss": 3.9412, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626971107135066e-05, + "loss": 3.9372, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626132512384014e-05, + "loss": 3.9426, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625293917632962e-05, + "loss": 3.9403, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.975489854812622, + "eval_runtime": 305.2702, + "eval_samples_per_second": 1250.011, + "eval_steps_per_second": 39.064, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.9332, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623618366011231e-05, + "loss": 3.9296, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622779771260179e-05, + "loss": 3.9495, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621941176509127e-05, + "loss": 3.9315, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.953, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.9236, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619427030136344e-05, + "loss": 3.9454, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185884353852924e-05, + "loss": 3.9281, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.9345, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9343, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616074289012509e-05, + "loss": 3.9316, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615235694261457e-05, + "loss": 3.9401, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614398737390778e-05, + "loss": 3.9259, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613560142639726e-05, + "loss": 3.9238, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612721547888674e-05, + "loss": 3.9266, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611882953137622e-05, + "loss": 3.9163, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.61104435838657e-05, + "loss": 3.9265, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610205763635518e-05, + "loss": 3.9285, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609367168884466e-05, + "loss": 3.921, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608528574133414e-05, + "loss": 3.9455, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607689979382362e-05, + "loss": 3.9293, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606853022511684e-05, + "loss": 3.9371, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606014427760631e-05, + "loss": 3.9257, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605175833009579e-05, + "loss": 3.9301, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604337238258527e-05, + "loss": 3.923, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603498643507475e-05, + "loss": 3.9229, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602660048756423e-05, + "loss": 3.9256, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601821454005371e-05, + "loss": 3.9164, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600984497134692e-05, + "loss": 3.9106, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60014590238364e-05, + "loss": 3.9151, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599307307632588e-05, + "loss": 3.9273, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598468712881536e-05, + "loss": 3.9256, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976301181304846e-05, + "loss": 3.9254, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967931612598055e-05, + "loss": 3.927, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959545665087535e-05, + "loss": 3.9074, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951159717577015e-05, + "loss": 3.9158, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942773770066495e-05, + "loss": 3.9123, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934387822555975e-05, + "loss": 3.9068, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926001875045455e-05, + "loss": 3.9087, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917615927534935e-05, + "loss": 3.9093, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909246358828144e-05, + "loss": 3.9134, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900860411317624e-05, + "loss": 3.9201, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892474463807104e-05, + "loss": 3.9141, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884088516296584e-05, + "loss": 3.9105, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875702568786064e-05, + "loss": 3.9202, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586733300007928e-05, + "loss": 3.9033, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585894705256876e-05, + "loss": 3.9132, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585056110505824e-05, + "loss": 3.9083, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584217515754772e-05, + "loss": 3.8936, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.58337892100372e-05, + "loss": 3.914, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582541964133041e-05, + "loss": 3.9055, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581703369381989e-05, + "loss": 3.9049, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580864774630937e-05, + "loss": 3.8969, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580026179879884e-05, + "loss": 3.9023, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579189223009206e-05, + "loss": 3.8865, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578350628258154e-05, + "loss": 3.9122, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577512033507102e-05, + "loss": 3.9023, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.57667343875605e-05, + "loss": 3.9063, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575834844004998e-05, + "loss": 3.9131, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574997887134319e-05, + "loss": 3.8952, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741592923832666e-05, + "loss": 3.8876, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733206976322146e-05, + "loss": 3.9071, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724821028811626e-05, + "loss": 3.8901, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571645146010484e-05, + "loss": 3.8879, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708065512594315e-05, + "loss": 3.9075, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699679565083795e-05, + "loss": 3.9017, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691293617573275e-05, + "loss": 3.8899, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568292404886649e-05, + "loss": 3.887, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567453810135597e-05, + "loss": 3.8824, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566615215384545e-05, + "loss": 3.8935, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565776620633493e-05, + "loss": 3.9028, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564938025882441e-05, + "loss": 3.9015, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564101069011762e-05, + "loss": 3.9039, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.56326247426071e-05, + "loss": 3.8954, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562423879509658e-05, + "loss": 3.9105, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561585284758606e-05, + "loss": 3.8864, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560748327887927e-05, + "loss": 3.9, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559909733136875e-05, + "loss": 3.8935, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559071138385823e-05, + "loss": 3.8809, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558232543634771e-05, + "loss": 3.8997, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5573955867640925e-05, + "loss": 3.9002, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565569920130405e-05, + "loss": 3.8967, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557183972619885e-05, + "loss": 3.8875, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548798025109365e-05, + "loss": 3.8758, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540428456402574e-05, + "loss": 3.8889, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.5532042508892054e-05, + "loss": 3.8917, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523656561381534e-05, + "loss": 3.8945, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515270613871014e-05, + "loss": 3.8866, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506884666360494e-05, + "loss": 3.8906, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.54985150976537e-05, + "loss": 3.8845, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549012915014318e-05, + "loss": 3.8829, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548174320263266e-05, + "loss": 3.8841, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547335725512214e-05, + "loss": 3.8825, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546498768641536e-05, + "loss": 3.9, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545660173890484e-05, + "loss": 3.8989, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544821579139432e-05, + "loss": 3.8964, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.54398298438838e-05, + "loss": 3.8735, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543146027517701e-05, + "loss": 3.8886, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542307432766649e-05, + "loss": 3.8849, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541468838015597e-05, + "loss": 3.8917, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540630243264545e-05, + "loss": 3.8825, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539791648513493e-05, + "loss": 3.8809, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389546916428136e-05, + "loss": 3.875, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381160968917616e-05, + "loss": 3.8955, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372775021407096e-05, + "loss": 3.8662, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364389073896576e-05, + "loss": 3.8816, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535601950518979e-05, + "loss": 3.8786, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534763355767927e-05, + "loss": 3.8786, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533924761016875e-05, + "loss": 3.8727, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533086166265823e-05, + "loss": 3.8907, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532249209395144e-05, + "loss": 3.8807, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531410614644092e-05, + "loss": 3.8754, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.53057201989304e-05, + "loss": 3.8889, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529733425141988e-05, + "loss": 3.8738, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528894830390936e-05, + "loss": 3.8868, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528057873520257e-05, + "loss": 3.8933, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527219278769205e-05, + "loss": 3.8808, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526380684018153e-05, + "loss": 3.8768, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255420892671017e-05, + "loss": 3.8751, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247051323964226e-05, + "loss": 3.8772, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238665376453706e-05, + "loss": 3.8727, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230279428943186e-05, + "loss": 3.8785, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221893481432665e-05, + "loss": 3.8652, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213523912725875e-05, + "loss": 3.8865, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205137965215355e-05, + "loss": 3.8792, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196752017704834e-05, + "loss": 3.8781, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188366070194314e-05, + "loss": 3.8637, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8736, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171610553977003e-05, + "loss": 3.8698, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163224606466483e-05, + "loss": 3.882, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515483865895597e-05, + "loss": 3.8859, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514646909024918e-05, + "loss": 3.8721, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513808314273866e-05, + "loss": 3.8583, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512969719522814e-05, + "loss": 3.878, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512131124771762e-05, + "loss": 3.8714, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511294167901083e-05, + "loss": 3.8847, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510455573150031e-05, + "loss": 3.8638, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509616978398979e-05, + "loss": 3.8779, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508778383647927e-05, + "loss": 3.8781, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507939788896874e-05, + "loss": 3.8804, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507102832026196e-05, + "loss": 3.8731, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506264237275144e-05, + "loss": 3.8715, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054256425240924e-05, + "loss": 3.8658, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.50458704777304e-05, + "loss": 3.8692, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503748453021988e-05, + "loss": 3.874, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502911496151309e-05, + "loss": 3.8714, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502072901400257e-05, + "loss": 3.8627, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012343066492046e-05, + "loss": 3.8718, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500397349778526e-05, + "loss": 3.8657, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9338457584381104, + "eval_runtime": 304.4885, + "eval_samples_per_second": 1253.22, + "eval_steps_per_second": 39.164, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499558755027474e-05, + "loss": 3.8538, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987201602764215e-05, + "loss": 3.8589, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978815655253695e-05, + "loss": 3.8757, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970429707743175e-05, + "loss": 3.8633, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496204376023266e-05, + "loss": 3.8778, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495365781272214e-05, + "loss": 3.8605, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494527186521162e-05, + "loss": 3.8689, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49368859177011e-05, + "loss": 3.8602, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492851634899431e-05, + "loss": 3.8618, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492013040148379e-05, + "loss": 3.8633, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491174445397327e-05, + "loss": 3.8613, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490335850646275e-05, + "loss": 3.8686, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489500531655969e-05, + "loss": 3.8574, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488661936904917e-05, + "loss": 3.8551, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487823342153865e-05, + "loss": 3.8561, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486984747402813e-05, + "loss": 3.8465, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486146152651761e-05, + "loss": 3.8559, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853075579007095e-05, + "loss": 3.8581, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844689631496575e-05, + "loss": 3.8524, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836303683986055e-05, + "loss": 3.8754, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827934115279264e-05, + "loss": 3.8595, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819548167768744e-05, + "loss": 3.8678, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811162220258224e-05, + "loss": 3.8576, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802776272747704e-05, + "loss": 3.8625, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479440670404091e-05, + "loss": 3.8511, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478602075653039e-05, + "loss": 3.8604, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.8553, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476924886150935e-05, + "loss": 3.8487, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476087929280256e-05, + "loss": 3.8469, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475249334529205e-05, + "loss": 3.8478, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474410739778153e-05, + "loss": 3.8562, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473572145027101e-05, + "loss": 3.859, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472735188156422e-05, + "loss": 3.8586, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.47189659340537e-05, + "loss": 3.8589, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471057998654318e-05, + "loss": 3.8428, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470219403903266e-05, + "loss": 3.8504, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469382447032587e-05, + "loss": 3.8473, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468543852281535e-05, + "loss": 3.8386, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467705257530483e-05, + "loss": 3.8458, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466866662779431e-05, + "loss": 3.8411, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660297059087516e-05, + "loss": 3.8511, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651911111577e-05, + "loss": 3.8535, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464352516406648e-05, + "loss": 3.8483, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463513921655596e-05, + "loss": 3.8411, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462675326904544e-05, + "loss": 3.8555, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461838370033865e-05, + "loss": 3.8392, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460999775282813e-05, + "loss": 3.8493, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460161180531761e-05, + "loss": 3.84, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459322585780709e-05, + "loss": 3.8276, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.45848562891003e-05, + "loss": 3.853, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457647034158978e-05, + "loss": 3.8409, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456808439407926e-05, + "loss": 3.8409, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455971482537247e-05, + "loss": 3.8342, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551328877861956e-05, + "loss": 3.8342, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542942930351436e-05, + "loss": 3.8262, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534556982840916e-05, + "loss": 3.8419, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526171035330396e-05, + "loss": 3.8424, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8433, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509399140309356e-05, + "loss": 3.8479, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450101319279883e-05, + "loss": 3.8344, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492643624092045e-05, + "loss": 3.8216, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8455, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.8269, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446748578156048e-05, + "loss": 3.8222, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459116212853694e-05, + "loss": 3.8481, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.8385, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.8285, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433958370322134e-05, + "loss": 3.8267, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442558880161535e-05, + "loss": 3.8191, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441720285410482e-05, + "loss": 3.8308, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088169065943e-05, + "loss": 3.845, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440043095908378e-05, + "loss": 3.8382, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392061390377e-05, + "loss": 3.839, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438367544286647e-05, + "loss": 3.8338, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437528949535595e-05, + "loss": 3.852, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436690354784543e-05, + "loss": 3.8249, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435853397913865e-05, + "loss": 3.8389, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435014803162813e-05, + "loss": 3.8342, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434176208411761e-05, + "loss": 3.8148, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433337613660709e-05, + "loss": 3.844, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.43250065679003e-05, + "loss": 3.838, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431662062038978e-05, + "loss": 3.836, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308234672879257e-05, + "loss": 3.829, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299848725368737e-05, + "loss": 3.815, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291479156661946e-05, + "loss": 3.8297, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283093209151426e-05, + "loss": 3.8289, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274707261640906e-05, + "loss": 3.8361, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266321314130386e-05, + "loss": 3.8254, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.42579517454236e-05, + "loss": 3.8293, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424956579791308e-05, + "loss": 3.8246, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424117985040256e-05, + "loss": 3.8269, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423279390289204e-05, + "loss": 3.8223, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422442433418525e-05, + "loss": 3.823, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421603838667473e-05, + "loss": 3.8377, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420765243916421e-05, + "loss": 3.8403, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419926649165369e-05, + "loss": 3.8404, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.41908969229469e-05, + "loss": 3.8115, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418251097543638e-05, + "loss": 3.8303, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417412502792586e-05, + "loss": 3.825, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416575545921907e-05, + "loss": 3.8316, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157369511708555e-05, + "loss": 3.8257, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148983564198035e-05, + "loss": 3.8184, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140597616687515e-05, + "loss": 3.8214, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132211669176995e-05, + "loss": 3.8349, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123825721666475e-05, + "loss": 3.8072, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115439774155955e-05, + "loss": 3.8225, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107053826645435e-05, + "loss": 3.8166, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098684257938644e-05, + "loss": 3.8272, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090298310428124e-05, + "loss": 3.8161, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081912362917604e-05, + "loss": 3.8296, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073526415407084e-05, + "loss": 3.8247, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065140467896564e-05, + "loss": 3.8169, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405677089918977e-05, + "loss": 3.8307, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404838495167925e-05, + "loss": 3.8177, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403999900416873e-05, + "loss": 3.8299, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403161305665822e-05, + "loss": 3.8339, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402324348795143e-05, + "loss": 3.8213, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401485754044091e-05, + "loss": 3.8183, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400647159293039e-05, + "loss": 3.8188, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399808564541987e-05, + "loss": 3.8187, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398971607671308e-05, + "loss": 3.8178, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398133012920256e-05, + "loss": 3.8199, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397294418169204e-05, + "loss": 3.81, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396455823418152e-05, + "loss": 3.8307, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956188665474726e-05, + "loss": 3.8212, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947802717964206e-05, + "loss": 3.8241, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939416770453686e-05, + "loss": 3.8087, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393103082294317e-05, + "loss": 3.8156, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392266125423638e-05, + "loss": 3.814, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391427530672586e-05, + "loss": 3.8241, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390588935921534e-05, + "loss": 3.8284, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389750341170482e-05, + "loss": 3.8198, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388913384299803e-05, + "loss": 3.8016, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388074789548751e-05, + "loss": 3.8249, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387236194797699e-05, + "loss": 3.8157, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386397600046647e-05, + "loss": 3.8264, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385560643175968e-05, + "loss": 3.8068, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384722048424916e-05, + "loss": 3.8244, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383883453673864e-05, + "loss": 3.8223, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383044858922813e-05, + "loss": 3.8274, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822079020521336e-05, + "loss": 3.8162, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813693073010816e-05, + "loss": 3.8179, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805307125500296e-05, + "loss": 3.8095, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796921177989776e-05, + "loss": 3.8161, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788551609282985e-05, + "loss": 3.819, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780165661772465e-05, + "loss": 3.8162, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771779714261945e-05, + "loss": 3.8119, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763393766751425e-05, + "loss": 3.813, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755024198044634e-05, + "loss": 3.8138, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.909238576889038, + "eval_runtime": 307.446, + "eval_samples_per_second": 1241.164, + "eval_steps_per_second": 38.787, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746638250534114e-05, + "loss": 3.8103, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738252303023594e-05, + "loss": 3.8032, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372986635551308e-05, + "loss": 3.8218, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372149678680629e-05, + "loss": 3.8074, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371311083929577e-05, + "loss": 3.8213, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370472489178525e-05, + "loss": 3.8078, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369633894427473e-05, + "loss": 3.8132, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368796937556794e-05, + "loss": 3.8112, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367958342805742e-05, + "loss": 3.8083, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.36711974805469e-05, + "loss": 3.8092, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366281153303637e-05, + "loss": 3.8124, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365444196432959e-05, + "loss": 3.8128, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.36460723956228e-05, + "loss": 3.8064, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363768644811228e-05, + "loss": 3.8014, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362930050060176e-05, + "loss": 3.8066, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362091455309124e-05, + "loss": 3.7908, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361252860558072e-05, + "loss": 3.8024, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.36041426580702e-05, + "loss": 3.8043, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595756710559676e-05, + "loss": 3.8021, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587370763049156e-05, + "loss": 3.8228, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357900119434237e-05, + "loss": 3.8098, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570615246831845e-05, + "loss": 3.8151, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562229299321325e-05, + "loss": 3.8059, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553843351810805e-05, + "loss": 3.8082, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354547378310402e-05, + "loss": 3.8015, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.35370878355935e-05, + "loss": 3.8088, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352870188808298e-05, + "loss": 3.8014, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352031594057246e-05, + "loss": 3.7987, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351194637186568e-05, + "loss": 3.7959, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350356042435515e-05, + "loss": 3.7952, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349517447684463e-05, + "loss": 3.8014, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348678852933411e-05, + "loss": 3.8096, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347841896062732e-05, + "loss": 3.8053, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.34700330131168e-05, + "loss": 3.8114, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346164706560628e-05, + "loss": 3.7921, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345326111809576e-05, + "loss": 3.8014, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444891549388975e-05, + "loss": 3.7945, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436505601878455e-05, + "loss": 3.7902, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428119654367935e-05, + "loss": 3.7976, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419733706857415e-05, + "loss": 3.7857, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411364138150624e-05, + "loss": 3.7996, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402978190640104e-05, + "loss": 3.8016, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394592243129584e-05, + "loss": 3.8038, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3386206295619064e-05, + "loss": 3.7935, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337783672691227e-05, + "loss": 3.8061, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336945077940175e-05, + "loss": 3.7854, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336106483189123e-05, + "loss": 3.8024, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335267888438071e-05, + "loss": 3.792, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334430931567393e-05, + "loss": 3.7713, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333592336816341e-05, + "loss": 3.8073, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332753742065289e-05, + "loss": 3.7901, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331915147314237e-05, + "loss": 3.7962, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331079828323931e-05, + "loss": 3.7818, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330241233572879e-05, + "loss": 3.785, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294026388218266e-05, + "loss": 3.7811, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285640440707746e-05, + "loss": 3.7883, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277254493197226e-05, + "loss": 3.7964, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.3268868545686706e-05, + "loss": 3.7907, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260482598176186e-05, + "loss": 3.8028, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252096650665666e-05, + "loss": 3.7834, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324372708195888e-05, + "loss": 3.7746, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323534113444836e-05, + "loss": 3.797, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322695518693784e-05, + "loss": 3.7747, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321858561823105e-05, + "loss": 3.7767, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321019967072053e-05, + "loss": 3.7985, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320181372321001e-05, + "loss": 3.7912, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319342777569949e-05, + "loss": 3.7789, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.31850582069927e-05, + "loss": 3.7797, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317667225948218e-05, + "loss": 3.7724, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316828631197166e-05, + "loss": 3.7825, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315990036446114e-05, + "loss": 3.795, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151530795754356e-05, + "loss": 3.7903, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143144848243836e-05, + "loss": 3.7917, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134758900733316e-05, + "loss": 3.7864, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3126372953222796e-05, + "loss": 3.8028, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3118003384516005e-05, + "loss": 3.7781, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109617437005485e-05, + "loss": 3.7927, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101231489494965e-05, + "loss": 3.7861, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092845541984445e-05, + "loss": 3.7689, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084475973277654e-05, + "loss": 3.7961, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3076090025767134e-05, + "loss": 3.7918, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067704078256614e-05, + "loss": 3.7887, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3059318130746094e-05, + "loss": 3.785, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.30509485620393e-05, + "loss": 3.7715, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304256261452879e-05, + "loss": 3.7758, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303417666701827e-05, + "loss": 3.7819, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302579071950775e-05, + "loss": 3.7899, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301742115080096e-05, + "loss": 3.7761, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300903520329044e-05, + "loss": 3.7839, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300064925577992e-05, + "loss": 3.7775, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.29922633082694e-05, + "loss": 3.7802, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298389373956261e-05, + "loss": 3.7748, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297550779205209e-05, + "loss": 3.7795, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296712184454157e-05, + "loss": 3.7894, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295873589703105e-05, + "loss": 3.7946, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950366328324256e-05, + "loss": 3.7937, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294198038081374e-05, + "loss": 3.7668, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293359443330322e-05, + "loss": 3.7852, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.29252084857927e-05, + "loss": 3.7754, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291683891708591e-05, + "loss": 3.7904, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290845296957539e-05, + "loss": 3.778, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290006702206487e-05, + "loss": 3.7784, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289168107455435e-05, + "loss": 3.7717, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288329512704383e-05, + "loss": 3.788, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287492555833704e-05, + "loss": 3.7631, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286653961082652e-05, + "loss": 3.7813, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858153663316e-05, + "loss": 3.7685, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284978409460921e-05, + "loss": 3.7831, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.28413981470987e-05, + "loss": 3.774, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283301219958818e-05, + "loss": 3.7795, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282462625207766e-05, + "loss": 3.7765, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816256683370866e-05, + "loss": 3.7775, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807870735860346e-05, + "loss": 3.7792, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799484788349826e-05, + "loss": 3.7762, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791098840839306e-05, + "loss": 3.7789, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782712893328786e-05, + "loss": 3.7939, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774326945818266e-05, + "loss": 3.7772, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765940998307746e-05, + "loss": 3.7725, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757571429600955e-05, + "loss": 3.7768, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749185482090435e-05, + "loss": 3.7768, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740799534579915e-05, + "loss": 3.7675, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2732413587069394e-05, + "loss": 3.7788, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2724027639558874e-05, + "loss": 3.7665, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715641692048354e-05, + "loss": 3.7851, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707255744537834e-05, + "loss": 3.7792, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698869797027314e-05, + "loss": 3.777, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690500228320523e-05, + "loss": 3.7691, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268211428081e-05, + "loss": 3.7682, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267372833329948e-05, + "loss": 3.7735, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266534238578896e-05, + "loss": 3.7823, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265697281708217e-05, + "loss": 3.7767, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264858686957165e-05, + "loss": 3.7804, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264020092206113e-05, + "loss": 3.7559, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263181497455062e-05, + "loss": 3.781, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262344540584383e-05, + "loss": 3.7723, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261505945833331e-05, + "loss": 3.7812, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260667351082279e-05, + "loss": 3.763, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259828756331227e-05, + "loss": 3.7836, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258991799460548e-05, + "loss": 3.7757, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258153204709496e-05, + "loss": 3.7848, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257314609958444e-05, + "loss": 3.7688, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256476015207392e-05, + "loss": 3.7815, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2556390583367126e-05, + "loss": 3.7608, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548004635856606e-05, + "loss": 3.7752, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539618688346086e-05, + "loss": 3.7774, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253123274083557e-05, + "loss": 3.7698, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252286317212878e-05, + "loss": 3.773, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251447722461826e-05, + "loss": 3.7652, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250609127710774e-05, + "loss": 3.7726, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8934266567230225, + "eval_runtime": 304.0267, + "eval_samples_per_second": 1255.123, + "eval_steps_per_second": 39.224, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249770532959722e-05, + "loss": 3.765, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.24893193820867e-05, + "loss": 3.7595, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248093343457618e-05, + "loss": 3.7767, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247254748706566e-05, + "loss": 3.7649, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246416153955514e-05, + "loss": 3.7785, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245577559204462e-05, + "loss": 3.765, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.24473896445341e-05, + "loss": 3.7708, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243900369702358e-05, + "loss": 3.7689, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243063412831679e-05, + "loss": 3.7662, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242224818080627e-05, + "loss": 3.7672, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241386223329575e-05, + "loss": 3.7699, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240547628578524e-05, + "loss": 3.7711, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397123095882175e-05, + "loss": 3.7658, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388737148371655e-05, + "loss": 3.7588, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7652, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371965253350615e-05, + "loss": 3.7487, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7597, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355193358329575e-05, + "loss": 3.7612, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346807410819055e-05, + "loss": 3.7591, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233842146330853e-05, + "loss": 3.7816, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330051894601744e-05, + "loss": 3.7695, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321665947091224e-05, + "loss": 3.7748, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313279999580704e-05, + "loss": 3.7619, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304894052070184e-05, + "loss": 3.7651, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.22965244833634e-05, + "loss": 3.7615, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228813853585288e-05, + "loss": 3.7661, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227975258834236e-05, + "loss": 3.7612, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227136664083183e-05, + "loss": 3.7615, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226299707212505e-05, + "loss": 3.7519, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225461112461453e-05, + "loss": 3.7561, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246225177104e-05, + "loss": 3.7562, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223783922959348e-05, + "loss": 3.7685, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.22294696608867e-05, + "loss": 3.7673, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222108371337618e-05, + "loss": 3.7703, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221269776586566e-05, + "loss": 3.7528, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204328197158874e-05, + "loss": 3.7552, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195942249648353e-05, + "loss": 3.7587, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187556302137833e-05, + "loss": 3.7499, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217917035462731e-05, + "loss": 3.7536, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217080078592052e-05, + "loss": 3.748, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216241483841e-05, + "loss": 3.7569, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154028890899476e-05, + "loss": 3.7636, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145642943388956e-05, + "loss": 3.7601, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213727337468217e-05, + "loss": 3.7537, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212888742717165e-05, + "loss": 3.7611, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212050147966113e-05, + "loss": 3.7519, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211211553215061e-05, + "loss": 3.7611, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210374596344383e-05, + "loss": 3.7533, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209536001593331e-05, + "loss": 3.7308, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208697406842278e-05, + "loss": 3.7737, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207858812091226e-05, + "loss": 3.7478, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070218552205476e-05, + "loss": 3.7587, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061848983498685e-05, + "loss": 3.7393, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053463035988165e-05, + "loss": 3.7501, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045077088477645e-05, + "loss": 3.7359, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036691140967125e-05, + "loss": 3.7515, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028305193456605e-05, + "loss": 3.7535, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019919245946085e-05, + "loss": 3.7537, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011533298435565e-05, + "loss": 3.7619, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003147350925045e-05, + "loss": 3.7446, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199479416102199e-05, + "loss": 3.7367, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198640821351147e-05, + "loss": 3.7616, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197802226600095e-05, + "loss": 3.7348, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196963631849042e-05, + "loss": 3.735, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19612503709799e-05, + "loss": 3.7571, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195286442346938e-05, + "loss": 3.7522, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194447847595886e-05, + "loss": 3.7389, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193609252844834e-05, + "loss": 3.7441, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192772295974156e-05, + "loss": 3.7327, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191933701223104e-05, + "loss": 3.7429, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191095106472052e-05, + "loss": 3.7524, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190256511721e-05, + "loss": 3.7515, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189419554850321e-05, + "loss": 3.7551, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188580960099269e-05, + "loss": 3.75, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187742365348217e-05, + "loss": 3.7588, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186903770597165e-05, + "loss": 3.7376, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186066813726486e-05, + "loss": 3.7555, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185228218975434e-05, + "loss": 3.7425, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843896242243817e-05, + "loss": 3.7366, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835510294733297e-05, + "loss": 3.7529, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182714072602651e-05, + "loss": 3.755, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181875477851599e-05, + "loss": 3.7504, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181036883100547e-05, + "loss": 3.7453, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180198288349495e-05, + "loss": 3.732, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179361331478816e-05, + "loss": 3.7351, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178522736727764e-05, + "loss": 3.7456, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177684141976712e-05, + "loss": 3.7515, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.17684554722566e-05, + "loss": 3.739, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176008590354981e-05, + "loss": 3.7466, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175169995603929e-05, + "loss": 3.731, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174331400852877e-05, + "loss": 3.7468, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173492806101825e-05, + "loss": 3.7356, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726558492311466e-05, + "loss": 3.7436, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718172544800946e-05, + "loss": 3.7515, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709786597290426e-05, + "loss": 3.7582, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7555, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693031081073115e-05, + "loss": 3.7296, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684645133562595e-05, + "loss": 3.7474, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676259186052075e-05, + "loss": 3.7369, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667873238541555e-05, + "loss": 3.7534, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659503669834764e-05, + "loss": 3.7397, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651117722324244e-05, + "loss": 3.7424, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642731774813724e-05, + "loss": 3.7353, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634345827303204e-05, + "loss": 3.7458, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162597625859642e-05, + "loss": 3.7298, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.16175903110859e-05, + "loss": 3.7445, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160920436357538e-05, + "loss": 3.7292, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160081841606486e-05, + "loss": 3.7485, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159244884735807e-05, + "loss": 3.7363, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158406289984755e-05, + "loss": 3.7411, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157567695233703e-05, + "loss": 3.7387, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156729100482651e-05, + "loss": 3.7435, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155892143611972e-05, + "loss": 3.742, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.15505354886092e-05, + "loss": 3.7357, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154214954109868e-05, + "loss": 3.7458, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153376359358816e-05, + "loss": 3.7534, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152539402488137e-05, + "loss": 3.7431, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151700807737085e-05, + "loss": 3.7364, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150863850866406e-05, + "loss": 3.7355, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150025256115354e-05, + "loss": 3.7405, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149186661364302e-05, + "loss": 3.7291, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.14834806661325e-05, + "loss": 3.7412, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147509471862198e-05, + "loss": 3.7267, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146670877111146e-05, + "loss": 3.7486, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145832282360094e-05, + "loss": 3.74, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144993687609042e-05, + "loss": 3.7397, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144156730738363e-05, + "loss": 3.7327, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143318135987311e-05, + "loss": 3.7309, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142479541236259e-05, + "loss": 3.7371, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141640946485207e-05, + "loss": 3.7476, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140803989614529e-05, + "loss": 3.7402, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139965394863477e-05, + "loss": 3.7404, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139126800112425e-05, + "loss": 3.7218, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138288205361373e-05, + "loss": 3.7459, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374512484906936e-05, + "loss": 3.7347, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366126537396416e-05, + "loss": 3.7482, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357740589885896e-05, + "loss": 3.7259, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349354642375376e-05, + "loss": 3.7455, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340985073668585e-05, + "loss": 3.7372, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332599126158065e-05, + "loss": 3.7537, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324213178647545e-05, + "loss": 3.7315, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315827231137025e-05, + "loss": 3.7414, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130745766243024e-05, + "loss": 3.7268, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129907171491972e-05, + "loss": 3.7384, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12906857674092e-05, + "loss": 3.7408, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128229981989868e-05, + "loss": 3.7298, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7416, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265527924877634e-05, + "loss": 3.7245, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1257141977367114e-05, + "loss": 3.7408, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8820981979370117, + "eval_runtime": 302.0404, + "eval_samples_per_second": 1263.377, + "eval_steps_per_second": 39.481, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248756029856594e-05, + "loss": 3.7351, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.12403864611498e-05, + "loss": 3.7217, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123200051363928e-05, + "loss": 3.74, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122361456612876e-05, + "loss": 3.7287, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121524499742198e-05, + "loss": 3.7438, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120685904991146e-05, + "loss": 3.7313, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119847310240094e-05, + "loss": 3.7355, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1190103533694154e-05, + "loss": 3.7357, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118171758618363e-05, + "loss": 3.728, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117333163867311e-05, + "loss": 3.7319, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116494569116259e-05, + "loss": 3.7333, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115655974365207e-05, + "loss": 3.7365, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148190174945276e-05, + "loss": 3.7336, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139804227434756e-05, + "loss": 3.7215, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131418279924236e-05, + "loss": 3.7254, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123032332413716e-05, + "loss": 3.7195, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114646384903196e-05, + "loss": 3.7227, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110626043739268e-05, + "loss": 3.7308, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109787448988216e-05, + "loss": 3.7195, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108950492117537e-05, + "loss": 3.7462, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.7355, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107273302615433e-05, + "loss": 3.74, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106434707864381e-05, + "loss": 3.7274, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105596113113329e-05, + "loss": 3.7269, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104757518362277e-05, + "loss": 3.7331, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103918923611225e-05, + "loss": 3.7258, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103080328860173e-05, + "loss": 3.7283, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102243371989494e-05, + "loss": 3.7317, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101404777238442e-05, + "loss": 3.7123, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.10056618248739e-05, + "loss": 3.7212, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099727587736338e-05, + "loss": 3.7239, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988906308656597e-05, + "loss": 3.7316, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980520361146076e-05, + "loss": 3.7344, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972134413635556e-05, + "loss": 3.7343, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963748466125036e-05, + "loss": 3.7184, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955378897418245e-05, + "loss": 3.7185, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946992949907725e-05, + "loss": 3.727, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938607002397205e-05, + "loss": 3.7174, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930221054886685e-05, + "loss": 3.7206, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921851486179894e-05, + "loss": 3.7134, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913481917473104e-05, + "loss": 3.7236, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905095969962583e-05, + "loss": 3.7248, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089671002245207e-05, + "loss": 3.7262, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088832407494155e-05, + "loss": 3.7239, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087993812743103e-05, + "loss": 3.7242, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087155217992051e-05, + "loss": 3.7204, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086316623240999e-05, + "loss": 3.7271, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085478028489946e-05, + "loss": 3.7196, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084642709499641e-05, + "loss": 3.6989, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083804114748589e-05, + "loss": 3.7379, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082965519997537e-05, + "loss": 3.7124, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082126925246485e-05, + "loss": 3.7258, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081288330495433e-05, + "loss": 3.7121, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080449735744381e-05, + "loss": 3.7127, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0796127788737024e-05, + "loss": 3.7002, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.0787741841226504e-05, + "loss": 3.7155, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779355893715984e-05, + "loss": 3.7231, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770969946205464e-05, + "loss": 3.7178, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076258399869494e-05, + "loss": 3.7285, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075419805118442e-05, + "loss": 3.7193, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.07458121036739e-05, + "loss": 3.6988, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073742615616338e-05, + "loss": 3.7248, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0729056587456586e-05, + "loss": 3.7041, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720670639946066e-05, + "loss": 3.6992, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0712284692435546e-05, + "loss": 3.7287, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0703898744925026e-05, + "loss": 3.7173, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069552917621824e-05, + "loss": 3.7037, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068714322870772e-05, + "loss": 3.7101, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.06787572811972e-05, + "loss": 3.7016, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067037133368668e-05, + "loss": 3.7098, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066200176497989e-05, + "loss": 3.7178, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065361581746937e-05, + "loss": 3.7184, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064522986995885e-05, + "loss": 3.7234, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063684392244833e-05, + "loss": 3.7157, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062847435374154e-05, + "loss": 3.727, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062008840623102e-05, + "loss": 3.7037, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.06117024587205e-05, + "loss": 3.7243, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060331651120998e-05, + "loss": 3.7066, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594946942503195e-05, + "loss": 3.7073, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586560994992675e-05, + "loss": 3.7212, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578175047482155e-05, + "loss": 3.7227, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569789099971635e-05, + "loss": 3.7182, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561419531264844e-05, + "loss": 3.7194, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553033583754324e-05, + "loss": 3.6957, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544647636243804e-05, + "loss": 3.6999, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053627806753701e-05, + "loss": 3.7114, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052789212002649e-05, + "loss": 3.7191, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051950617251597e-05, + "loss": 3.7084, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051112022500545e-05, + "loss": 3.7129, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050275065629867e-05, + "loss": 3.7014, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049436470878815e-05, + "loss": 3.7152, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048597876127763e-05, + "loss": 3.7035, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047759281376711e-05, + "loss": 3.7105, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046922324506032e-05, + "loss": 3.7193, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.04608372975498e-05, + "loss": 3.7227, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045245135003928e-05, + "loss": 3.7244, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044406540252876e-05, + "loss": 3.7019, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043569583382197e-05, + "loss": 3.7133, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042730988631145e-05, + "loss": 3.7076, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418940317604656e-05, + "loss": 3.7149, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410554370094136e-05, + "loss": 3.7079, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040216842258362e-05, + "loss": 3.7141, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.03937824750731e-05, + "loss": 3.7028, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038539652756258e-05, + "loss": 3.7119, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037701058005206e-05, + "loss": 3.7026, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036862463254154e-05, + "loss": 3.7095, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036023868503102e-05, + "loss": 3.6961, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035186911632423e-05, + "loss": 3.7153, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034348316881371e-05, + "loss": 3.7055, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033509722130319e-05, + "loss": 3.7091, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032671127379267e-05, + "loss": 3.7072, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031835808388961e-05, + "loss": 3.7101, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030997213637909e-05, + "loss": 3.7136, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301586188868576e-05, + "loss": 3.7062, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293200241358056e-05, + "loss": 3.7137, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.7205, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276428346337016e-05, + "loss": 3.7073, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268042398826496e-05, + "loss": 3.7136, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259672830119705e-05, + "loss": 3.7037, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.7068, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242900935098665e-05, + "loss": 3.7068, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234514987588145e-05, + "loss": 3.7078, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226129040077625e-05, + "loss": 3.6955, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217743092567105e-05, + "loss": 3.7155, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209357145056585e-05, + "loss": 3.7094, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200971197546065e-05, + "loss": 3.7111, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192601628839274e-05, + "loss": 3.701, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184215681328754e-05, + "loss": 3.701, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017582973381824e-05, + "loss": 3.7029, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167443786307714e-05, + "loss": 3.7142, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015907421760093e-05, + "loss": 3.7098, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015068827009041e-05, + "loss": 3.7147, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014230232257989e-05, + "loss": 3.6896, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013391637506936e-05, + "loss": 3.7136, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012554680636258e-05, + "loss": 3.7056, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011716085885206e-05, + "loss": 3.7165, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010877491134154e-05, + "loss": 3.6986, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010038896383101e-05, + "loss": 3.712, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009201939512423e-05, + "loss": 3.7037, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008363344761371e-05, + "loss": 3.7243, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007524750010319e-05, + "loss": 3.7037, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006686155259267e-05, + "loss": 3.7092, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0058491983885883e-05, + "loss": 3.7015, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0050106036375363e-05, + "loss": 3.7086, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041720088864837e-05, + "loss": 3.7048, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033334141354317e-05, + "loss": 3.702, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024948193843797e-05, + "loss": 3.7111, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016562246333276e-05, + "loss": 3.6912, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008176298822756e-05, + "loss": 3.7154, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.875060796737671, + "eval_runtime": 302.6472, + "eval_samples_per_second": 1260.844, + "eval_steps_per_second": 39.402, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999790351312236e-05, + "loss": 3.7003, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991404403801716e-05, + "loss": 3.6939, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983018456291196e-05, + "loss": 3.7052, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974632508780676e-05, + "loss": 3.7008, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996624656127016e-05, + "loss": 3.714, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995786061375964e-05, + "loss": 3.7017, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994947466624912e-05, + "loss": 3.7044, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994110509754233e-05, + "loss": 3.708, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993271915003181e-05, + "loss": 3.6984, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992433320252129e-05, + "loss": 3.7052, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991594725501077e-05, + "loss": 3.7024, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990756130750025e-05, + "loss": 3.7055, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989919173879346e-05, + "loss": 3.71, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989080579128294e-05, + "loss": 3.6857, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988241984377242e-05, + "loss": 3.6984, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.98740338962619e-05, + "loss": 3.6847, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986564794875138e-05, + "loss": 3.6963, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985726200124086e-05, + "loss": 3.6989, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984887605373034e-05, + "loss": 3.6886, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984050648502355e-05, + "loss": 3.7157, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983212053751303e-05, + "loss": 3.7078, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982373459000251e-05, + "loss": 3.7092, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981534864249199e-05, + "loss": 3.6998, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980696269498147e-05, + "loss": 3.7001, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979857674747095e-05, + "loss": 3.7045, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979020717876416e-05, + "loss": 3.6934, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978182123125364e-05, + "loss": 3.6968, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977343528374312e-05, + "loss": 3.7015, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97650493362326e-05, + "loss": 3.6869, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756663388722085e-05, + "loss": 3.6877, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748277441211565e-05, + "loss": 3.6969, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739891493701045e-05, + "loss": 3.703, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731505546190525e-05, + "loss": 3.6973, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723135977483734e-05, + "loss": 3.7108, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714750029973214e-05, + "loss": 3.6891, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706364082462694e-05, + "loss": 3.6897, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9697978134952174e-05, + "loss": 3.6982, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968962494504911e-05, + "loss": 3.6855, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968123899753859e-05, + "loss": 3.6937, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967285305002807e-05, + "loss": 3.6874, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966446710251755e-05, + "loss": 3.6912, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965608115500703e-05, + "loss": 3.6958, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964769520749652e-05, + "loss": 3.6976, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963932563878973e-05, + "loss": 3.6975, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963093969127921e-05, + "loss": 3.694, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962255374376869e-05, + "loss": 3.693, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961416779625817e-05, + "loss": 3.6942, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960578184874765e-05, + "loss": 3.6948, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959739590123713e-05, + "loss": 3.669, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958902633253034e-05, + "loss": 3.7056, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958064038501982e-05, + "loss": 3.6835, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95722544375093e-05, + "loss": 3.6999, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956386848999878e-05, + "loss": 3.6844, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955548254248826e-05, + "loss": 3.6826, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954711297378147e-05, + "loss": 3.6759, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953872702627095e-05, + "loss": 3.6815, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953034107876043e-05, + "loss": 3.7, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952195513124991e-05, + "loss": 3.6845, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513569183739386e-05, + "loss": 3.7027, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505183236228865e-05, + "loss": 3.69, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949681366752208e-05, + "loss": 3.6717, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948842772001156e-05, + "loss": 3.6923, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480041772501035e-05, + "loss": 3.6828, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471655824990514e-05, + "loss": 3.6709, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463269877479994e-05, + "loss": 3.6961, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454883929969474e-05, + "loss": 3.6896, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446497982458954e-05, + "loss": 3.6774, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943811203494844e-05, + "loss": 3.6837, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942974246624165e-05, + "loss": 3.6694, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942135651873113e-05, + "loss": 3.6845, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941297057122061e-05, + "loss": 3.6885, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940458462371009e-05, + "loss": 3.6873, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.93962150550033e-05, + "loss": 3.6973, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938784548629651e-05, + "loss": 3.6835, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937945953878599e-05, + "loss": 3.6998, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937107359127547e-05, + "loss": 3.6825, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936268764376495e-05, + "loss": 3.6941, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935430169625443e-05, + "loss": 3.6774, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934591574874391e-05, + "loss": 3.6779, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337529801233395e-05, + "loss": 3.6928, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329143853722875e-05, + "loss": 3.6949, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320774285016084e-05, + "loss": 3.6884, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312388337505564e-05, + "loss": 3.6919, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304002389995044e-05, + "loss": 3.6663, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295616442484524e-05, + "loss": 3.6723, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928724687377773e-05, + "loss": 3.6857, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927887730507094e-05, + "loss": 3.6895, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927049135756042e-05, + "loss": 3.6801, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621054100499e-05, + "loss": 3.6864, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925371946253938e-05, + "loss": 3.6766, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924533351502886e-05, + "loss": 3.6853, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923696394632208e-05, + "loss": 3.6767, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922857799881156e-05, + "loss": 3.6837, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922019205130104e-05, + "loss": 3.6923, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921180610379052e-05, + "loss": 3.6959, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920342015628e-05, + "loss": 3.6968, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919503420876948e-05, + "loss": 3.6721, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918664826125896e-05, + "loss": 3.6846, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178278692552166e-05, + "loss": 3.6822, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169892745041646e-05, + "loss": 3.6878, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161506797531126e-05, + "loss": 3.6798, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153120850020606e-05, + "loss": 3.683, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144751281313815e-05, + "loss": 3.6804, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.91363653338033e-05, + "loss": 3.6817, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912797938629278e-05, + "loss": 3.6763, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911959343878226e-05, + "loss": 3.681, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911122387007547e-05, + "loss": 3.6694, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910283792256495e-05, + "loss": 3.6881, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909445197505443e-05, + "loss": 3.6814, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908606602754391e-05, + "loss": 3.679, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907768008003339e-05, + "loss": 3.6853, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.90693105113266e-05, + "loss": 3.6782, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906092456381608e-05, + "loss": 3.6874, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905253861630556e-05, + "loss": 3.6791, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904415266879504e-05, + "loss": 3.688, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903576672128452e-05, + "loss": 3.6916, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027380773774e-05, + "loss": 3.6833, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019011205067216e-05, + "loss": 3.6831, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010625257556696e-05, + "loss": 3.6789, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900223931004617e-05, + "loss": 3.6779, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899385336253565e-05, + "loss": 3.6811, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898546741502513e-05, + "loss": 3.682, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897708146751461e-05, + "loss": 3.6668, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896869552000409e-05, + "loss": 3.6905, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896030957249357e-05, + "loss": 3.6812, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951956382590514e-05, + "loss": 3.6846, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943570435079994e-05, + "loss": 3.6762, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935184487569473e-05, + "loss": 3.6754, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926798540058953e-05, + "loss": 3.677, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891841259254843e-05, + "loss": 3.6852, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891004302384164e-05, + "loss": 3.6844, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890165707633112e-05, + "loss": 3.6873, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.88932711288206e-05, + "loss": 3.66, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888488518131008e-05, + "loss": 3.6871, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887651561260329e-05, + "loss": 3.6781, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886812966509277e-05, + "loss": 3.6904, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885974371758225e-05, + "loss": 3.6717, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885135777007173e-05, + "loss": 3.6799, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884297182256121e-05, + "loss": 3.6815, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883458587505069e-05, + "loss": 3.6957, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882619992754017e-05, + "loss": 3.6745, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881781398002966e-05, + "loss": 3.6839, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880944441132287e-05, + "loss": 3.6761, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880105846381235e-05, + "loss": 3.6879, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879267251630183e-05, + "loss": 3.6748, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878428656879131e-05, + "loss": 3.6761, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877590062128079e-05, + "loss": 3.6807, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876751467377027e-05, + "loss": 3.6707, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875912872625975e-05, + "loss": 3.6843, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8706541061401367, + "eval_runtime": 316.7005, + "eval_samples_per_second": 1204.895, + "eval_steps_per_second": 37.654, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875074277874923e-05, + "loss": 3.675, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742373210042436e-05, + "loss": 3.6663, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8733987262531916e-05, + "loss": 3.6804, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725617693825125e-05, + "loss": 3.677, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871723174631461e-05, + "loss": 3.6907, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870884579880409e-05, + "loss": 3.676, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870045985129357e-05, + "loss": 3.6719, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869209028258678e-05, + "loss": 3.685, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868370433507626e-05, + "loss": 3.6715, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867531838756574e-05, + "loss": 3.6782, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866693244005522e-05, + "loss": 3.6755, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.86585464925447e-05, + "loss": 3.6797, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865017692383791e-05, + "loss": 3.6819, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864179097632739e-05, + "loss": 3.6629, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863340502881687e-05, + "loss": 3.6707, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862501908130635e-05, + "loss": 3.6587, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616649512599565e-05, + "loss": 3.6706, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608263565089045e-05, + "loss": 3.6762, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599877617578525e-05, + "loss": 3.6602, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591491670068e-05, + "loss": 3.6902, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8583122101361214e-05, + "loss": 3.6817, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8574736153850694e-05, + "loss": 3.681, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566350206340174e-05, + "loss": 3.6763, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855796425882965e-05, + "loss": 3.6744, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854957831131913e-05, + "loss": 3.6766, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854120874261234e-05, + "loss": 3.6751, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853282279510182e-05, + "loss": 3.6639, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.85244368475913e-05, + "loss": 3.6791, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851605090008078e-05, + "loss": 3.6579, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850766495257026e-05, + "loss": 3.6647, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849927900505974e-05, + "loss": 3.6721, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849090943635295e-05, + "loss": 3.6769, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848252348884243e-05, + "loss": 3.6714, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847413754133191e-05, + "loss": 3.6829, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846575159382139e-05, + "loss": 3.6669, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845736564631087e-05, + "loss": 3.6598, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844897969880035e-05, + "loss": 3.6751, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844061013009356e-05, + "loss": 3.6582, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843222418258304e-05, + "loss": 3.6667, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842383823507252e-05, + "loss": 3.6693, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415452287562e-05, + "loss": 3.6661, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840706634005148e-05, + "loss": 3.6684, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839868039254097e-05, + "loss": 3.6736, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390310823834177e-05, + "loss": 3.6703, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381924876323656e-05, + "loss": 3.6672, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373538928813136e-05, + "loss": 3.6667, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365152981302616e-05, + "loss": 3.67, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356767033792096e-05, + "loss": 3.6705, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348397465085305e-05, + "loss": 3.6465, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340011517574785e-05, + "loss": 3.6779, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331625570064265e-05, + "loss": 3.6613, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323239622553745e-05, + "loss": 3.6694, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314853675043225e-05, + "loss": 3.6597, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306467727532705e-05, + "loss": 3.6562, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829809815882592e-05, + "loss": 3.6535, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.82897122113154e-05, + "loss": 3.6577, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828132626380488e-05, + "loss": 3.6768, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827294031629436e-05, + "loss": 3.6586, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8264554368783834e-05, + "loss": 3.6775, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825618480007705e-05, + "loss": 3.6672, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824779885256653e-05, + "loss": 3.645, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823941290505601e-05, + "loss": 3.6643, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823102695754548e-05, + "loss": 3.6537, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.82226573888387e-05, + "loss": 3.6519, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821427144132818e-05, + "loss": 3.6693, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820588549381766e-05, + "loss": 3.6635, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819749954630714e-05, + "loss": 3.6528, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818911359879662e-05, + "loss": 3.659, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180744030089835e-05, + "loss": 3.6486, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817235808257931e-05, + "loss": 3.6534, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816397213506879e-05, + "loss": 3.6658, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815558618755827e-05, + "loss": 3.6648, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147216618851484e-05, + "loss": 3.6704, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813883067134096e-05, + "loss": 3.6612, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813044472383044e-05, + "loss": 3.6749, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812205877631992e-05, + "loss": 3.6548, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.81136728288094e-05, + "loss": 3.6741, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810528688129888e-05, + "loss": 3.6495, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809691731259209e-05, + "loss": 3.6558, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808853136508157e-05, + "loss": 3.6649, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808014541757105e-05, + "loss": 3.6697, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807175947006053e-05, + "loss": 3.6663, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806338990135374e-05, + "loss": 3.6694, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805500395384322e-05, + "loss": 3.6439, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.80466180063327e-05, + "loss": 3.6469, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803823205882218e-05, + "loss": 3.6642, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802984611131166e-05, + "loss": 3.6644, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802147654260487e-05, + "loss": 3.6557, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801309059509435e-05, + "loss": 3.6625, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800470464758383e-05, + "loss": 3.6577, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799631870007331e-05, + "loss": 3.6577, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987949131366526e-05, + "loss": 3.6532, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979563183856006e-05, + "loss": 3.6575, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971177236345486e-05, + "loss": 3.6674, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962791288834966e-05, + "loss": 3.6716, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954405341324446e-05, + "loss": 3.6707, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946035772617655e-05, + "loss": 3.6484, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937649825107135e-05, + "loss": 3.66, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929263877596615e-05, + "loss": 3.6573, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920877930086095e-05, + "loss": 3.6655, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912491982575575e-05, + "loss": 3.6577, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904122413868784e-05, + "loss": 3.6565, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895736466358264e-05, + "loss": 3.6545, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788735051884775e-05, + "loss": 3.6548, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787896457133723e-05, + "loss": 3.6555, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787057862382671e-05, + "loss": 3.6565, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786220905511992e-05, + "loss": 3.6502, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.78538231076094e-05, + "loss": 3.6613, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784543716009888e-05, + "loss": 3.6562, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783705121258836e-05, + "loss": 3.6526, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782866526507784e-05, + "loss": 3.6572, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782029569637105e-05, + "loss": 3.6571, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781190974886053e-05, + "loss": 3.6622, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780352380135001e-05, + "loss": 3.6536, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779513785383949e-05, + "loss": 3.6633, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778675190632897e-05, + "loss": 3.6688, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778382337622184e-05, + "loss": 3.6605, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7769996390111664e-05, + "loss": 3.6577, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761610442601144e-05, + "loss": 3.6559, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775322449509062e-05, + "loss": 3.6522, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774485492638383e-05, + "loss": 3.6569, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773646897887331e-05, + "loss": 3.6528, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772808303136279e-05, + "loss": 3.6455, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719697083852266e-05, + "loss": 3.667, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771132751514548e-05, + "loss": 3.6599, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770294156763496e-05, + "loss": 3.6594, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769455562012444e-05, + "loss": 3.6535, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768616967261392e-05, + "loss": 3.6495, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767780010390714e-05, + "loss": 3.6516, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766941415639662e-05, + "loss": 3.663, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766102820888609e-05, + "loss": 3.6593, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765264226137557e-05, + "loss": 3.6666, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764425631386505e-05, + "loss": 3.636, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763588674515827e-05, + "loss": 3.666, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762750079764774e-05, + "loss": 3.6534, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761911485013722e-05, + "loss": 3.6651, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.76107289026267e-05, + "loss": 3.6526, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760235933391991e-05, + "loss": 3.651, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759397338640939e-05, + "loss": 3.6596, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585587438898876e-05, + "loss": 3.6743, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577201491388356e-05, + "loss": 3.6526, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568831922681565e-05, + "loss": 3.6605, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7560445975171045e-05, + "loss": 3.6511, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7552060027660525e-05, + "loss": 3.6607, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543674080150005e-05, + "loss": 3.652, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535288132639485e-05, + "loss": 3.6514, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526918563932694e-05, + "loss": 3.6581, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518532616422174e-05, + "loss": 3.6479, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510146668911654e-05, + "loss": 3.6646, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.867990493774414, + "eval_runtime": 313.8151, + "eval_samples_per_second": 1215.974, + "eval_steps_per_second": 38.0, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501760721401134e-05, + "loss": 3.6505, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493374773890614e-05, + "loss": 3.6425, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484988826380093e-05, + "loss": 3.6561, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476602878869573e-05, + "loss": 3.6533, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746823331016279e-05, + "loss": 3.6665, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745984736265227e-05, + "loss": 3.6525, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745146141514175e-05, + "loss": 3.651, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744307546763123e-05, + "loss": 3.6601, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743468952012071e-05, + "loss": 3.648, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742631995141392e-05, + "loss": 3.6477, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.74179340039034e-05, + "loss": 3.6576, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740954805639288e-05, + "loss": 3.6556, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740117848768609e-05, + "loss": 3.6582, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739279254017557e-05, + "loss": 3.6389, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738440659266505e-05, + "loss": 3.6464, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737602064515453e-05, + "loss": 3.6344, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367634697644014e-05, + "loss": 3.6472, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359248750133494e-05, + "loss": 3.656, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350862802622974e-05, + "loss": 3.635, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342476855112454e-05, + "loss": 3.6623, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733410728640566e-05, + "loss": 3.6623, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732572133889514e-05, + "loss": 3.6587, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731733539138462e-05, + "loss": 3.6535, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308949443874096e-05, + "loss": 3.6519, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730057987516731e-05, + "loss": 3.6543, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729219392765679e-05, + "loss": 3.6496, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728380798014627e-05, + "loss": 3.6444, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727542203263575e-05, + "loss": 3.6574, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726705246392897e-05, + "loss": 3.6378, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725866651641845e-05, + "loss": 3.6391, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725028056890793e-05, + "loss": 3.6505, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.72418946213974e-05, + "loss": 3.6507, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723350867388688e-05, + "loss": 3.6521, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7225139105180096e-05, + "loss": 3.6564, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721675315766957e-05, + "loss": 3.6434, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720836721015905e-05, + "loss": 3.6425, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719998126264853e-05, + "loss": 3.6486, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191611693941745e-05, + "loss": 3.6377, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718322574643122e-05, + "loss": 3.6431, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174839798920705e-05, + "loss": 3.6448, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166453851410185e-05, + "loss": 3.6382, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158067903899665e-05, + "loss": 3.6484, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149681956389145e-05, + "loss": 3.6541, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141312387682354e-05, + "loss": 3.6457, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132926440171834e-05, + "loss": 3.6444, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124540492661314e-05, + "loss": 3.6417, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116154545150794e-05, + "loss": 3.6481, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107784976444e-05, + "loss": 3.647, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709939902893348e-05, + "loss": 3.6277, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709101308142296e-05, + "loss": 3.6539, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708262713391244e-05, + "loss": 3.6358, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707425756520566e-05, + "loss": 3.65, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706587161769514e-05, + "loss": 3.6392, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705748567018462e-05, + "loss": 3.6319, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.70490997226741e-05, + "loss": 3.6279, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704073015396731e-05, + "loss": 3.6331, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703234420645679e-05, + "loss": 3.6543, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702395825894627e-05, + "loss": 3.6359, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701557231143575e-05, + "loss": 3.6562, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700720274272896e-05, + "loss": 3.6469, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699881679521844e-05, + "loss": 3.6235, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699043084770792e-05, + "loss": 3.6439, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.69820449001974e-05, + "loss": 3.6317, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973675331490606e-05, + "loss": 3.6291, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696528938398009e-05, + "loss": 3.6447, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695690343646957e-05, + "loss": 3.6452, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694851748895905e-05, + "loss": 3.6302, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694013154144853e-05, + "loss": 3.6395, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693176197274174e-05, + "loss": 3.6235, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692337602523122e-05, + "loss": 3.6341, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.69149900777207e-05, + "loss": 3.6398, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690660413021018e-05, + "loss": 3.644, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689823456150339e-05, + "loss": 3.6419, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688984861399287e-05, + "loss": 3.6416, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688146266648235e-05, + "loss": 3.6523, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687307671897183e-05, + "loss": 3.6345, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864707150265046e-05, + "loss": 3.6512, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856321202754526e-05, + "loss": 3.6282, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847935255244006e-05, + "loss": 3.6359, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839549307733486e-05, + "loss": 3.6442, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831163360222966e-05, + "loss": 3.6431, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822793791516175e-05, + "loss": 3.6459, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814407844005655e-05, + "loss": 3.6472, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806021896495135e-05, + "loss": 3.6247, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797635948984615e-05, + "loss": 3.6204, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789250001474095e-05, + "loss": 3.6417, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780880432767304e-05, + "loss": 3.6394, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772494485256784e-05, + "loss": 3.6341, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764108537746264e-05, + "loss": 3.6389, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755722590235744e-05, + "loss": 3.6363, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674733664272523e-05, + "loss": 3.6342, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673896707401844e-05, + "loss": 3.6338, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673058112650792e-05, + "loss": 3.6351, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.67221951789974e-05, + "loss": 3.6457, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671380923148688e-05, + "loss": 3.6493, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670543966278009e-05, + "loss": 3.6504, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669705371526957e-05, + "loss": 3.6262, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668866776775905e-05, + "loss": 3.6384, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668028182024853e-05, + "loss": 3.6372, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667191225154174e-05, + "loss": 3.6383, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666352630403122e-05, + "loss": 3.6392, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.66551403565207e-05, + "loss": 3.6353, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664675440901018e-05, + "loss": 3.6345, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638384840303393e-05, + "loss": 3.6316, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629998892792873e-05, + "loss": 3.6322, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662161294528235e-05, + "loss": 3.6355, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613226997771827e-05, + "loss": 3.631, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604841050261307e-05, + "loss": 3.6383, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659647148155452e-05, + "loss": 3.6342, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588085534044e-05, + "loss": 3.6286, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579699586533476e-05, + "loss": 3.6405, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571313639022955e-05, + "loss": 3.6297, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656294407031617e-05, + "loss": 3.64, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655455812280565e-05, + "loss": 3.6365, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654617217529513e-05, + "loss": 3.6376, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653778622778461e-05, + "loss": 3.6483, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652941665907783e-05, + "loss": 3.6378, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.65210307115673e-05, + "loss": 3.6349, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651264476405678e-05, + "loss": 3.6366, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650425881654626e-05, + "loss": 3.6291, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495889247839476e-05, + "loss": 3.6386, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648750330032895e-05, + "loss": 3.6319, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647911735281843e-05, + "loss": 3.6244, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647073140530791e-05, + "loss": 3.6432, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462361836601125e-05, + "loss": 3.6401, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453975889090605e-05, + "loss": 3.6359, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445589941580085e-05, + "loss": 3.6323, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437203994069565e-05, + "loss": 3.6288, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428818046559045e-05, + "loss": 3.6277, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420448477852254e-05, + "loss": 3.6426, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412062530341734e-05, + "loss": 3.6361, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403676582831214e-05, + "loss": 3.6431, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395290635320694e-05, + "loss": 3.614, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.63869210666139e-05, + "loss": 3.6469, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637853511910338e-05, + "loss": 3.6292, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637014917159286e-05, + "loss": 3.6489, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636176322408234e-05, + "loss": 3.6279, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635339365537556e-05, + "loss": 3.6323, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634500770786504e-05, + "loss": 3.6365, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633662176035452e-05, + "loss": 3.6559, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328235812844e-05, + "loss": 3.629, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631986624413721e-05, + "loss": 3.6431, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631148029662669e-05, + "loss": 3.6258, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630309434911617e-05, + "loss": 3.64, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629470840160565e-05, + "loss": 3.6289, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286338832898857e-05, + "loss": 3.6337, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6277952885388337e-05, + "loss": 3.635, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269566937877816e-05, + "loss": 3.6293, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261180990367296e-05, + "loss": 3.6408, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8651695251464844, + "eval_runtime": 312.925, + "eval_samples_per_second": 1219.433, + "eval_steps_per_second": 38.108, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625281142166051e-05, + "loss": 3.6312, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624442547414999e-05, + "loss": 3.6191, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623603952663947e-05, + "loss": 3.6359, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622765357912895e-05, + "loss": 3.6304, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621926763161843e-05, + "loss": 3.6464, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621089806291164e-05, + "loss": 3.6328, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620251211540112e-05, + "loss": 3.6318, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.61941261678906e-05, + "loss": 3.637, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618574022038008e-05, + "loss": 3.6263, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617737065167329e-05, + "loss": 3.6249, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616898470416277e-05, + "loss": 3.6404, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616059875665225e-05, + "loss": 3.6324, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152229187945466e-05, + "loss": 3.6413, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6143843240434946e-05, + "loss": 3.616, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135457292924426e-05, + "loss": 3.6211, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127071345413906e-05, + "loss": 3.6178, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118685397903386e-05, + "loss": 3.6277, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110299450392866e-05, + "loss": 3.6272, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101913502882346e-05, + "loss": 3.6205, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093527555371826e-05, + "loss": 3.6372, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085157986665035e-05, + "loss": 3.6458, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076772039154515e-05, + "loss": 3.6358, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068386091643995e-05, + "loss": 3.6319, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060000144133475e-05, + "loss": 3.6319, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051614196622955e-05, + "loss": 3.635, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604324462791617e-05, + "loss": 3.6266, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603485868040565e-05, + "loss": 3.6231, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602647273289513e-05, + "loss": 3.6349, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601808678538461e-05, + "loss": 3.6164, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009700837874083e-05, + "loss": 3.6185, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.60013312691673e-05, + "loss": 3.627, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599294532165678e-05, + "loss": 3.6305, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598455937414625e-05, + "loss": 3.6333, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597617342663573e-05, + "loss": 3.635, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596780385792895e-05, + "loss": 3.6229, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595941791041843e-05, + "loss": 3.6236, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595103196290791e-05, + "loss": 3.6258, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594264601539739e-05, + "loss": 3.6183, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934276446690604e-05, + "loss": 3.6274, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925890499180084e-05, + "loss": 3.619, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591750455166956e-05, + "loss": 3.6195, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590911860415904e-05, + "loss": 3.6264, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590073265664852e-05, + "loss": 3.6389, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892363087941726e-05, + "loss": 3.6187, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883977140431206e-05, + "loss": 3.6259, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875591192920686e-05, + "loss": 3.6259, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867205245410166e-05, + "loss": 3.6241, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858835676703375e-05, + "loss": 3.6268, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585044972919286e-05, + "loss": 3.61, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584206378168234e-05, + "loss": 3.6304, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583367783417182e-05, + "loss": 3.6202, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.58252918866613e-05, + "loss": 3.6304, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581692231795451e-05, + "loss": 3.6174, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580853637044399e-05, + "loss": 3.6112, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580015042293347e-05, + "loss": 3.6092, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579176447542295e-05, + "loss": 3.6095, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578339490671616e-05, + "loss": 3.6359, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577500895920564e-05, + "loss": 3.616, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576662301169512e-05, + "loss": 3.6348, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.57582370641846e-05, + "loss": 3.6235, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5749867495477816e-05, + "loss": 3.6062, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741481547967296e-05, + "loss": 3.6214, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733095600456775e-05, + "loss": 3.6119, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724709652946255e-05, + "loss": 3.6093, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716340084239465e-05, + "loss": 3.6228, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707954136728944e-05, + "loss": 3.624, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5699568189218424e-05, + "loss": 3.6096, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5691182241707904e-05, + "loss": 3.6204, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5682796294197384e-05, + "loss": 3.6001, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.5674426725490593e-05, + "loss": 3.6149, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5666040777980073e-05, + "loss": 3.6194, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565765483046955e-05, + "loss": 3.6278, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564926888295903e-05, + "loss": 3.6213, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564089931425225e-05, + "loss": 3.6212, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563251336674173e-05, + "loss": 3.6328, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562412741923121e-05, + "loss": 3.619, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561574147172069e-05, + "loss": 3.6298, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.56073719030139e-05, + "loss": 3.612, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559898595550338e-05, + "loss": 3.6157, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559060000799286e-05, + "loss": 3.6199, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558221406048234e-05, + "loss": 3.6218, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557382811297182e-05, + "loss": 3.6215, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556545854426503e-05, + "loss": 3.63, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555707259675451e-05, + "loss": 3.6077, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554868664924399e-05, + "loss": 3.5999, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554030070173347e-05, + "loss": 3.6177, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553193113302668e-05, + "loss": 3.6245, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552354518551616e-05, + "loss": 3.6142, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551515923800564e-05, + "loss": 3.621, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550677329049512e-05, + "loss": 3.6133, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549840372178833e-05, + "loss": 3.6147, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549001777427781e-05, + "loss": 3.6142, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548163182676729e-05, + "loss": 3.6156, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547324587925677e-05, + "loss": 3.6219, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546487631054998e-05, + "loss": 3.6298, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545649036303946e-05, + "loss": 3.6306, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544810441552894e-05, + "loss": 3.6052, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543971846801842e-05, + "loss": 3.6207, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431348899311636e-05, + "loss": 3.6147, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422962951801116e-05, + "loss": 3.619, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414577004290596e-05, + "loss": 3.6201, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406191056780076e-05, + "loss": 3.6123, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5397805109269556e-05, + "loss": 3.6143, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389435540562765e-05, + "loss": 3.6124, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5381049593052245e-05, + "loss": 3.6123, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372663645541725e-05, + "loss": 3.6162, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364277698031205e-05, + "loss": 3.6102, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355908129324414e-05, + "loss": 3.6185, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347522181813894e-05, + "loss": 3.6188, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5339136234303374e-05, + "loss": 3.6093, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330750286792854e-05, + "loss": 3.6175, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532238071808607e-05, + "loss": 3.614, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531399477057555e-05, + "loss": 3.619, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530560882306503e-05, + "loss": 3.6171, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529722287555451e-05, + "loss": 3.6135, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528885330684772e-05, + "loss": 3.6272, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.52804673593372e-05, + "loss": 3.6262, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527208141182668e-05, + "loss": 3.614, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526369546431616e-05, + "loss": 3.6168, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525532589560937e-05, + "loss": 3.6084, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524693994809885e-05, + "loss": 3.6188, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523855400058833e-05, + "loss": 3.6133, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523016805307781e-05, + "loss": 3.6034, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522178210556729e-05, + "loss": 3.624, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213412536860504e-05, + "loss": 3.6204, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5205026589349984e-05, + "loss": 3.6178, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519664064183946e-05, + "loss": 3.6161, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518825469432894e-05, + "loss": 3.6065, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517988512562215e-05, + "loss": 3.607, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517149917811163e-05, + "loss": 3.6222, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163113230601106e-05, + "loss": 3.6193, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154727283090586e-05, + "loss": 3.6256, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.51463577143838e-05, + "loss": 3.5965, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513797176687328e-05, + "loss": 3.6195, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512958581936276e-05, + "loss": 3.6149, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512119987185224e-05, + "loss": 3.6234, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511283030314546e-05, + "loss": 3.6118, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510444435563493e-05, + "loss": 3.6101, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509605840812441e-05, + "loss": 3.6179, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508767246061389e-05, + "loss": 3.6328, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507928651310337e-05, + "loss": 3.6125, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507091694439658e-05, + "loss": 3.6204, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506253099688606e-05, + "loss": 3.6075, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505414504937554e-05, + "loss": 3.6176, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504575910186502e-05, + "loss": 3.6138, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037389533158235e-05, + "loss": 3.6123, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5029003585647715e-05, + "loss": 3.6164, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020617638137195e-05, + "loss": 3.6131, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012231690626675e-05, + "loss": 3.6168, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.86417293548584, + "eval_runtime": 309.2095, + "eval_samples_per_second": 1234.086, + "eval_steps_per_second": 38.566, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003862121919884e-05, + "loss": 3.6289, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995476174409364e-05, + "loss": 3.5953, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987090226898844e-05, + "loss": 3.6159, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978704279388324e-05, + "loss": 3.6134, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497033471068153e-05, + "loss": 3.6209, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496194876317101e-05, + "loss": 3.6201, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495356281566049e-05, + "loss": 3.6109, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494517686814997e-05, + "loss": 3.6176, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493679092063945e-05, + "loss": 3.609, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492842135193267e-05, + "loss": 3.6112, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492003540442215e-05, + "loss": 3.6167, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491164945691163e-05, + "loss": 3.6151, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490327988820484e-05, + "loss": 3.6222, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489489394069432e-05, + "loss": 3.5971, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.48865079931838e-05, + "loss": 3.6022, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487812204567328e-05, + "loss": 3.5973, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486973609816276e-05, + "loss": 3.6109, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486135015065224e-05, + "loss": 3.6067, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485296420314172e-05, + "loss": 3.6059, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.48445782556312e-05, + "loss": 3.6145, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483620868692441e-05, + "loss": 3.6276, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4827822739413893e-05, + "loss": 3.6155, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481943679190337e-05, + "loss": 3.6122, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481105084439285e-05, + "loss": 3.6142, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480268127568606e-05, + "loss": 3.622, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479429532817554e-05, + "loss": 3.6041, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478590938066502e-05, + "loss": 3.6043, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.47775234331545e-05, + "loss": 3.6172, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476915386444771e-05, + "loss": 3.5941, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476076791693719e-05, + "loss": 3.6002, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475238196942667e-05, + "loss": 3.6084, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474399602191615e-05, + "loss": 3.6098, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473562645320936e-05, + "loss": 3.615, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472724050569884e-05, + "loss": 3.6147, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471885455818833e-05, + "loss": 3.6065, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471046861067781e-05, + "loss": 3.6038, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702099041971016e-05, + "loss": 3.607, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4693713094460496e-05, + "loss": 3.5974, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4685327146949976e-05, + "loss": 3.6091, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4676941199439456e-05, + "loss": 3.5993, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668571630732665e-05, + "loss": 3.604, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660185683222145e-05, + "loss": 3.6074, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4651799735711625e-05, + "loss": 3.62, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4643413788201105e-05, + "loss": 3.6011, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4635044219494314e-05, + "loss": 3.6084, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626658271983794e-05, + "loss": 3.6093, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461827232447328e-05, + "loss": 3.603, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460988637696276e-05, + "loss": 3.6093, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460150042945224e-05, + "loss": 3.5921, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459313086074545e-05, + "loss": 3.6077, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458474491323493e-05, + "loss": 3.6041, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457635896572441e-05, + "loss": 3.608, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456797301821388e-05, + "loss": 3.6011, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.45596034495071e-05, + "loss": 3.593, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455121750199658e-05, + "loss": 3.5908, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454283155448606e-05, + "loss": 3.5899, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453444560697553e-05, + "loss": 3.6196, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452607603826875e-05, + "loss": 3.597, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517690090758234e-05, + "loss": 3.6143, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509304143247714e-05, + "loss": 3.604, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450091819573719e-05, + "loss": 3.5891, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4492548627030403e-05, + "loss": 3.6027, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448416267951988e-05, + "loss": 3.5939, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475776732009357e-05, + "loss": 3.593, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467390784498836e-05, + "loss": 3.5998, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445902121579205e-05, + "loss": 3.6067, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445063526828153e-05, + "loss": 3.5951, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442249320771005e-05, + "loss": 3.5983, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433863373260485e-05, + "loss": 3.583, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.44254938045537e-05, + "loss": 3.5969, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441710785704318e-05, + "loss": 3.6011, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440872190953266e-05, + "loss": 3.6079, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440033596202214e-05, + "loss": 3.606, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439195001451162e-05, + "loss": 3.6047, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438358044580483e-05, + "loss": 3.6085, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437519449829431e-05, + "loss": 3.599, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436680855078379e-05, + "loss": 3.6095, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435842260327327e-05, + "loss": 3.5947, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435005303456648e-05, + "loss": 3.6002, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434166708705596e-05, + "loss": 3.5998, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433328113954544e-05, + "loss": 3.603, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324895192034926e-05, + "loss": 3.6085, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316525623328135e-05, + "loss": 3.6115, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308139675817615e-05, + "loss": 3.5904, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4299753728307095e-05, + "loss": 3.578, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291367780796575e-05, + "loss": 3.6019, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282998212089784e-05, + "loss": 3.6047, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274612264579264e-05, + "loss": 3.5963, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266226317068744e-05, + "loss": 3.6022, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4257840369558224e-05, + "loss": 3.5986, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424947080085143e-05, + "loss": 3.5942, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424108485334091e-05, + "loss": 3.5975, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423269890583039e-05, + "loss": 3.5962, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422431295831988e-05, + "loss": 3.6028, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421594338961309e-05, + "loss": 3.6121, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420755744210257e-05, + "loss": 3.6126, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419917149459205e-05, + "loss": 3.588, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419078554708153e-05, + "loss": 3.6013, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418241597837474e-05, + "loss": 3.6006, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417403003086422e-05, + "loss": 3.6021, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.41656440833537e-05, + "loss": 3.6007, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415725813584318e-05, + "loss": 3.5965, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414887218833266e-05, + "loss": 3.595, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140502619625866e-05, + "loss": 3.5954, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132116672115346e-05, + "loss": 3.5952, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412373072460483e-05, + "loss": 3.5958, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411534477709431e-05, + "loss": 3.5913, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410697520838752e-05, + "loss": 3.6022, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098589260877e-05, + "loss": 3.5992, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409020331336648e-05, + "loss": 3.5914, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408181736585596e-05, + "loss": 3.6014, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407344779714917e-05, + "loss": 3.5933, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406506184963865e-05, + "loss": 3.6032, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405667590212813e-05, + "loss": 3.5996, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404828995461761e-05, + "loss": 3.5989, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403992038591082e-05, + "loss": 3.6039, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.40315344384003e-05, + "loss": 3.611, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402314849088979e-05, + "loss": 3.5951, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401476254337927e-05, + "loss": 3.5989, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4006392974672476e-05, + "loss": 3.5924, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3998007027161956e-05, + "loss": 3.6016, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.3989621079651436e-05, + "loss": 3.5958, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.3981235132140916e-05, + "loss": 3.5836, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3972865563434125e-05, + "loss": 3.603, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3964479615923605e-05, + "loss": 3.6033, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3956093668413085e-05, + "loss": 3.6008, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947707720902565e-05, + "loss": 3.5969, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939338152195774e-05, + "loss": 3.5866, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3930952204685254e-05, + "loss": 3.5917, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392256625717474e-05, + "loss": 3.6063, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391418030966422e-05, + "loss": 3.5994, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390581074095743e-05, + "loss": 3.6084, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389742479344691e-05, + "loss": 3.5786, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388903884593639e-05, + "loss": 3.6017, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388065289842587e-05, + "loss": 3.5998, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387228332971908e-05, + "loss": 3.6016, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386389738220856e-05, + "loss": 3.5927, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385551143469804e-05, + "loss": 3.5937, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384712548718752e-05, + "loss": 3.5989, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383875591848073e-05, + "loss": 3.6173, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383036997097021e-05, + "loss": 3.5956, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382198402345969e-05, + "loss": 3.6021, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3813598075949174e-05, + "loss": 3.5939, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380522850724238e-05, + "loss": 3.6002, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379684255973186e-05, + "loss": 3.5927, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378845661222134e-05, + "loss": 3.6015, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378007066471082e-05, + "loss": 3.5915, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377170109600403e-05, + "loss": 3.5957, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376331514849351e-05, + "loss": 3.6004, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8642704486846924, + "eval_runtime": 323.2529, + "eval_samples_per_second": 1180.472, + "eval_steps_per_second": 36.891, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375492920098299e-05, + "loss": 3.5988, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374654325347247e-05, + "loss": 3.5798, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373817368476568e-05, + "loss": 3.5938, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372978773725516e-05, + "loss": 3.602, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372140178974464e-05, + "loss": 3.5986, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371301584223413e-05, + "loss": 3.6036, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370464627352734e-05, + "loss": 3.5897, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369626032601682e-05, + "loss": 3.6014, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.36878743785063e-05, + "loss": 3.5904, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367948843099578e-05, + "loss": 3.5928, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367110248348526e-05, + "loss": 3.5974, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662732914778466e-05, + "loss": 3.5973, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654363346071675e-05, + "loss": 3.6075, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3645977398561155e-05, + "loss": 3.5809, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637591451050635e-05, + "loss": 3.5793, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629205503540115e-05, + "loss": 3.5844, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3620819556029595e-05, + "loss": 3.5926, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361243360851908e-05, + "loss": 3.5866, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360404766100856e-05, + "loss": 3.5879, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3595661713498035e-05, + "loss": 3.5991, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358729214479125e-05, + "loss": 3.6059, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357890619728073e-05, + "loss": 3.6017, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3570520249770204e-05, + "loss": 3.5937, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3562134302259684e-05, + "loss": 3.5948, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3553748354749164e-05, + "loss": 3.6008, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354537878604238e-05, + "loss": 3.5887, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353699283853185e-05, + "loss": 3.5874, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352860689102133e-05, + "loss": 3.602, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352022094351082e-05, + "loss": 3.5736, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3511851374804035e-05, + "loss": 3.5858, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350346542729351e-05, + "loss": 3.5857, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349507947978299e-05, + "loss": 3.596, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348669353227247e-05, + "loss": 3.5965, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347830758476195e-05, + "loss": 3.5965, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346993801605516e-05, + "loss": 3.592, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346155206854464e-05, + "loss": 3.5871, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345316612103412e-05, + "loss": 3.5869, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.34447801735236e-05, + "loss": 3.5775, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436410604816806e-05, + "loss": 3.5955, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3428024657306286e-05, + "loss": 3.5813, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341963870979577e-05, + "loss": 3.5882, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341125276228525e-05, + "loss": 3.5862, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340288319357846e-05, + "loss": 3.6027, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339449724606794e-05, + "loss": 3.5866, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338611129855742e-05, + "loss": 3.5887, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.33777253510469e-05, + "loss": 3.5928, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336935578234011e-05, + "loss": 3.5877, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336096983482959e-05, + "loss": 3.5885, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335258388731907e-05, + "loss": 3.5762, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334419793980855e-05, + "loss": 3.5891, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333582837110176e-05, + "loss": 3.591, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332744242359124e-05, + "loss": 3.5888, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3319056476080727e-05, + "loss": 3.5834, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3310670528570207e-05, + "loss": 3.5734, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302300959863416e-05, + "loss": 3.5775, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3293915012352896e-05, + "loss": 3.5693, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285529064842376e-05, + "loss": 3.6056, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277143117331856e-05, + "loss": 3.5777, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3268773548625065e-05, + "loss": 3.6004, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260387601114545e-05, + "loss": 3.5817, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3252001653604025e-05, + "loss": 3.5727, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3243615706093504e-05, + "loss": 3.5822, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3235229758582984e-05, + "loss": 3.5772, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3226860189876194e-05, + "loss": 3.5788, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321847424236568e-05, + "loss": 3.5777, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321008829485516e-05, + "loss": 3.5924, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320170234734464e-05, + "loss": 3.5805, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319333277863785e-05, + "loss": 3.5773, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318494683112733e-05, + "loss": 3.5681, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317656088361681e-05, + "loss": 3.5798, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316817493610629e-05, + "loss": 3.5823, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315978898859577e-05, + "loss": 3.5911, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315141941988898e-05, + "loss": 3.5872, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314303347237846e-05, + "loss": 3.5887, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313464752486794e-05, + "loss": 3.5892, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312627795616115e-05, + "loss": 3.5833, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3117892008650634e-05, + "loss": 3.5878, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109506061140114e-05, + "loss": 3.5793, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101120113629594e-05, + "loss": 3.5863, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.30927505449228e-05, + "loss": 3.5816, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308436459741228e-05, + "loss": 3.5854, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307597864990176e-05, + "loss": 3.5957, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306759270239124e-05, + "loss": 3.5926, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305920675488072e-05, + "loss": 3.5772, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305083718617393e-05, + "loss": 3.5589, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304245123866341e-05, + "loss": 3.5863, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303406529115289e-05, + "loss": 3.5846, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302567934364237e-05, + "loss": 3.5822, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301730977493558e-05, + "loss": 3.58, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300892382742507e-05, + "loss": 3.5867, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300053787991455e-05, + "loss": 3.5767, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299215193240403e-05, + "loss": 3.5787, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2983782363697237e-05, + "loss": 3.5808, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975396416186717e-05, + "loss": 3.585, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2967010468676196e-05, + "loss": 3.5951, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2958624521165676e-05, + "loss": 3.5944, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2950254952458886e-05, + "loss": 3.572, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2941869004948365e-05, + "loss": 3.5836, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2933483057437845e-05, + "loss": 3.5835, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2925097109927325e-05, + "loss": 3.5857, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916727541220534e-05, + "loss": 3.5826, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290834159371002e-05, + "loss": 3.5813, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.28999556461995e-05, + "loss": 3.5752, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289156969868898e-05, + "loss": 3.5784, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288318375117846e-05, + "loss": 3.5825, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287481418247167e-05, + "loss": 3.5743, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286642823496115e-05, + "loss": 3.5772, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285804228745063e-05, + "loss": 3.5823, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284965633994011e-05, + "loss": 3.5778, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284128677123332e-05, + "loss": 3.5754, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.28329008237228e-05, + "loss": 3.5898, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282451487621228e-05, + "loss": 3.5733, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281612892870176e-05, + "loss": 3.5865, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2807759359994975e-05, + "loss": 3.5835, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799373412484455e-05, + "loss": 3.5783, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2790987464973935e-05, + "loss": 3.5893, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278260151746341e-05, + "loss": 3.5945, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774231948756624e-05, + "loss": 3.5816, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2765846001246104e-05, + "loss": 3.5824, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757460053735584e-05, + "loss": 3.5751, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274907410622506e-05, + "loss": 3.5821, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274070453751827e-05, + "loss": 3.5798, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273231859000775e-05, + "loss": 3.5735, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2723932642497226e-05, + "loss": 3.5809, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271554669498671e-05, + "loss": 3.5906, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270716074747619e-05, + "loss": 3.5821, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269879117876941e-05, + "loss": 3.5807, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269040523125888e-05, + "loss": 3.5708, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268201928374836e-05, + "loss": 3.5755, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267363333623784e-05, + "loss": 3.5835, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266526376753106e-05, + "loss": 3.581, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265687782002053e-05, + "loss": 3.5928, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264849187251001e-05, + "loss": 3.5654, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264010592499949e-05, + "loss": 3.583, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.26317363562927e-05, + "loss": 3.584, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262335040878218e-05, + "loss": 3.5838, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2614964461271666e-05, + "loss": 3.5756, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2606578513761146e-05, + "loss": 3.5759, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2598208945054355e-05, + "loss": 3.5885, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2589822997543835e-05, + "loss": 3.5968, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581437050033315e-05, + "loss": 3.5805, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2573051102522795e-05, + "loss": 3.5832, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2564681533816004e-05, + "loss": 3.5764, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556295586305484e-05, + "loss": 3.5816, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2547909638794964e-05, + "loss": 3.5757, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539523691284444e-05, + "loss": 3.5866, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531137743773924e-05, + "loss": 3.5735, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252276817506713e-05, + "loss": 3.5801, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251438222755662e-05, + "loss": 3.5813, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8644797801971436, + "eval_runtime": 304.0801, + "eval_samples_per_second": 1254.903, + "eval_steps_per_second": 39.217, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.25059962800461e-05, + "loss": 3.5757, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249761033253558e-05, + "loss": 3.5698, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248922438502506e-05, + "loss": 3.5731, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248083843751454e-05, + "loss": 3.5854, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247245249000402e-05, + "loss": 3.5813, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246408292129723e-05, + "loss": 3.5888, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245569697378671e-05, + "loss": 3.5721, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244731102627619e-05, + "loss": 3.5855, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243892507876567e-05, + "loss": 3.574, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243055551005888e-05, + "loss": 3.5755, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242216956254836e-05, + "loss": 3.5787, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241378361503784e-05, + "loss": 3.5824, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405414046331054e-05, + "loss": 3.5923, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2397028098820534e-05, + "loss": 3.5687, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2388642151310014e-05, + "loss": 3.5593, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.2380256203799494e-05, + "loss": 3.5705, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2371870256288973e-05, + "loss": 3.5721, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363484308778453e-05, + "loss": 3.5734, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235509836126793e-05, + "loss": 3.572, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234671241375741e-05, + "loss": 3.5797, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338326466246887e-05, + "loss": 3.5923, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.23299568975401e-05, + "loss": 3.5798, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232157095002958e-05, + "loss": 3.5795, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231318500251906e-05, + "loss": 3.5808, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230479905500854e-05, + "loss": 3.5877, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229642948630175e-05, + "loss": 3.5681, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228804353879124e-05, + "loss": 3.5766, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227965759128072e-05, + "loss": 3.5814, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227127164377019e-05, + "loss": 3.562, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226290207506341e-05, + "loss": 3.565, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225451612755289e-05, + "loss": 3.5688, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224613018004236e-05, + "loss": 3.5801, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223774423253184e-05, + "loss": 3.5842, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2229374663825056e-05, + "loss": 3.574, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2220988716314536e-05, + "loss": 3.5804, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221260276880401e-05, + "loss": 3.568, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220421682129349e-05, + "loss": 3.5662, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2195847252586705e-05, + "loss": 3.5645, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218746130507619e-05, + "loss": 3.5773, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2179075357565665e-05, + "loss": 3.5629, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170689410055145e-05, + "loss": 3.5697, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162303462544625e-05, + "loss": 3.5737, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2153933893837834e-05, + "loss": 3.5862, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145547946327314e-05, + "loss": 3.5684, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2137161998816794e-05, + "loss": 3.5759, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2128776051306274e-05, + "loss": 3.5771, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212040648259948e-05, + "loss": 3.5681, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211202053508896e-05, + "loss": 3.5763, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210363458757844e-05, + "loss": 3.5634, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209524864006793e-05, + "loss": 3.5707, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208687907136114e-05, + "loss": 3.5776, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207849312385062e-05, + "loss": 3.5694, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.20701071763401e-05, + "loss": 3.5671, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206172122882958e-05, + "loss": 3.5529, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205335166012279e-05, + "loss": 3.5677, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204496571261227e-05, + "loss": 3.5495, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203657976510175e-05, + "loss": 3.5893, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202819381759123e-05, + "loss": 3.5624, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2019824248884437e-05, + "loss": 3.5855, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011438301373917e-05, + "loss": 3.5667, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2003052353863396e-05, + "loss": 3.554, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199466640635288e-05, + "loss": 3.5663, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198628045884236e-05, + "loss": 3.5694, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197791089013557e-05, + "loss": 3.5605, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196952494262505e-05, + "loss": 3.5562, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196113899511453e-05, + "loss": 3.5799, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195275304760401e-05, + "loss": 3.5681, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194438347889722e-05, + "loss": 3.5569, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.19359975313867e-05, + "loss": 3.5548, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192761158387618e-05, + "loss": 3.5629, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191922563636566e-05, + "loss": 3.5654, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191083968885514e-05, + "loss": 3.578, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190247012014835e-05, + "loss": 3.5686, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189408417263784e-05, + "loss": 3.573, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188569822512732e-05, + "loss": 3.5725, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.18773122776168e-05, + "loss": 3.5672, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1868942708910006e-05, + "loss": 3.5728, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860556761399486e-05, + "loss": 3.5612, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852170813888966e-05, + "loss": 3.5722, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1843784866378446e-05, + "loss": 3.5659, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835415297671655e-05, + "loss": 3.5645, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1827029350161135e-05, + "loss": 3.5767, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818643402650615e-05, + "loss": 3.5766, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810257455140095e-05, + "loss": 3.5611, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801887886433304e-05, + "loss": 3.5434, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179350193892279e-05, + "loss": 3.572, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178511599141227e-05, + "loss": 3.564, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177673004390175e-05, + "loss": 3.5708, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176834409639123e-05, + "loss": 3.5627, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175997452768444e-05, + "loss": 3.5704, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175158858017392e-05, + "loss": 3.5663, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.17432026326634e-05, + "loss": 3.5606, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173483306395661e-05, + "loss": 3.5637, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172644711644609e-05, + "loss": 3.5681, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171806116893557e-05, + "loss": 3.5788, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170967522142505e-05, + "loss": 3.5774, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170130565271826e-05, + "loss": 3.5602, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1692919705207744e-05, + "loss": 3.5652, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684533757697224e-05, + "loss": 3.5704, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676147810186704e-05, + "loss": 3.5698, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166777824147991e-05, + "loss": 3.5626, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165939229396939e-05, + "loss": 3.5653, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165100634645887e-05, + "loss": 3.5616, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164262039894835e-05, + "loss": 3.5589, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163423445143783e-05, + "loss": 3.5703, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162586488273104e-05, + "loss": 3.5543, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161747893522052e-05, + "loss": 3.5606, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160909298771e-05, + "loss": 3.5705, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160070704019948e-05, + "loss": 3.5607, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.15923374714927e-05, + "loss": 3.5589, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158395152398218e-05, + "loss": 3.5751, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157556557647166e-05, + "loss": 3.5576, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156717962896114e-05, + "loss": 3.5694, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155879368145062e-05, + "loss": 3.5655, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155042411274383e-05, + "loss": 3.5645, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154203816523331e-05, + "loss": 3.5724, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153365221772279e-05, + "loss": 3.5762, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152526627021227e-05, + "loss": 3.5666, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516896701505476e-05, + "loss": 3.5638, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508510753994956e-05, + "loss": 3.5595, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500124806484436e-05, + "loss": 3.5687, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491738858973916e-05, + "loss": 3.5612, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148336929026713e-05, + "loss": 3.5603, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147498334275661e-05, + "loss": 3.563, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146659739524609e-05, + "loss": 3.5732, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458211447735565e-05, + "loss": 3.5652, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144984187902878e-05, + "loss": 3.567, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144145593151826e-05, + "loss": 3.5581, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143306998400774e-05, + "loss": 3.5591, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424684036497214e-05, + "loss": 3.5648, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141631446779043e-05, + "loss": 3.5705, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140792852027991e-05, + "loss": 3.5751, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139954257276938e-05, + "loss": 3.5513, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139115662525887e-05, + "loss": 3.5714, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1382787056552085e-05, + "loss": 3.5676, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374401109041565e-05, + "loss": 3.5672, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136601516153104e-05, + "loss": 3.5581, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135762921402052e-05, + "loss": 3.5651, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349259645313734e-05, + "loss": 3.5718, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1340873697803214e-05, + "loss": 3.58, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133248775029269e-05, + "loss": 3.5653, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132410180278217e-05, + "loss": 3.5658, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131573223407538e-05, + "loss": 3.5643, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307346286564856e-05, + "loss": 3.5635, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1298960339054336e-05, + "loss": 3.5603, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129057439154382e-05, + "loss": 3.5758, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.12821884440333e-05, + "loss": 3.556, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127381887532651e-05, + "loss": 3.5722, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126543292781599e-05, + "loss": 3.5608, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.865694522857666, + "eval_runtime": 303.0655, + "eval_samples_per_second": 1259.104, + "eval_steps_per_second": 39.348, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125704698030547e-05, + "loss": 3.5632, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124866103279495e-05, + "loss": 3.5553, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124029146408816e-05, + "loss": 3.5573, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123190551657764e-05, + "loss": 3.5695, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122351956906712e-05, + "loss": 3.5664, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.12151336215566e-05, + "loss": 3.574, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120676405284981e-05, + "loss": 3.5561, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119837810533929e-05, + "loss": 3.5734, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118999215782878e-05, + "loss": 3.5556, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1181606210318257e-05, + "loss": 3.5632, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1173220262807737e-05, + "loss": 3.5616, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1164850694100946e-05, + "loss": 3.5672, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156464746590426e-05, + "loss": 3.5684, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1148095177883635e-05, + "loss": 3.5611, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1139709230373115e-05, + "loss": 3.5492, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1131323282862595e-05, + "loss": 3.5549, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1122937335352075e-05, + "loss": 3.5523, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114551387841555e-05, + "loss": 3.5568, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106165440331034e-05, + "loss": 3.5592, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1097779492820514e-05, + "loss": 3.5594, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1089393545309994e-05, + "loss": 3.5788, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108102397660321e-05, + "loss": 3.5655, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107263802909269e-05, + "loss": 3.566, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106425208158217e-05, + "loss": 3.5655, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105586613407165e-05, + "loss": 3.5736, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104749656536486e-05, + "loss": 3.5497, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103911061785434e-05, + "loss": 3.5618, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103072467034382e-05, + "loss": 3.5638, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102235510163703e-05, + "loss": 3.5528, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101396915412651e-05, + "loss": 3.5451, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100558320661599e-05, + "loss": 3.5537, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099719725910547e-05, + "loss": 3.5653, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098881131159495e-05, + "loss": 3.5656, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980441742888164e-05, + "loss": 3.5633, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972055795377644e-05, + "loss": 3.564, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963669847867124e-05, + "loss": 3.5537, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095530027916033e-05, + "loss": 3.5509, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094691433164981e-05, + "loss": 3.5481, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093852838413929e-05, + "loss": 3.5635, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093014243662877e-05, + "loss": 3.5484, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092175648911825e-05, + "loss": 3.5572, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091337054160773e-05, + "loss": 3.5537, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090500097290094e-05, + "loss": 3.5723, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089661502539042e-05, + "loss": 3.5512, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.08882290778799e-05, + "loss": 3.5569, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087984313036938e-05, + "loss": 3.5626, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.08714735616626e-05, + "loss": 3.552, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086308761415208e-05, + "loss": 3.563, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085470166664156e-05, + "loss": 3.5474, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084631571913104e-05, + "loss": 3.5559, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0837946150424246e-05, + "loss": 3.56, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829560202913726e-05, + "loss": 3.5565, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0821174255403206e-05, + "loss": 3.553, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0812788307892686e-05, + "loss": 3.5383, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804402360382166e-05, + "loss": 3.5539, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0796032791675375e-05, + "loss": 3.5358, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787646844164855e-05, + "loss": 3.5725, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779260896654335e-05, + "loss": 3.5501, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077089132794755e-05, + "loss": 3.566, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076250538043703e-05, + "loss": 3.5569, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075411943292651e-05, + "loss": 3.5423, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074573348541599e-05, + "loss": 3.5477, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0737347537905464e-05, + "loss": 3.5529, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0728961590394944e-05, + "loss": 3.5462, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072059202168816e-05, + "loss": 3.5385, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071220607417764e-05, + "loss": 3.5633, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070382012666711e-05, + "loss": 3.5585, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069543417915659e-05, + "loss": 3.5421, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068706461044981e-05, + "loss": 3.5356, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067867866293929e-05, + "loss": 3.5465, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067029271542877e-05, + "loss": 3.5524, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066190676791825e-05, + "loss": 3.5639, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653537199211465e-05, + "loss": 3.5535, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064515125170094e-05, + "loss": 3.5588, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063676530419042e-05, + "loss": 3.5555, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.06283793566799e-05, + "loss": 3.5581, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620009787973114e-05, + "loss": 3.5546, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061162384046259e-05, + "loss": 3.5498, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060323789295207e-05, + "loss": 3.5604, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059485194544155e-05, + "loss": 3.5512, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058648237673476e-05, + "loss": 3.5514, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057809642922424e-05, + "loss": 3.5624, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056971048171372e-05, + "loss": 3.5584, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.05613245342032e-05, + "loss": 3.545, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055293858669268e-05, + "loss": 3.53, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054456901798589e-05, + "loss": 3.5533, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053618307047537e-05, + "loss": 3.5543, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052779712296485e-05, + "loss": 3.5531, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051941117545433e-05, + "loss": 3.5518, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511041606747544e-05, + "loss": 3.5535, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502655659237024e-05, + "loss": 3.5506, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494269711726504e-05, + "loss": 3.5418, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485883764215984e-05, + "loss": 3.5496, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477514195509193e-05, + "loss": 3.5572, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469128247998673e-05, + "loss": 3.5629, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460742300488153e-05, + "loss": 3.5592, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452372731781365e-05, + "loss": 3.5535, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443986784270845e-05, + "loss": 3.5465, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435600836760325e-05, + "loss": 3.5539, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427214889249805e-05, + "loss": 3.5544, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418845320543014e-05, + "loss": 3.5513, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410459373032498e-05, + "loss": 3.5498, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402073425521978e-05, + "loss": 3.5472, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393687478011458e-05, + "loss": 3.5417, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385301530500938e-05, + "loss": 3.5597, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376931961794147e-05, + "loss": 3.5378, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368546014283627e-05, + "loss": 3.5466, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360160066773107e-05, + "loss": 3.5539, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035177411926259e-05, + "loss": 3.5484, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.03434045505558e-05, + "loss": 3.5429, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033501860304528e-05, + "loss": 3.5545, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032663265553476e-05, + "loss": 3.5476, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031824670802424e-05, + "loss": 3.5512, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030986076051372e-05, + "loss": 3.5522, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030149119180693e-05, + "loss": 3.5504, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029310524429641e-05, + "loss": 3.5576, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028471929678589e-05, + "loss": 3.5629, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027633334927537e-05, + "loss": 3.5501, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026796378056858e-05, + "loss": 3.5482, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025957783305806e-05, + "loss": 3.5486, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.025119188554754e-05, + "loss": 3.5511, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242805938037023e-05, + "loss": 3.5433, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234436369330233e-05, + "loss": 3.5461, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226050421819713e-05, + "loss": 3.5488, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217664474309192e-05, + "loss": 3.561, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209278526798672e-05, + "loss": 3.549, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200908958091885e-05, + "loss": 3.5532, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192523010581365e-05, + "loss": 3.5443, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184137063070845e-05, + "loss": 3.5483, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175751115560325e-05, + "loss": 3.5469, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167381546853534e-05, + "loss": 3.5578, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0158995599343014e-05, + "loss": 3.5594, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150609651832494e-05, + "loss": 3.5375, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142223704321977e-05, + "loss": 3.5502, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133854135615186e-05, + "loss": 3.5579, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125468188104666e-05, + "loss": 3.551, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117082240594146e-05, + "loss": 3.5467, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108696293083626e-05, + "loss": 3.5456, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010032672437684e-05, + "loss": 3.5588, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009194077686632e-05, + "loss": 3.5638, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.00835548293558e-05, + "loss": 3.5517, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007516888184528e-05, + "loss": 3.5528, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066799313138488e-05, + "loss": 3.5481, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058413365627968e-05, + "loss": 3.547, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050027418117447e-05, + "loss": 3.5441, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004164147060693e-05, + "loss": 3.5631, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003327190190014e-05, + "loss": 3.5422, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002488595438962e-05, + "loss": 3.5544, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.00165000068791e-05, + "loss": 3.5444, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000811405936858e-05, + "loss": 3.5501, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.86727237701416, + "eval_runtime": 303.9085, + "eval_samples_per_second": 1255.612, + "eval_steps_per_second": 39.239, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999972811185806e-05, + "loss": 3.5389, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999134216434754e-05, + "loss": 3.5421, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982956216837016e-05, + "loss": 3.556, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974570269326496e-05, + "loss": 3.5484, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966200700619712e-05, + "loss": 3.5638, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957814753109192e-05, + "loss": 3.5407, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994942880559867e-05, + "loss": 3.5541, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994104285808815e-05, + "loss": 3.5434, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932673289381364e-05, + "loss": 3.5501, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924287341870838e-05, + "loss": 3.5474, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915901394360318e-05, + "loss": 3.5523, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907515446849798e-05, + "loss": 3.5551, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899145878143013e-05, + "loss": 3.5458, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989075993063249e-05, + "loss": 3.5348, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988237398312197e-05, + "loss": 3.5446, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987398803561145e-05, + "loss": 3.5339, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986560208810093e-05, + "loss": 3.5435, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985721614059041e-05, + "loss": 3.544, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984883019307989e-05, + "loss": 3.5437, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984044424556937e-05, + "loss": 3.5638, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832074676862582e-05, + "loss": 3.554, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823688729352062e-05, + "loss": 3.5529, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815302781841542e-05, + "loss": 3.5463, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806916834331022e-05, + "loss": 3.5582, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979854726562423e-05, + "loss": 3.5399, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790161318113714e-05, + "loss": 3.5443, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781775370603194e-05, + "loss": 3.5488, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773389423092674e-05, + "loss": 3.5395, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765019854385884e-05, + "loss": 3.5295, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756633906875363e-05, + "loss": 3.5416, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748247959364843e-05, + "loss": 3.5482, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739862011854323e-05, + "loss": 3.5513, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731492443147536e-05, + "loss": 3.551, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723106495637016e-05, + "loss": 3.5507, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714720548126496e-05, + "loss": 3.5361, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706334600615976e-05, + "loss": 3.5399, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697965031909185e-05, + "loss": 3.5319, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689579084398668e-05, + "loss": 3.5485, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681193136888148e-05, + "loss": 3.5367, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672807189377628e-05, + "loss": 3.5446, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664421241867108e-05, + "loss": 3.5398, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656051673160317e-05, + "loss": 3.5546, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647665725649797e-05, + "loss": 3.5457, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639279778139277e-05, + "loss": 3.5408, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630893830628757e-05, + "loss": 3.5487, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962252426192197e-05, + "loss": 3.5376, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961413831441145e-05, + "loss": 3.5499, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960575236690093e-05, + "loss": 3.532, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959736641939041e-05, + "loss": 3.5378, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588996850683622e-05, + "loss": 3.548, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580610903173102e-05, + "loss": 3.5359, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572224955662582e-05, + "loss": 3.541, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563839008152062e-05, + "loss": 3.5277, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955546943944527e-05, + "loss": 3.5373, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954708349193475e-05, + "loss": 3.5193, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953869754442423e-05, + "loss": 3.5557, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.953031159691371e-05, + "loss": 3.5347, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521925649403194e-05, + "loss": 3.5534, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513556080696403e-05, + "loss": 3.5421, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505170133185883e-05, + "loss": 3.5284, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496784185675363e-05, + "loss": 3.5309, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488398238164843e-05, + "loss": 3.5385, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480028669458055e-05, + "loss": 3.5303, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471642721947535e-05, + "loss": 3.5261, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463256774437015e-05, + "loss": 3.5496, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454870826926495e-05, + "loss": 3.5431, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446501258219704e-05, + "loss": 3.5274, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438115310709184e-05, + "loss": 3.5231, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429729363198664e-05, + "loss": 3.5299, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421343415688148e-05, + "loss": 3.5391, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9412973846981357e-05, + "loss": 3.5456, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404587899470837e-05, + "loss": 3.5403, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396201951960317e-05, + "loss": 3.5436, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387816004449797e-05, + "loss": 3.5429, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937944643574301e-05, + "loss": 3.5453, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937106048823249e-05, + "loss": 3.5372, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936267454072197e-05, + "loss": 3.5385, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935428859321145e-05, + "loss": 3.5436, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345919024504658e-05, + "loss": 3.5368, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337533076994138e-05, + "loss": 3.5366, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329147129483618e-05, + "loss": 3.5449, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320761181973095e-05, + "loss": 3.5502, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931239161326631e-05, + "loss": 3.5302, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930400566575579e-05, + "loss": 3.5181, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929561971824527e-05, + "loss": 3.5377, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287233770734747e-05, + "loss": 3.5399, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278864202027963e-05, + "loss": 3.5396, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270478254517443e-05, + "loss": 3.536, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262092307006916e-05, + "loss": 3.5377, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253706359496396e-05, + "loss": 3.5342, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245320411985876e-05, + "loss": 3.5297, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236950843279092e-05, + "loss": 3.5362, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228564895768568e-05, + "loss": 3.5389, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220178948258048e-05, + "loss": 3.5481, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211793000747528e-05, + "loss": 3.5493, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203423432040744e-05, + "loss": 3.5446, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195037484530217e-05, + "loss": 3.5267, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.91866515370197e-05, + "loss": 3.5406, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917826558950918e-05, + "loss": 3.5396, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916989602080239e-05, + "loss": 3.5405, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916151007329187e-05, + "loss": 3.5341, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915312412578135e-05, + "loss": 3.5334, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914473817827083e-05, + "loss": 3.5304, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136368609564042e-05, + "loss": 3.5468, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127982662053522e-05, + "loss": 3.5215, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119596714543002e-05, + "loss": 3.5358, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111210767032482e-05, + "loss": 3.5414, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910284119832569e-05, + "loss": 3.5311, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909445525081517e-05, + "loss": 3.5291, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086069303304654e-05, + "loss": 3.5409, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077683355794134e-05, + "loss": 3.5312, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069313787087343e-05, + "loss": 3.5406, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060927839576823e-05, + "loss": 3.5391, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052541892066303e-05, + "loss": 3.5364, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044155944555783e-05, + "loss": 3.5416, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035786375848996e-05, + "loss": 3.5492, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027400428338476e-05, + "loss": 3.5365, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019014480827956e-05, + "loss": 3.5353, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010628533317436e-05, + "loss": 3.5349, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002258964610645e-05, + "loss": 3.5376, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993873017100125e-05, + "loss": 3.5312, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985487069589608e-05, + "loss": 3.5294, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977101122079088e-05, + "loss": 3.5368, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968715174568568e-05, + "loss": 3.5445, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960345605861777e-05, + "loss": 3.5388, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951959658351257e-05, + "loss": 3.5379, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943573710840737e-05, + "loss": 3.5304, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935187763330217e-05, + "loss": 3.5309, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892681819462343e-05, + "loss": 3.533, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891843224711291e-05, + "loss": 3.5466, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891004629960239e-05, + "loss": 3.5457, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890166035209187e-05, + "loss": 3.525, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893290783385078e-05, + "loss": 3.5338, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888490483587456e-05, + "loss": 3.5419, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887651888836404e-05, + "loss": 3.5332, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886813294085352e-05, + "loss": 3.5407, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885976337214673e-05, + "loss": 3.5289, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885137742463621e-05, + "loss": 3.5457, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884299147712569e-05, + "loss": 3.5462, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883460552961517e-05, + "loss": 3.5412, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826235960908383e-05, + "loss": 3.538, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817850013397863e-05, + "loss": 3.5364, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809464065887343e-05, + "loss": 3.5312, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801078118376823e-05, + "loss": 3.5316, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792708549670032e-05, + "loss": 3.5498, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784322602159515e-05, + "loss": 3.5275, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775936654648995e-05, + "loss": 3.5373, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767550707138475e-05, + "loss": 3.5363, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759181138431684e-05, + "loss": 3.5339, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8686256408691406, + "eval_runtime": 317.6604, + "eval_samples_per_second": 1201.255, + "eval_steps_per_second": 37.54, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750795190921164e-05, + "loss": 3.5265, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742409243410644e-05, + "loss": 3.5316, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734023295900124e-05, + "loss": 3.5448, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725637348389604e-05, + "loss": 3.5314, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717267779682817e-05, + "loss": 3.549, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708881832172297e-05, + "loss": 3.5238, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700495884661776e-05, + "loss": 3.5434, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692109937151256e-05, + "loss": 3.5292, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683740368444466e-05, + "loss": 3.5344, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867535442093395e-05, + "loss": 3.5377, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866696847342343e-05, + "loss": 3.5344, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865858252591291e-05, + "loss": 3.5413, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650212957206118e-05, + "loss": 3.5311, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641827009695598e-05, + "loss": 3.5256, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633441062185078e-05, + "loss": 3.5274, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625055114674558e-05, + "loss": 3.5237, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861666916716404e-05, + "loss": 3.5237, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860828321965352e-05, + "loss": 3.5308, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599897272142994e-05, + "loss": 3.5305, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591511324632474e-05, + "loss": 3.5546, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858314175592569e-05, + "loss": 3.5384, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857475580841517e-05, + "loss": 3.5388, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566369860904647e-05, + "loss": 3.5344, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557983913394127e-05, + "loss": 3.5401, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549614344687342e-05, + "loss": 3.5286, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541228397176822e-05, + "loss": 3.5335, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532842449666296e-05, + "loss": 3.5345, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852445650215578e-05, + "loss": 3.5272, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516086933448995e-05, + "loss": 3.5106, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507700985938468e-05, + "loss": 3.532, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499315038427948e-05, + "loss": 3.5329, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8490929090917428e-05, + "loss": 3.5385, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482559522210644e-05, + "loss": 3.5372, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847417357470012e-05, + "loss": 3.5343, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.84657876271896e-05, + "loss": 3.5257, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845740167967908e-05, + "loss": 3.5276, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449032110972296e-05, + "loss": 3.5191, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844064616346177e-05, + "loss": 3.5332, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843226021595125e-05, + "loss": 3.5227, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423874268440733e-05, + "loss": 3.5268, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841550469973394e-05, + "loss": 3.5289, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840711875222342e-05, + "loss": 3.5397, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.83987328047129e-05, + "loss": 3.5327, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.839034685720238e-05, + "loss": 3.5298, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381977288495594e-05, + "loss": 3.5363, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373591340985074e-05, + "loss": 3.5249, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365205393474554e-05, + "loss": 3.5325, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356819445964034e-05, + "loss": 3.5231, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348449877257243e-05, + "loss": 3.5221, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340063929746723e-05, + "loss": 3.5345, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331677982236203e-05, + "loss": 3.526, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323292034725686e-05, + "loss": 3.5234, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314922466018895e-05, + "loss": 3.5153, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306536518508375e-05, + "loss": 3.5231, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298150570997855e-05, + "loss": 3.5105, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289764623487335e-05, + "loss": 3.54, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281395054780548e-05, + "loss": 3.5228, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273009107270028e-05, + "loss": 3.5335, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264623159759508e-05, + "loss": 3.5306, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256237212248988e-05, + "loss": 3.5178, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247867643542197e-05, + "loss": 3.5164, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239481696031677e-05, + "loss": 3.5255, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231095748521157e-05, + "loss": 3.5171, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822270980101064e-05, + "loss": 3.5138, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821432385350012e-05, + "loss": 3.5331, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820595428479333e-05, + "loss": 3.5335, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819756833728281e-05, + "loss": 3.513, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818918238977229e-05, + "loss": 3.5123, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.818079644226177e-05, + "loss": 3.5168, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817242687355498e-05, + "loss": 3.5266, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.816404092604446e-05, + "loss": 3.5275, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815565497853394e-05, + "loss": 3.5273, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814726903102342e-05, + "loss": 3.532, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813889946231663e-05, + "loss": 3.5297, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813051351480611e-05, + "loss": 3.5339, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122127567295594e-05, + "loss": 3.5175, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113741619785074e-05, + "loss": 3.5263, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105372051078283e-05, + "loss": 3.5304, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096986103567763e-05, + "loss": 3.5188, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088600156057243e-05, + "loss": 3.5302, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080214208546722e-05, + "loss": 3.5313, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071844639839935e-05, + "loss": 3.535, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063458692329415e-05, + "loss": 3.5135, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055072744818895e-05, + "loss": 3.5085, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046686797308375e-05, + "loss": 3.5232, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038317228601584e-05, + "loss": 3.5254, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8029931281091064e-05, + "loss": 3.5294, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021545333580547e-05, + "loss": 3.5222, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013159386070027e-05, + "loss": 3.5231, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004789817363236e-05, + "loss": 3.5251, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996403869852716e-05, + "loss": 3.5159, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988017922342196e-05, + "loss": 3.5212, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979631974831676e-05, + "loss": 3.5246, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797126240612489e-05, + "loss": 3.5338, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796287645861437e-05, + "loss": 3.5347, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795449051110385e-05, + "loss": 3.532, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.794610456359333e-05, + "loss": 3.5164, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793771861608281e-05, + "loss": 3.5279, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929349047376018e-05, + "loss": 3.5226, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920963099865497e-05, + "loss": 3.5333, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791257715235498e-05, + "loss": 3.5186, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790419120484446e-05, + "loss": 3.5188, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789582163613767e-05, + "loss": 3.5159, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788743568862715e-05, + "loss": 3.5336, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787904974111663e-05, + "loss": 3.5065, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.787066379360611e-05, + "loss": 3.5242, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862294224899322e-05, + "loss": 3.5275, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853908277388802e-05, + "loss": 3.5166, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845522329878282e-05, + "loss": 3.5168, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837136382367762e-05, + "loss": 3.5336, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782876681366097e-05, + "loss": 3.5186, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.782038086615045e-05, + "loss": 3.5223, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811994918639935e-05, + "loss": 3.5277, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803608971129414e-05, + "loss": 3.52, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795239402422624e-05, + "loss": 3.5297, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786853454912104e-05, + "loss": 3.5352, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778467507401583e-05, + "loss": 3.5238, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770081559891063e-05, + "loss": 3.5232, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761695612380543e-05, + "loss": 3.5244, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753326043673756e-05, + "loss": 3.5206, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7744940096163236e-05, + "loss": 3.5173, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736554148652716e-05, + "loss": 3.5173, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728168201142196e-05, + "loss": 3.5192, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719798632435405e-05, + "loss": 3.5362, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711412684924888e-05, + "loss": 3.5237, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703026737414368e-05, + "loss": 3.5268, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694640789903848e-05, + "loss": 3.5174, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686271221197057e-05, + "loss": 3.5163, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677885273686537e-05, + "loss": 3.5193, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669499326176017e-05, + "loss": 3.5367, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661113378665494e-05, + "loss": 3.5333, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765274380995871e-05, + "loss": 3.5122, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764435786244819e-05, + "loss": 3.519, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763597191493767e-05, + "loss": 3.5293, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627585967427143e-05, + "loss": 3.5212, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761921639872036e-05, + "loss": 3.529, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610830451209842e-05, + "loss": 3.5161, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602444503699322e-05, + "loss": 3.5315, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594058556188795e-05, + "loss": 3.5321, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758568898748201e-05, + "loss": 3.5245, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757730303997149e-05, + "loss": 3.5261, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568917092460967e-05, + "loss": 3.5273, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560531144950447e-05, + "loss": 3.5182, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552145197439927e-05, + "loss": 3.5197, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543775628733143e-05, + "loss": 3.5351, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535389681222616e-05, + "loss": 3.5162, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527003733712096e-05, + "loss": 3.5257, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751861778620158e-05, + "loss": 3.5233, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510248217494796e-05, + "loss": 3.5179, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8709800243377686, + "eval_runtime": 328.1391, + "eval_samples_per_second": 1162.894, + "eval_steps_per_second": 36.341, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.750186226998427e-05, + "loss": 3.513, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749347632247375e-05, + "loss": 3.519, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.748509037496323e-05, + "loss": 3.5321, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747670442745271e-05, + "loss": 3.5142, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746833485874592e-05, + "loss": 3.5388, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.74599489112354e-05, + "loss": 3.5126, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.745156296372488e-05, + "loss": 3.5314, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.744317701621436e-05, + "loss": 3.5113, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743480744750757e-05, + "loss": 3.5255, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742642149999705e-05, + "loss": 3.5219, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418035552486533e-05, + "loss": 3.5179, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409649604976013e-05, + "loss": 3.5305, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401280036269222e-05, + "loss": 3.517, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392894088758702e-05, + "loss": 3.5122, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384508141248182e-05, + "loss": 3.5145, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376122193737662e-05, + "loss": 3.5106, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367752625030875e-05, + "loss": 3.5141, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359366677520355e-05, + "loss": 3.5178, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7350980730009835e-05, + "loss": 3.5149, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342594782499315e-05, + "loss": 3.5399, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334225213792524e-05, + "loss": 3.5229, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325839266282004e-05, + "loss": 3.5277, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317453318771487e-05, + "loss": 3.5216, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309067371260967e-05, + "loss": 3.5281, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300697802554176e-05, + "loss": 3.5154, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292311855043656e-05, + "loss": 3.5182, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283925907533136e-05, + "loss": 3.5217, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275539960022616e-05, + "loss": 3.513, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726717039131583e-05, + "loss": 3.5002, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725878444380531e-05, + "loss": 3.5155, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250398496294788e-05, + "loss": 3.5258, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242012548784268e-05, + "loss": 3.5209, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233642980077477e-05, + "loss": 3.5266, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225257032566957e-05, + "loss": 3.5241, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.721687108505644e-05, + "loss": 3.5131, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720848513754592e-05, + "loss": 3.5129, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.720011556883913e-05, + "loss": 3.5113, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.719172962132861e-05, + "loss": 3.5152, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718334367381809e-05, + "loss": 3.5103, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717495772630757e-05, + "loss": 3.5132, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166588157600782e-05, + "loss": 3.5162, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158202210090262e-05, + "loss": 3.5277, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149816262579742e-05, + "loss": 3.5165, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141430315069222e-05, + "loss": 3.5162, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713306074636243e-05, + "loss": 3.5262, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712467479885191e-05, + "loss": 3.51, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116288851341394e-05, + "loss": 3.5189, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107902903830874e-05, + "loss": 3.5116, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099533335124083e-05, + "loss": 3.5036, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091147387613563e-05, + "loss": 3.5216, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082761440103043e-05, + "loss": 3.5162, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074375492592523e-05, + "loss": 3.5109, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066005923885736e-05, + "loss": 3.5069, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057619976375216e-05, + "loss": 3.5112, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049234028864696e-05, + "loss": 3.4957, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040848081354176e-05, + "loss": 3.5231, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032478512647385e-05, + "loss": 3.5138, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024092565136865e-05, + "loss": 3.5199, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015706617626345e-05, + "loss": 3.5208, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007320670115828e-05, + "loss": 3.5054, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6998951101409037e-05, + "loss": 3.5013, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990565153898517e-05, + "loss": 3.5173, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982179206387997e-05, + "loss": 3.504, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973793258877477e-05, + "loss": 3.5023, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696542369017069e-05, + "loss": 3.5212, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695703774266017e-05, + "loss": 3.5219, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694865179514965e-05, + "loss": 3.5009, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694026584763913e-05, + "loss": 3.4984, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693187990012861e-05, + "loss": 3.5027, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923510331421818e-05, + "loss": 3.5107, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915124383911298e-05, + "loss": 3.5165, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690673843640078e-05, + "loss": 3.5139, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689835248889026e-05, + "loss": 3.5216, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.688998292018347e-05, + "loss": 3.513, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688159697267295e-05, + "loss": 3.5239, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687321102516243e-05, + "loss": 3.5059, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686482507765191e-05, + "loss": 3.5151, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856455508945123e-05, + "loss": 3.5163, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848069561434603e-05, + "loss": 3.5054, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839683613924083e-05, + "loss": 3.5154, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831297666413563e-05, + "loss": 3.5223, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822928097706772e-05, + "loss": 3.5212, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814542150196252e-05, + "loss": 3.5033, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806156202685735e-05, + "loss": 3.4963, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797770255175215e-05, + "loss": 3.5102, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789400686468424e-05, + "loss": 3.5078, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781014738957904e-05, + "loss": 3.52, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772628791447384e-05, + "loss": 3.5107, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764242843936864e-05, + "loss": 3.5119, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755873275230077e-05, + "loss": 3.5102, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747487327719557e-05, + "loss": 3.5015, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739101380209037e-05, + "loss": 3.5103, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730715432698517e-05, + "loss": 3.5074, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722345863991726e-05, + "loss": 3.5248, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713959916481206e-05, + "loss": 3.5256, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670557396897069e-05, + "loss": 3.5159, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669718802146017e-05, + "loss": 3.5011, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688818452753378e-05, + "loss": 3.5181, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680432505242858e-05, + "loss": 3.5117, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672046557732338e-05, + "loss": 3.5186, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663660610221814e-05, + "loss": 3.5052, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665529104151503e-05, + "loss": 3.509, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664690509400451e-05, + "loss": 3.5027, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663851914649399e-05, + "loss": 3.5185, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630133198983463e-05, + "loss": 3.4945, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662176363027668e-05, + "loss": 3.5136, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661337768276616e-05, + "loss": 3.5067, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6604991735255643e-05, + "loss": 3.511, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596605787745116e-05, + "loss": 3.5005, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588219840234596e-05, + "loss": 3.5202, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657985027152781e-05, + "loss": 3.5117, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571464324017288e-05, + "loss": 3.5064, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563078376506768e-05, + "loss": 3.5165, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554692428996248e-05, + "loss": 3.5031, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546322860289464e-05, + "loss": 3.5226, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537936912778937e-05, + "loss": 3.5275, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529550965268417e-05, + "loss": 3.5087, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521165017757897e-05, + "loss": 3.5081, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512795449051113e-05, + "loss": 3.5112, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.650440950154059e-05, + "loss": 3.5076, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.649602355403007e-05, + "loss": 3.504, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487653985323285e-05, + "loss": 3.5052, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647926803781276e-05, + "loss": 3.5059, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470882090302242e-05, + "loss": 3.5224, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462496142791722e-05, + "loss": 3.5123, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454110195281202e-05, + "loss": 3.5124, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644574062657441e-05, + "loss": 3.5041, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643735467906389e-05, + "loss": 3.504, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642896873155337e-05, + "loss": 3.5035, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642058278404285e-05, + "loss": 3.5252, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412213215336063e-05, + "loss": 3.5202, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403827267825543e-05, + "loss": 3.5041, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395441320315023e-05, + "loss": 3.502, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387055372804503e-05, + "loss": 3.5157, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378685804097712e-05, + "loss": 3.5053, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370299856587196e-05, + "loss": 3.5204, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361913909076675e-05, + "loss": 3.5033, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353527961566155e-05, + "loss": 3.5226, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345158392859365e-05, + "loss": 3.5141, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336772445348844e-05, + "loss": 3.515, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328386497838324e-05, + "loss": 3.5147, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320000550327804e-05, + "loss": 3.5122, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311630981621017e-05, + "loss": 3.5059, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303245034110497e-05, + "loss": 3.5114, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294859086599977e-05, + "loss": 3.5213, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286473139089457e-05, + "loss": 3.5087, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278103570382666e-05, + "loss": 3.5078, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626971762287215e-05, + "loss": 3.5071, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626133167536163e-05, + "loss": 3.506, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.870781421661377, + "eval_runtime": 306.4238, + "eval_samples_per_second": 1245.305, + "eval_steps_per_second": 38.917, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625294572785111e-05, + "loss": 3.5038, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244576159144318e-05, + "loss": 3.5031, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236190211633798e-05, + "loss": 3.5208, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227804264123278e-05, + "loss": 3.5024, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219418316612758e-05, + "loss": 3.5294, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621104874790597e-05, + "loss": 3.4979, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620266280039545e-05, + "loss": 3.5185, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619427685288493e-05, + "loss": 3.5008, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618589090537441e-05, + "loss": 3.5092, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617752133666762e-05, + "loss": 3.5092, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169135389157103e-05, + "loss": 3.5049, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160749441646583e-05, + "loss": 3.5188, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152363494136063e-05, + "loss": 3.5048, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143993925429272e-05, + "loss": 3.499, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135607977918752e-05, + "loss": 3.5041, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127222030408232e-05, + "loss": 3.4947, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118836082897712e-05, + "loss": 3.5025, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110466514190924e-05, + "loss": 3.5067, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102080566680404e-05, + "loss": 3.5015, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093694619169884e-05, + "loss": 3.5266, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085308671659364e-05, + "loss": 3.5132, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076939102952573e-05, + "loss": 3.5173, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068553155442053e-05, + "loss": 3.5072, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060167207931536e-05, + "loss": 3.5139, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051781260421016e-05, + "loss": 3.505, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043411691714226e-05, + "loss": 3.508, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035025744203705e-05, + "loss": 3.5114, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026639796693185e-05, + "loss": 3.5, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018253849182665e-05, + "loss": 3.4924, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009884280475878e-05, + "loss": 3.4984, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001498332965358e-05, + "loss": 3.5136, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993112385454838e-05, + "loss": 3.5081, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984726437944318e-05, + "loss": 3.5172, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976356869237527e-05, + "loss": 3.514, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967970921727007e-05, + "loss": 3.4931, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595958497421649e-05, + "loss": 3.5012, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595119902670597e-05, + "loss": 3.5016, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594282945799918e-05, + "loss": 3.498, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593444351048866e-05, + "loss": 3.5012, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592605756297814e-05, + "loss": 3.498, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591767161546762e-05, + "loss": 3.5063, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590930204676083e-05, + "loss": 3.5124, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590091609925031e-05, + "loss": 3.5082, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589253015173979e-05, + "loss": 3.5005, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588414420422927e-05, + "loss": 3.5145, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587575825671875e-05, + "loss": 3.4991, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586738868801196e-05, + "loss": 3.5062, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859002740501444e-05, + "loss": 3.5034, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850616792990924e-05, + "loss": 3.4891, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842247224284133e-05, + "loss": 3.5109, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833861276773613e-05, + "loss": 3.5027, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825475329263093e-05, + "loss": 3.503, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817089381752573e-05, + "loss": 3.4933, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808703434242053e-05, + "loss": 3.4956, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800333865535265e-05, + "loss": 3.4837, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791947918024745e-05, + "loss": 3.5073, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783561970514225e-05, + "loss": 3.5033, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775176023003705e-05, + "loss": 3.5054, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766806454296914e-05, + "loss": 3.5074, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758420506786397e-05, + "loss": 3.4942, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750034559275877e-05, + "loss": 3.4878, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741648611765357e-05, + "loss": 3.5074, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733279043058566e-05, + "loss": 3.4914, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724893095548046e-05, + "loss": 3.49, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716507148037526e-05, + "loss": 3.5055, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708121200527006e-05, + "loss": 3.5059, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569975163182022e-05, + "loss": 3.4901, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.56913656843097e-05, + "loss": 3.4909, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568297973679918e-05, + "loss": 3.4861, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567459378928866e-05, + "loss": 3.4943, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666224220581868e-05, + "loss": 3.5053, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565783827307135e-05, + "loss": 3.5047, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564945232556083e-05, + "loss": 3.509, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.564106637805031e-05, + "loss": 3.5007, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563269680934352e-05, + "loss": 3.5151, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624310861833e-05, + "loss": 3.4917, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561592491432248e-05, + "loss": 3.506, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560753896681196e-05, + "loss": 3.5003, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599169398105172e-05, + "loss": 3.489, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590783450594652e-05, + "loss": 3.5082, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582397503084132e-05, + "loss": 3.5073, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574011555573612e-05, + "loss": 3.5068, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556564198686682e-05, + "loss": 3.4949, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557256039356305e-05, + "loss": 3.4856, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548870091845785e-05, + "loss": 3.4977, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540484144335258e-05, + "loss": 3.4976, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532114575628474e-05, + "loss": 3.5064, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523728628117954e-05, + "loss": 3.4943, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515342680607434e-05, + "loss": 3.5028, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550695673309691e-05, + "loss": 3.4951, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498587164390126e-05, + "loss": 3.4957, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490201216879606e-05, + "loss": 3.4949, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481815269369086e-05, + "loss": 3.4929, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.547342932185856e-05, + "loss": 3.5137, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465059753151775e-05, + "loss": 3.5102, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545667380564126e-05, + "loss": 3.5083, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.544828785813073e-05, + "loss": 3.4871, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543990191062021e-05, + "loss": 3.5069, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431532341913427e-05, + "loss": 3.5003, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423146394402907e-05, + "loss": 3.5043, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414760446892384e-05, + "loss": 3.4932, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406374499381864e-05, + "loss": 3.4963, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539800493067508e-05, + "loss": 3.4896, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389618983164553e-05, + "loss": 3.5106, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381233035654033e-05, + "loss": 3.485, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5372847088143513e-05, + "loss": 3.4997, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536447751943673e-05, + "loss": 3.495, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356091571926205e-05, + "loss": 3.4983, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347705624415685e-05, + "loss": 3.4893, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339319676905165e-05, + "loss": 3.5099, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533095010819838e-05, + "loss": 3.4972, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322564160687858e-05, + "loss": 3.4952, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314178213177338e-05, + "loss": 3.5071, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305792265666818e-05, + "loss": 3.4947, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297422696960027e-05, + "loss": 3.5069, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5289036749449507e-05, + "loss": 3.5123, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280650801938987e-05, + "loss": 3.4988, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272264854428467e-05, + "loss": 3.4975, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526389528572168e-05, + "loss": 3.4947, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525550933821116e-05, + "loss": 3.4939, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524712339070064e-05, + "loss": 3.4943, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523873744319012e-05, + "loss": 3.499, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230367874483328e-05, + "loss": 3.4893, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522198192697281e-05, + "loss": 3.5106, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521359597946229e-05, + "loss": 3.5024, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.520521003195177e-05, + "loss": 3.5026, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519684046324498e-05, + "loss": 3.491, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518845451573446e-05, + "loss": 3.4949, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.518006856822394e-05, + "loss": 3.4943, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.517168262071342e-05, + "loss": 3.5079, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163313052006633e-05, + "loss": 3.51, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154927104496113e-05, + "loss": 3.4968, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146541156985593e-05, + "loss": 3.4846, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138155209475073e-05, + "loss": 3.5032, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512978564076828e-05, + "loss": 3.4951, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512139969325776e-05, + "loss": 3.5081, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113013745747245e-05, + "loss": 3.4897, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104627798236725e-05, + "loss": 3.5072, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096258229529934e-05, + "loss": 3.5056, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087872282019414e-05, + "loss": 3.5069, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079486334508894e-05, + "loss": 3.5016, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071100386998374e-05, + "loss": 3.4974, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062730818291586e-05, + "loss": 3.4944, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054344870781066e-05, + "loss": 3.498, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5045958923270546e-05, + "loss": 3.5035, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037572975760026e-05, + "loss": 3.5018, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029203407053235e-05, + "loss": 3.4963, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020817459542715e-05, + "loss": 3.4991, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.50124315120322e-05, + "loss": 3.4907, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.872690200805664, + "eval_runtime": 303.0605, + "eval_samples_per_second": 1259.125, + "eval_steps_per_second": 39.349, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500404556452168e-05, + "loss": 3.484, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499565961701116e-05, + "loss": 3.4941, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498727366950064e-05, + "loss": 3.5043, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497888772199012e-05, + "loss": 3.4938, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970518153283328e-05, + "loss": 3.5123, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962132205772808e-05, + "loss": 3.4931, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495374625826229e-05, + "loss": 3.501, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494536031075177e-05, + "loss": 3.4913, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493699074204498e-05, + "loss": 3.4967, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492860479453446e-05, + "loss": 3.4967, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492021884702394e-05, + "loss": 3.4954, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491183289951342e-05, + "loss": 3.5046, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903463330806632e-05, + "loss": 3.4944, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895077383296112e-05, + "loss": 3.4881, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886691435785592e-05, + "loss": 3.4925, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878305488275072e-05, + "loss": 3.4833, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486991954076455e-05, + "loss": 3.4896, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486153359325403e-05, + "loss": 3.4934, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485314764574351e-05, + "loss": 3.4888, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844761698232992e-05, + "loss": 3.514, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.48363921295262e-05, + "loss": 3.4998, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482800618201568e-05, + "loss": 3.5067, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481962023450516e-05, + "loss": 3.4983, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481123428699464e-05, + "loss": 3.502, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802864718287853e-05, + "loss": 3.4891, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794478770777333e-05, + "loss": 3.4996, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786092823266813e-05, + "loss": 3.4969, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777706875756293e-05, + "loss": 3.4873, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769337307049502e-05, + "loss": 3.4842, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4760951359538982e-05, + "loss": 3.4877, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752565412028462e-05, + "loss": 3.4959, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744179464517946e-05, + "loss": 3.498, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735809895811155e-05, + "loss": 3.5009, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727423948300635e-05, + "loss": 3.5012, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719038000790115e-05, + "loss": 3.4822, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710652053279595e-05, + "loss": 3.4915, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702282484572807e-05, + "loss": 3.4906, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693896537062287e-05, + "loss": 3.4849, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685510589551767e-05, + "loss": 3.4924, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677124642041247e-05, + "loss": 3.4845, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668755073334456e-05, + "loss": 3.4981, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660369125823936e-05, + "loss": 3.5, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651983178313416e-05, + "loss": 3.4969, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.46435972308029e-05, + "loss": 3.4866, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463522766209611e-05, + "loss": 3.5009, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462684171458559e-05, + "loss": 3.487, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461845576707507e-05, + "loss": 3.4965, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610069819564548e-05, + "loss": 3.4899, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.460170025085776e-05, + "loss": 3.4762, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459331430334724e-05, + "loss": 3.5007, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458492835583672e-05, + "loss": 3.4901, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576542408326197e-05, + "loss": 3.4893, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456817283961941e-05, + "loss": 3.483, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.455978689210889e-05, + "loss": 3.4805, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.455140094459837e-05, + "loss": 3.4755, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.454301499708785e-05, + "loss": 3.4907, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.453462904957733e-05, + "loss": 3.4938, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526259480870542e-05, + "loss": 3.491, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517873533360022e-05, + "loss": 3.4947, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.45094875858495e-05, + "loss": 3.485, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501101638338982e-05, + "loss": 3.4744, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492732069632194e-05, + "loss": 3.4981, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448434612212167e-05, + "loss": 3.477, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447596017461115e-05, + "loss": 3.4745, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446757422710063e-05, + "loss": 3.4995, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459204658393843e-05, + "loss": 3.491, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450818710883323e-05, + "loss": 3.4783, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442432763372803e-05, + "loss": 3.48, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434046815862283e-05, + "loss": 3.4719, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425677247155496e-05, + "loss": 3.4803, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417291299644972e-05, + "loss": 3.4974, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4408905352134452e-05, + "loss": 3.4892, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400519404623932e-05, + "loss": 3.4947, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392149835917145e-05, + "loss": 3.487, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383763888406625e-05, + "loss": 3.5067, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375377940896105e-05, + "loss": 3.48, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366991993385585e-05, + "loss": 3.4942, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358622424678794e-05, + "loss": 3.4891, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350236477168277e-05, + "loss": 3.4729, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341850529657757e-05, + "loss": 3.5016, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333464582147237e-05, + "loss": 3.4945, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325095013440446e-05, + "loss": 3.4942, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316709065929926e-05, + "loss": 3.4858, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308323118419406e-05, + "loss": 3.4722, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299937170908886e-05, + "loss": 3.4855, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.42915676022021e-05, + "loss": 3.4841, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283181654691578e-05, + "loss": 3.4951, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274795707181058e-05, + "loss": 3.4825, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266409759670538e-05, + "loss": 3.4884, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258040190963747e-05, + "loss": 3.4841, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.424965424345323e-05, + "loss": 3.4865, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.424126829594271e-05, + "loss": 3.4802, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423288234843219e-05, + "loss": 3.4823, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.42245127797254e-05, + "loss": 3.4998, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421612683221488e-05, + "loss": 3.4999, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420774088470436e-05, + "loss": 3.5004, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419935493719384e-05, + "loss": 3.4727, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190968989683323e-05, + "loss": 3.4936, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182599420976532e-05, + "loss": 3.4879, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174213473466012e-05, + "loss": 3.4915, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165827525955492e-05, + "loss": 3.4864, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.41574579572487e-05, + "loss": 3.4827, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149072009738184e-05, + "loss": 3.4818, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140686062227664e-05, + "loss": 3.4952, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132300114717144e-05, + "loss": 3.4723, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412391416720662e-05, + "loss": 3.4854, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115544598499833e-05, + "loss": 3.4814, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107158650989313e-05, + "loss": 3.4901, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098772703478793e-05, + "loss": 3.4802, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090386755968273e-05, + "loss": 3.4953, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082017187261486e-05, + "loss": 3.4878, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073631239750966e-05, + "loss": 3.4831, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065245292240446e-05, + "loss": 3.4938, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056859344729922e-05, + "loss": 3.4855, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048489776023138e-05, + "loss": 3.4944, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040103828512618e-05, + "loss": 3.4989, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031717881002094e-05, + "loss": 3.4841, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023331933491574e-05, + "loss": 3.4825, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014962364784787e-05, + "loss": 3.4867, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006576417274267e-05, + "loss": 3.4818, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998190469763747e-05, + "loss": 3.4834, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989804522253227e-05, + "loss": 3.4859, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398143495354644e-05, + "loss": 3.4783, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397304900603592e-05, + "loss": 3.4979, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964663058525396e-05, + "loss": 3.4891, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956277111014876e-05, + "loss": 3.4918, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394790754230809e-05, + "loss": 3.4793, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939521594797568e-05, + "loss": 3.4829, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931135647287048e-05, + "loss": 3.4828, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922749699776528e-05, + "loss": 3.4915, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391438013106974e-05, + "loss": 3.4964, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905994183559217e-05, + "loss": 3.4876, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.38976082360487e-05, + "loss": 3.4719, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388922228853818e-05, + "loss": 3.4944, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880852719831393e-05, + "loss": 3.4817, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387246677232087e-05, + "loss": 3.4951, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386408082481035e-05, + "loss": 3.4772, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385569487729983e-05, + "loss": 3.4953, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847325308593042e-05, + "loss": 3.4934, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838939361082522e-05, + "loss": 3.4961, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830553413572002e-05, + "loss": 3.4891, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822167466061482e-05, + "loss": 3.4874, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381379789735469e-05, + "loss": 3.4813, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380541194984417e-05, + "loss": 3.4878, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797026002333654e-05, + "loss": 3.4911, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788640054823134e-05, + "loss": 3.4888, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780270486116343e-05, + "loss": 3.4851, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771884538605823e-05, + "loss": 3.4837, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763498591095303e-05, + "loss": 3.4841, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.873694658279419, + "eval_runtime": 302.6789, + "eval_samples_per_second": 1260.712, + "eval_steps_per_second": 39.398, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755112643584783e-05, + "loss": 3.4819, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746743074877996e-05, + "loss": 3.4803, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738357127367476e-05, + "loss": 3.4923, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729971179856955e-05, + "loss": 3.4812, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721585232346435e-05, + "loss": 3.4993, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713215663639645e-05, + "loss": 3.4823, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3704829716129124e-05, + "loss": 3.4877, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696443768618608e-05, + "loss": 3.4853, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3688057821108088e-05, + "loss": 3.4838, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679688252401297e-05, + "loss": 3.4841, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671302304890777e-05, + "loss": 3.4865, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662916357380257e-05, + "loss": 3.49, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654530409869737e-05, + "loss": 3.4843, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364616084116295e-05, + "loss": 3.4777, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363777489365243e-05, + "loss": 3.4837, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.362938894614191e-05, + "loss": 3.4699, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362100299863139e-05, + "loss": 3.4774, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612633429924598e-05, + "loss": 3.4822, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604247482414078e-05, + "loss": 3.4794, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.359586153490356e-05, + "loss": 3.5027, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.358747558739304e-05, + "loss": 3.4886, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357910601868625e-05, + "loss": 3.4946, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357072007117573e-05, + "loss": 3.4846, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.356233412366521e-05, + "loss": 3.4881, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.355394817615469e-05, + "loss": 3.4805, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545578607447903e-05, + "loss": 3.4892, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537192659937383e-05, + "loss": 3.4833, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528806712426863e-05, + "loss": 3.4789, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520420764916343e-05, + "loss": 3.4723, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512051196209552e-05, + "loss": 3.4776, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503665248699032e-05, + "loss": 3.4815, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495279301188515e-05, + "loss": 3.4881, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486893353677992e-05, + "loss": 3.4882, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478523784971204e-05, + "loss": 3.491, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470137837460684e-05, + "loss": 3.473, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461751889950164e-05, + "loss": 3.4801, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345336594243964e-05, + "loss": 3.4785, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444996373732857e-05, + "loss": 3.4736, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436610426222337e-05, + "loss": 3.4828, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428224478711816e-05, + "loss": 3.4685, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419838531201293e-05, + "loss": 3.4837, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411468962494506e-05, + "loss": 3.4876, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3403083014983985e-05, + "loss": 3.4879, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394697067473465e-05, + "loss": 3.4782, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386311119962945e-05, + "loss": 3.4924, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377941551256158e-05, + "loss": 3.4708, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369555603745638e-05, + "loss": 3.4867, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361169656235114e-05, + "loss": 3.4786, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352783708724594e-05, + "loss": 3.4587, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334441414001781e-05, + "loss": 3.4937, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333602819250729e-05, + "loss": 3.4777, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327642244996767e-05, + "loss": 3.4821, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319256297486247e-05, + "loss": 3.47, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.331088672877946e-05, + "loss": 3.4697, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330250078126894e-05, + "loss": 3.4687, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329411483375842e-05, + "loss": 3.4745, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.32857288862479e-05, + "loss": 3.4824, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327735931754111e-05, + "loss": 3.4777, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268973370030588e-05, + "loss": 3.4867, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260587422520068e-05, + "loss": 3.4703, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252201475009548e-05, + "loss": 3.4631, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243831906302764e-05, + "loss": 3.4849, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.323544595879224e-05, + "loss": 3.4638, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322706001128172e-05, + "loss": 3.4651, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.32186740637712e-05, + "loss": 3.4873, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.321030449506441e-05, + "loss": 3.48, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201918547553893e-05, + "loss": 3.4666, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193532600043373e-05, + "loss": 3.4702, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185146652532853e-05, + "loss": 3.4629, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176777083826062e-05, + "loss": 3.4687, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168391136315542e-05, + "loss": 3.4852, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3160005188805022e-05, + "loss": 3.4781, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151619241294502e-05, + "loss": 3.4809, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143249672587714e-05, + "loss": 3.4775, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134863725077194e-05, + "loss": 3.4931, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126477777566674e-05, + "loss": 3.4692, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118091830056154e-05, + "loss": 3.4827, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109722261349363e-05, + "loss": 3.4763, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101336313838846e-05, + "loss": 3.462, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3092950366328326e-05, + "loss": 3.4892, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084564418817806e-05, + "loss": 3.4822, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076194850111016e-05, + "loss": 3.4829, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067808902600495e-05, + "loss": 3.4772, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059422955089975e-05, + "loss": 3.4643, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3051037007579455e-05, + "loss": 3.4669, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042667438872668e-05, + "loss": 3.4746, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034281491362148e-05, + "loss": 3.4848, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025895543851628e-05, + "loss": 3.4689, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017509596341108e-05, + "loss": 3.477, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009140027634317e-05, + "loss": 3.4718, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.30007540801238e-05, + "loss": 3.4773, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299236813261328e-05, + "loss": 3.4672, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298398218510276e-05, + "loss": 3.4734, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297559623759224e-05, + "loss": 3.4861, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296722666888545e-05, + "loss": 3.4885, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.295884072137493e-05, + "loss": 3.4888, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.295045477386441e-05, + "loss": 3.4605, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942068826353892e-05, + "loss": 3.4838, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.29336992576471e-05, + "loss": 3.4743, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292531331013658e-05, + "loss": 3.4839, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291692736262606e-05, + "loss": 3.47, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908541415115538e-05, + "loss": 3.4759, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900171846408754e-05, + "loss": 3.4665, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891785898898234e-05, + "loss": 3.484, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883399951387714e-05, + "loss": 3.4624, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.287501400387719e-05, + "loss": 3.4805, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866644435170403e-05, + "loss": 3.4664, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858258487659883e-05, + "loss": 3.4811, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849872540149363e-05, + "loss": 3.472, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841486592638843e-05, + "loss": 3.4768, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833117023932055e-05, + "loss": 3.4755, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824731076421535e-05, + "loss": 3.4774, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281634512891101e-05, + "loss": 3.48, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280795918140049e-05, + "loss": 3.4741, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799589612693707e-05, + "loss": 3.4801, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2791203665183187e-05, + "loss": 3.4929, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782817717672664e-05, + "loss": 3.4731, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774431770162144e-05, + "loss": 3.4707, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766062201455356e-05, + "loss": 3.4776, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757676253944833e-05, + "loss": 3.4723, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2749290306434316e-05, + "loss": 3.4657, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740904358923796e-05, + "loss": 3.4774, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.273253479021701e-05, + "loss": 3.466, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724148842706485e-05, + "loss": 3.485, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715762895195965e-05, + "loss": 3.4802, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707376947685445e-05, + "loss": 3.4777, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.269900737897866e-05, + "loss": 3.4699, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690621431468138e-05, + "loss": 3.4693, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682235483957618e-05, + "loss": 3.4738, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673849536447098e-05, + "loss": 3.4835, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665479967740307e-05, + "loss": 3.4799, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657094020229787e-05, + "loss": 3.4831, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264870807271927e-05, + "loss": 3.4579, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.264032212520875e-05, + "loss": 3.482, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.263195255650196e-05, + "loss": 3.4708, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262356660899144e-05, + "loss": 3.4823, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.261518066148092e-05, + "loss": 3.467, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.26067947139704e-05, + "loss": 3.4881, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.259842514526361e-05, + "loss": 3.479, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.259003919775309e-05, + "loss": 3.4864, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.258165325024257e-05, + "loss": 3.4741, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257326730273205e-05, + "loss": 3.4815, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256489773402526e-05, + "loss": 3.4648, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255651178651474e-05, + "loss": 3.4787, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548125839004224e-05, + "loss": 3.4808, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539756270297433e-05, + "loss": 3.4739, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531370322786913e-05, + "loss": 3.4789, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522984375276393e-05, + "loss": 3.4686, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514598427765873e-05, + "loss": 3.4737, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.874763250350952, + "eval_runtime": 302.091, + "eval_samples_per_second": 1263.166, + "eval_steps_per_second": 39.475, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506212480255353e-05, + "loss": 3.4713, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497826532744833e-05, + "loss": 3.4685, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489440585234316e-05, + "loss": 3.4799, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481054637723792e-05, + "loss": 3.4706, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472685069017005e-05, + "loss": 3.4871, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464299121506485e-05, + "loss": 3.4701, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245591317399596e-05, + "loss": 3.4773, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244752722648544e-05, + "loss": 3.4764, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2439157657778657e-05, + "loss": 3.4728, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430771710268137e-05, + "loss": 3.4727, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422385762757614e-05, + "loss": 3.4751, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413999815247094e-05, + "loss": 3.4785, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405630246540306e-05, + "loss": 3.4724, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397244299029786e-05, + "loss": 3.4662, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388858351519266e-05, + "loss": 3.471, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380472404008746e-05, + "loss": 3.4577, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237210283530196e-05, + "loss": 3.4647, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363716887791435e-05, + "loss": 3.4695, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355330940280915e-05, + "loss": 3.4667, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346944992770395e-05, + "loss": 3.491, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233857542406361e-05, + "loss": 3.4803, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330189476553088e-05, + "loss": 3.4839, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321803529042568e-05, + "loss": 3.471, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.231343396033578e-05, + "loss": 3.4764, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.230504801282526e-05, + "loss": 3.4718, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.229666206531474e-05, + "loss": 3.4749, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.228827611780422e-05, + "loss": 3.4709, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279906549097432e-05, + "loss": 3.472, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.227152060158691e-05, + "loss": 3.4572, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226313465407639e-05, + "loss": 3.4666, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.225474870656587e-05, + "loss": 3.4663, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.224637913785908e-05, + "loss": 3.479, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.223799319034856e-05, + "loss": 3.4775, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222960724283804e-05, + "loss": 3.4805, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.222122129532752e-05, + "loss": 3.4621, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212851726620734e-05, + "loss": 3.4634, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220446577911021e-05, + "loss": 3.4719, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196079831599694e-05, + "loss": 3.4622, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187693884089174e-05, + "loss": 3.4691, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179324315382383e-05, + "loss": 3.4618, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170938367871863e-05, + "loss": 3.4706, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162552420361343e-05, + "loss": 3.4768, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154166472850823e-05, + "loss": 3.4741, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145796904144035e-05, + "loss": 3.4688, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137410956633515e-05, + "loss": 3.4771, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129025009122995e-05, + "loss": 3.4678, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120639061612475e-05, + "loss": 3.4739, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112269492905684e-05, + "loss": 3.4672, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103883545395164e-05, + "loss": 3.4464, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095497597884647e-05, + "loss": 3.4888, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087111650374127e-05, + "loss": 3.462, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078742081667336e-05, + "loss": 3.4731, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070356134156816e-05, + "loss": 3.455, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061970186646296e-05, + "loss": 3.4619, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053584239135776e-05, + "loss": 3.4506, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204521467042899e-05, + "loss": 3.4642, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203682872291847e-05, + "loss": 3.472, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.202844277540795e-05, + "loss": 3.4684, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.202005682789743e-05, + "loss": 3.4735, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011687259190638e-05, + "loss": 3.4617, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003301311680118e-05, + "loss": 3.4535, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.19949153641696e-05, + "loss": 3.478, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198652941665908e-05, + "loss": 3.4528, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197815984795229e-05, + "loss": 3.4505, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196977390044177e-05, + "loss": 3.4757, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.196138795293125e-05, + "loss": 3.4693, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.195300200542073e-05, + "loss": 3.4547, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944632436713942e-05, + "loss": 3.4595, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936246489203422e-05, + "loss": 3.4522, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927860541692902e-05, + "loss": 3.4569, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919474594182382e-05, + "loss": 3.4696, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191110502547559e-05, + "loss": 3.4677, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190271907796507e-05, + "loss": 3.473, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894333130454555e-05, + "loss": 3.4692, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885947182944035e-05, + "loss": 3.4783, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877577614237244e-05, + "loss": 3.456, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869191666726724e-05, + "loss": 3.4751, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860805719216204e-05, + "loss": 3.4616, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852419771705684e-05, + "loss": 3.4576, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844050202998896e-05, + "loss": 3.4728, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835664255488376e-05, + "loss": 3.4731, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827278307977856e-05, + "loss": 3.4712, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818892360467332e-05, + "loss": 3.4663, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810522791760545e-05, + "loss": 3.4545, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802136844250025e-05, + "loss": 3.4534, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793750896739505e-05, + "loss": 3.4649, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785364949228985e-05, + "loss": 3.4737, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776995380522197e-05, + "loss": 3.4586, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768609433011677e-05, + "loss": 3.4674, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760223485501157e-05, + "loss": 3.4543, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1751837537990634e-05, + "loss": 3.469, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174346796928385e-05, + "loss": 3.4579, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173508202177333e-05, + "loss": 3.4641, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726696074262806e-05, + "loss": 3.4752, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718310126752286e-05, + "loss": 3.478, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.17099405580455e-05, + "loss": 3.4773, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.170155461053498e-05, + "loss": 3.45, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.169316866302446e-05, + "loss": 3.4719, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.168478271551394e-05, + "loss": 3.4595, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.167641314680715e-05, + "loss": 3.4731, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166802719929663e-05, + "loss": 3.4594, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659641251786107e-05, + "loss": 3.4671, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651255304275587e-05, + "loss": 3.4563, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642885735568803e-05, + "loss": 3.4673, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.163449978805828e-05, + "loss": 3.4534, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162611384054776e-05, + "loss": 3.4684, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161772789303724e-05, + "loss": 3.4532, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609358324330452e-05, + "loss": 3.4709, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600972376819932e-05, + "loss": 3.4605, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592586429309412e-05, + "loss": 3.464, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584200481798892e-05, + "loss": 3.4613, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575830913092105e-05, + "loss": 3.466, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156744496558158e-05, + "loss": 3.4674, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155905901807106e-05, + "loss": 3.4627, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155067307056054e-05, + "loss": 3.4713, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542303501853754e-05, + "loss": 3.4768, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533917554343234e-05, + "loss": 3.4687, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525531606832714e-05, + "loss": 3.4632, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517162038125926e-05, + "loss": 3.462, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508776090615403e-05, + "loss": 3.4645, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1500390143104886e-05, + "loss": 3.4566, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1492004195594366e-05, + "loss": 3.4656, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483634626887575e-05, + "loss": 3.4529, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475248679377055e-05, + "loss": 3.4753, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466862731866535e-05, + "loss": 3.4675, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458476784356015e-05, + "loss": 3.4677, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450107215649227e-05, + "loss": 3.4608, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441721268138707e-05, + "loss": 3.4581, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433335320628187e-05, + "loss": 3.4622, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424949373117667e-05, + "loss": 3.4748, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416579804410876e-05, + "loss": 3.4678, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408193856900356e-05, + "loss": 3.4693, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.139980790938984e-05, + "loss": 3.4483, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139142196187932e-05, + "loss": 3.4725, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138305239317253e-05, + "loss": 3.4595, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137466644566201e-05, + "loss": 3.4746, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136628049815149e-05, + "loss": 3.4533, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.135789455064097e-05, + "loss": 3.4728, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.134952498193418e-05, + "loss": 3.467, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.134113903442366e-05, + "loss": 3.4807, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133275308691314e-05, + "loss": 3.4617, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132436713940262e-05, + "loss": 3.4694, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.131599757069583e-05, + "loss": 3.456, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130761162318531e-05, + "loss": 3.4672, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.129922567567479e-05, + "loss": 3.468, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290839728164273e-05, + "loss": 3.462, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282470159457482e-05, + "loss": 3.47, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274084211946962e-05, + "loss": 3.4534, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265698264436442e-05, + "loss": 3.4672, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8765432834625244, + "eval_runtime": 313.6432, + "eval_samples_per_second": 1216.64, + "eval_steps_per_second": 38.021, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257312316925922e-05, + "loss": 3.4608, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248926369415402e-05, + "loss": 3.4556, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240540421904882e-05, + "loss": 3.4679, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232154474394362e-05, + "loss": 3.4608, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223784905687575e-05, + "loss": 3.4743, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215398958177054e-05, + "loss": 3.462, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120701301066653e-05, + "loss": 3.4644, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119862706315601e-05, + "loss": 3.4669, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190257494449227e-05, + "loss": 3.46, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181871546938703e-05, + "loss": 3.4624, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173485599428183e-05, + "loss": 3.4636, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165099651917663e-05, + "loss": 3.468, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156730083210876e-05, + "loss": 3.4663, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148344135700356e-05, + "loss": 3.4525, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139958188189836e-05, + "loss": 3.456, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131572240679316e-05, + "loss": 3.4482, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123202671972528e-05, + "loss": 3.4542, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114816724462005e-05, + "loss": 3.4634, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106430776951485e-05, + "loss": 3.4509, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098044829440965e-05, + "loss": 3.4789, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089675260734177e-05, + "loss": 3.4703, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081289313223657e-05, + "loss": 3.4734, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072903365713137e-05, + "loss": 3.4607, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064517418202617e-05, + "loss": 3.4619, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056147849495826e-05, + "loss": 3.4681, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.104776190198531e-05, + "loss": 3.462, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103937595447479e-05, + "loss": 3.4612, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.103099000696427e-05, + "loss": 3.4668, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102262043825748e-05, + "loss": 3.4451, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101423449074696e-05, + "loss": 3.4563, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100584854323644e-05, + "loss": 3.4562, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099746259572592e-05, + "loss": 3.4622, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.098909302701913e-05, + "loss": 3.4687, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.098070707950861e-05, + "loss": 3.4687, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.097232113199809e-05, + "loss": 3.452, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.096393518448757e-05, + "loss": 3.453, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095556561578078e-05, + "loss": 3.4631, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947179668270263e-05, + "loss": 3.4518, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938793720759743e-05, + "loss": 3.4589, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930424152052952e-05, + "loss": 3.4475, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922038204542432e-05, + "loss": 3.4609, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913652257031912e-05, + "loss": 3.4607, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905266309521392e-05, + "loss": 3.4644, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896896740814605e-05, + "loss": 3.4614, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888510793304084e-05, + "loss": 3.4603, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880124845793564e-05, + "loss": 3.4585, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871738898283044e-05, + "loss": 3.4642, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863369329576253e-05, + "loss": 3.4566, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854983382065733e-05, + "loss": 3.4385, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846597434555213e-05, + "loss": 3.4755, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838211487044697e-05, + "loss": 3.4499, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829841918337906e-05, + "loss": 3.4625, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821455970827386e-05, + "loss": 3.4505, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813070023316866e-05, + "loss": 3.4483, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804684075806346e-05, + "loss": 3.4403, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796314507099558e-05, + "loss": 3.4532, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787928559589038e-05, + "loss": 3.4631, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779542612078518e-05, + "loss": 3.4558, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771156664567998e-05, + "loss": 3.4635, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762787095861207e-05, + "loss": 3.457, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754401148350687e-05, + "loss": 3.4377, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746015200840167e-05, + "loss": 3.4631, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073762925332965e-05, + "loss": 3.4442, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072925968462286e-05, + "loss": 3.4392, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.072087373711234e-05, + "loss": 3.4676, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.071248778960182e-05, + "loss": 3.4556, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.07041018420913e-05, + "loss": 3.4432, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695732273384512e-05, + "loss": 3.4499, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687346325873992e-05, + "loss": 3.4436, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0678960378363472e-05, + "loss": 3.447, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670574430852952e-05, + "loss": 3.4578, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.066220486214616e-05, + "loss": 3.4559, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065381891463564e-05, + "loss": 3.4625, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.064543296712512e-05, + "loss": 3.4567, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.06370470196146e-05, + "loss": 3.4688, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628677450907813e-05, + "loss": 3.4441, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620291503397293e-05, + "loss": 3.467, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611905555886773e-05, + "loss": 3.4488, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060351960837625e-05, + "loss": 3.4487, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595150039669466e-05, + "loss": 3.4634, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586764092158945e-05, + "loss": 3.4629, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578378144648425e-05, + "loss": 3.4615, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569992197137902e-05, + "loss": 3.4612, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561622628431114e-05, + "loss": 3.4381, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553236680920594e-05, + "loss": 3.443, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544850733410074e-05, + "loss": 3.4542, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536464785899554e-05, + "loss": 3.4632, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528095217192767e-05, + "loss": 3.4516, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519709269682247e-05, + "loss": 3.456, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511323322171723e-05, + "loss": 3.4454, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502937374661203e-05, + "loss": 3.4583, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049456780595442e-05, + "loss": 3.4487, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.04861818584439e-05, + "loss": 3.4524, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477795910933376e-05, + "loss": 3.4625, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469409963422856e-05, + "loss": 3.4639, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461040394716068e-05, + "loss": 3.4682, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452654447205548e-05, + "loss": 3.4426, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444268499695028e-05, + "loss": 3.4601, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0435882552184508e-05, + "loss": 3.452, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042751298347772e-05, + "loss": 3.4603, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419127035967197e-05, + "loss": 3.4468, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410741088456677e-05, + "loss": 3.4595, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402355140946157e-05, + "loss": 3.446, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393985572239373e-05, + "loss": 3.4555, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038559962472885e-05, + "loss": 3.447, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037721367721833e-05, + "loss": 3.4545, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036882772970781e-05, + "loss": 3.4399, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.036045816100102e-05, + "loss": 3.4605, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352072213490502e-05, + "loss": 3.4519, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343686265979982e-05, + "loss": 3.455, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033530031846946e-05, + "loss": 3.4519, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032693074976267e-05, + "loss": 3.4532, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031854480225215e-05, + "loss": 3.4558, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.031015885474163e-05, + "loss": 3.4518, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030177290723111e-05, + "loss": 3.4598, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293403338524323e-05, + "loss": 3.4664, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285017391013803e-05, + "loss": 3.4513, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276631443503283e-05, + "loss": 3.4571, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268245495992763e-05, + "loss": 3.4494, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0259875927285972e-05, + "loss": 3.4519, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0251489979775452e-05, + "loss": 3.4519, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0243104032264935e-05, + "loss": 3.4509, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234718084754415e-05, + "loss": 3.4414, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226348516047624e-05, + "loss": 3.4619, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217962568537104e-05, + "loss": 3.4558, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209576621026584e-05, + "loss": 3.4575, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201190673516064e-05, + "loss": 3.4504, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192821104809277e-05, + "loss": 3.4471, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184435157298757e-05, + "loss": 3.449, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176049209788237e-05, + "loss": 3.4599, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167663262277717e-05, + "loss": 3.4582, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159293693570926e-05, + "loss": 3.4634, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150907746060406e-05, + "loss": 3.4361, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.014252179854989e-05, + "loss": 3.4597, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013413585103937e-05, + "loss": 3.4502, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125766282332578e-05, + "loss": 3.4624, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117380334822058e-05, + "loss": 3.445, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108994387311538e-05, + "loss": 3.4589, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100608439801018e-05, + "loss": 3.4556, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.009223887109423e-05, + "loss": 3.4715, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.008385292358371e-05, + "loss": 3.4524, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007546697607319e-05, + "loss": 3.4581, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.006708102856267e-05, + "loss": 3.4483, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.005871145985588e-05, + "loss": 3.4576, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.005032551234536e-05, + "loss": 3.4534, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041939564834843e-05, + "loss": 3.452, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033553617324323e-05, + "loss": 3.4602, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025184048617532e-05, + "loss": 3.4395, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0016798101107012e-05, + "loss": 3.4616, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8779537677764893, + "eval_runtime": 314.5254, + "eval_samples_per_second": 1213.228, + "eval_steps_per_second": 37.914, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008412153596492e-05, + "loss": 3.4495, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.0000042584889704e-05, + "loss": 3.445, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991656637379184e-05, + "loss": 3.4545, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983270689868664e-05, + "loss": 3.4515, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9974884742358144e-05, + "loss": 3.465, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9966515173651353e-05, + "loss": 3.4521, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9958129226140833e-05, + "loss": 3.4541, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9949743278630313e-05, + "loss": 3.4557, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941357331119796e-05, + "loss": 3.4462, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9932987762413005e-05, + "loss": 3.4539, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924601814902485e-05, + "loss": 3.452, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916215867391965e-05, + "loss": 3.4571, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.9907829919881442e-05, + "loss": 3.4579, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9899443972370922e-05, + "loss": 3.4387, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9891074403664138e-05, + "loss": 3.4483, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9882688456153618e-05, + "loss": 3.4359, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874302508643094e-05, + "loss": 3.4452, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9865916561132574e-05, + "loss": 3.4505, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9857546992425787e-05, + "loss": 3.4434, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9849161044915267e-05, + "loss": 3.4647, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9840775097404747e-05, + "loss": 3.4616, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832389149894227e-05, + "loss": 3.4606, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.982401958118744e-05, + "loss": 3.4542, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815633633676916e-05, + "loss": 3.4532, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807247686166396e-05, + "loss": 3.4569, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9798861738655876e-05, + "loss": 3.4475, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.979049216994909e-05, + "loss": 3.4478, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9782106222438568e-05, + "loss": 3.456, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9773720274928048e-05, + "loss": 3.4394, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.976535070622126e-05, + "loss": 3.4399, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.975696475871074e-05, + "loss": 3.4522, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.974857881120022e-05, + "loss": 3.4537, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.97401928636897e-05, + "loss": 3.4507, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9731823294982913e-05, + "loss": 3.4652, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.972343734747239e-05, + "loss": 3.4428, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.971505139996187e-05, + "loss": 3.4407, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.970666545245135e-05, + "loss": 3.4491, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698295883744565e-05, + "loss": 3.4385, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9689909936234042e-05, + "loss": 3.4516, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681523988723522e-05, + "loss": 3.4404, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673138041213e-05, + "loss": 3.4459, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9664768472506214e-05, + "loss": 3.4504, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.965638252499569e-05, + "loss": 3.4526, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9647996577485174e-05, + "loss": 3.4517, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639610629974654e-05, + "loss": 3.4502, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631241061267863e-05, + "loss": 3.4489, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9622855113757343e-05, + "loss": 3.448, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614469166246823e-05, + "loss": 3.4516, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9606083218736303e-05, + "loss": 3.4265, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9597713650029515e-05, + "loss": 3.4606, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9589327702518995e-05, + "loss": 3.4396, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9580941755008475e-05, + "loss": 3.4543, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572555807497955e-05, + "loss": 3.4386, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564186238791164e-05, + "loss": 3.4355, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9555800291280644e-05, + "loss": 3.4316, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9547414343770128e-05, + "loss": 3.4361, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9539028396259608e-05, + "loss": 3.4561, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9530658827552817e-05, + "loss": 3.4402, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522272880042297e-05, + "loss": 3.4559, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9513886932531777e-05, + "loss": 3.4472, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505500985021257e-05, + "loss": 3.4269, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949713141631447e-05, + "loss": 3.4503, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948874546880395e-05, + "loss": 3.4401, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.948035952129343e-05, + "loss": 3.4279, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.947197357378291e-05, + "loss": 3.4525, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463604005076118e-05, + "loss": 3.4464, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455218057565598e-05, + "loss": 3.4345, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.944683211005508e-05, + "loss": 3.4415, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943844616254456e-05, + "loss": 3.4279, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.943007659383777e-05, + "loss": 3.4402, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.942169064632725e-05, + "loss": 3.4457, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.941330469881673e-05, + "loss": 3.4453, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940491875130621e-05, + "loss": 3.456, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396549182599423e-05, + "loss": 3.4435, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388163235088903e-05, + "loss": 3.4572, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379777287578383e-05, + "loss": 3.4426, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371391340067863e-05, + "loss": 3.4527, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9363021771361072e-05, + "loss": 3.4369, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9354635823850552e-05, + "loss": 3.4368, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9346249876340035e-05, + "loss": 3.4529, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337863928829515e-05, + "loss": 3.4549, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329494360122724e-05, + "loss": 3.4489, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321108412612204e-05, + "loss": 3.4522, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9312722465101684e-05, + "loss": 3.4275, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304336517591164e-05, + "loss": 3.4324, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9295966948884376e-05, + "loss": 3.446, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287581001373856e-05, + "loss": 3.4507, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279195053863336e-05, + "loss": 3.4382, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9270809106352813e-05, + "loss": 3.4465, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262439537646025e-05, + "loss": 3.4374, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9254053590135505e-05, + "loss": 3.4453, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924566764262499e-05, + "loss": 3.439, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9237281695114465e-05, + "loss": 3.4423, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9228912126407678e-05, + "loss": 3.4546, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9220526178897158e-05, + "loss": 3.4555, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212140231386638e-05, + "loss": 3.4575, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9203754283876114e-05, + "loss": 3.4319, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.919538471516933e-05, + "loss": 3.4489, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.918699876765881e-05, + "loss": 3.4437, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9178612820148287e-05, + "loss": 3.4477, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170226872637767e-05, + "loss": 3.4382, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.916185730393098e-05, + "loss": 3.4463, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.915347135642046e-05, + "loss": 3.4408, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.914508540890994e-05, + "loss": 3.4422, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913669946139942e-05, + "loss": 3.4383, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912832989269263e-05, + "loss": 3.4424, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.911994394518211e-05, + "loss": 3.4324, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111557997671588e-05, + "loss": 3.4479, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103172050161068e-05, + "loss": 3.445, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094802481454284e-05, + "loss": 3.4392, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.908641653394376e-05, + "loss": 3.4456, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.907803058643324e-05, + "loss": 3.44, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.906964463892272e-05, + "loss": 3.4499, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061275070215933e-05, + "loss": 3.4403, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052889122705413e-05, + "loss": 3.4502, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044503175194893e-05, + "loss": 3.4558, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036117227684373e-05, + "loss": 3.4439, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9027747658977585e-05, + "loss": 3.4462, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.901936171146706e-05, + "loss": 3.4398, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.901097576395654e-05, + "loss": 3.4387, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.900258981644602e-05, + "loss": 3.4421, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994220247739234e-05, + "loss": 3.4434, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985834300228714e-05, + "loss": 3.428, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977448352718194e-05, + "loss": 3.4526, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8969062405207674e-05, + "loss": 3.4444, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8960692836500883e-05, + "loss": 3.4478, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8952306888990366e-05, + "loss": 3.4425, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8943920941479846e-05, + "loss": 3.4372, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935534993969326e-05, + "loss": 3.4398, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927165425262535e-05, + "loss": 3.449, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918779477752015e-05, + "loss": 3.4469, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910393530241495e-05, + "loss": 3.4528, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8902007582730975e-05, + "loss": 3.4216, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8893638014024188e-05, + "loss": 3.4499, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8885252066513668e-05, + "loss": 3.4387, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8876866119003148e-05, + "loss": 3.4531, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8868480171492628e-05, + "loss": 3.4334, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8860110602785837e-05, + "loss": 3.4435, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.885172465527532e-05, + "loss": 3.4495, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.88433387077648e-05, + "loss": 3.4593, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.883495276025428e-05, + "loss": 3.4413, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882658319154749e-05, + "loss": 3.4475, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.881819724403697e-05, + "loss": 3.439, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.880981129652645e-05, + "loss": 3.4526, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.880142534901593e-05, + "loss": 3.4417, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.879305578030914e-05, + "loss": 3.44, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.878466983279862e-05, + "loss": 3.446, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.87762838852881e-05, + "loss": 3.4332, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.876789793777758e-05, + "loss": 3.4467, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.8812294006347656, + "eval_runtime": 306.8, + "eval_samples_per_second": 1243.778, + "eval_steps_per_second": 38.869, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.875952836907079e-05, + "loss": 3.437, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751142421560274e-05, + "loss": 3.4331, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742756474049754e-05, + "loss": 3.4467, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734370526539234e-05, + "loss": 3.4414, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726000957832443e-05, + "loss": 3.456, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717615010321923e-05, + "loss": 3.4406, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709229062811403e-05, + "loss": 3.4411, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700843115300883e-05, + "loss": 3.4487, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692473546594095e-05, + "loss": 3.4361, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684087599083575e-05, + "loss": 3.4425, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675701651573055e-05, + "loss": 3.4411, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667315704062535e-05, + "loss": 3.4464, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8658946135355744e-05, + "loss": 3.4473, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8650560187845227e-05, + "loss": 3.4286, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8642174240334707e-05, + "loss": 3.4357, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633788292824184e-05, + "loss": 3.4245, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625418724117396e-05, + "loss": 3.4359, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617032776606876e-05, + "loss": 3.4447, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8608646829096356e-05, + "loss": 3.4277, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600260881585836e-05, + "loss": 3.4548, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.859189131287905e-05, + "loss": 3.4505, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858350536536853e-05, + "loss": 3.4487, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857511941785801e-05, + "loss": 3.4436, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566733470347485e-05, + "loss": 3.4419, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558363901640698e-05, + "loss": 3.4453, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.854997795413018e-05, + "loss": 3.443, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541592006619658e-05, + "loss": 3.433, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533206059109138e-05, + "loss": 3.4456, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852483649040235e-05, + "loss": 3.4269, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.851645054289183e-05, + "loss": 3.4329, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508064595381307e-05, + "loss": 3.4402, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849967864787079e-05, + "loss": 3.4411, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491309079164002e-05, + "loss": 3.4413, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8482923131653482e-05, + "loss": 3.4507, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847453718414296e-05, + "loss": 3.4366, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846615123663244e-05, + "loss": 3.4267, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.845778166792565e-05, + "loss": 3.4423, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.844939572041513e-05, + "loss": 3.428, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.844100977290461e-05, + "loss": 3.4365, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.843262382539409e-05, + "loss": 3.4355, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424254256687304e-05, + "loss": 3.4347, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.841586830917678e-05, + "loss": 3.4378, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.840748236166626e-05, + "loss": 3.445, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399096414155744e-05, + "loss": 3.4414, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390726845448956e-05, + "loss": 3.4393, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382340897938433e-05, + "loss": 3.4345, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8373954950427913e-05, + "loss": 3.4396, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365569002917393e-05, + "loss": 3.4413, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357199434210605e-05, + "loss": 3.4179, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348813486700085e-05, + "loss": 3.4479, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340427539189565e-05, + "loss": 3.4304, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332041591679045e-05, + "loss": 3.44, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323672022972254e-05, + "loss": 3.4305, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315286075461734e-05, + "loss": 3.4261, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8306900127951214e-05, + "loss": 3.4244, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8298514180440697e-05, + "loss": 3.4281, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8290144611733906e-05, + "loss": 3.4477, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281758664223386e-05, + "loss": 3.4296, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273372716712866e-05, + "loss": 3.446, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265003148006075e-05, + "loss": 3.4387, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825661720049556e-05, + "loss": 3.4154, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824823125298504e-05, + "loss": 3.4374, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.823984530547452e-05, + "loss": 3.4257, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231475736767728e-05, + "loss": 3.4244, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223089789257208e-05, + "loss": 3.4392, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214703841746688e-05, + "loss": 3.4363, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206317894236168e-05, + "loss": 3.4252, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819794832552938e-05, + "loss": 3.4298, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.818956237801886e-05, + "loss": 3.4209, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.818117643050834e-05, + "loss": 3.4261, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.817279048299782e-05, + "loss": 3.4392, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.816442091429103e-05, + "loss": 3.4364, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156034966780512e-05, + "loss": 3.4417, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147649019269992e-05, + "loss": 3.4338, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139263071759472e-05, + "loss": 3.449, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.813089350305268e-05, + "loss": 3.4283, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.812250755554216e-05, + "loss": 3.4466, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.811412160803164e-05, + "loss": 3.4232, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.810573566052112e-05, + "loss": 3.4276, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097366091814334e-05, + "loss": 3.4388, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088980144303814e-05, + "loss": 3.4427, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080594196793294e-05, + "loss": 3.439, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072208249282774e-05, + "loss": 3.4419, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063838680575983e-05, + "loss": 3.4177, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055452733065466e-05, + "loss": 3.4197, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8047066785554946e-05, + "loss": 3.4361, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038680838044426e-05, + "loss": 3.4384, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030311269337635e-05, + "loss": 3.4276, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8021925321827115e-05, + "loss": 3.4337, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013539374316595e-05, + "loss": 3.433, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005153426806075e-05, + "loss": 3.4336, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996783858099287e-05, + "loss": 3.4249, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988397910588767e-05, + "loss": 3.4328, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7980011963078247e-05, + "loss": 3.4427, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971626015567727e-05, + "loss": 3.4452, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963256446860936e-05, + "loss": 3.4457, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7954870499350416e-05, + "loss": 3.4226, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.79464845518399e-05, + "loss": 3.4353, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793809860432938e-05, + "loss": 3.432, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792972903562259e-05, + "loss": 3.4389, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.792134308811207e-05, + "loss": 3.4315, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.791295714060155e-05, + "loss": 3.4323, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.790457119309103e-05, + "loss": 3.4296, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.789620162438424e-05, + "loss": 3.4276, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.788781567687372e-05, + "loss": 3.4292, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.78794297293632e-05, + "loss": 3.4328, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7871043781852678e-05, + "loss": 3.4249, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.786267421314589e-05, + "loss": 3.4379, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785428826563537e-05, + "loss": 3.4345, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845902318124853e-05, + "loss": 3.4277, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.783751637061433e-05, + "loss": 3.4317, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829146801907542e-05, + "loss": 3.4297, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7820760854397022e-05, + "loss": 3.4368, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.78123749068865e-05, + "loss": 3.4286, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7803988959375982e-05, + "loss": 3.4413, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795619390669195e-05, + "loss": 3.4453, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787233443158675e-05, + "loss": 3.4363, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.777884749564815e-05, + "loss": 3.4346, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.777046154813763e-05, + "loss": 3.4332, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762091979430844e-05, + "loss": 3.4282, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7753706031920324e-05, + "loss": 3.4343, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745320084409804e-05, + "loss": 3.4287, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736934136899284e-05, + "loss": 3.4216, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728564568192496e-05, + "loss": 3.4439, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720178620681973e-05, + "loss": 3.4369, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7711792673171453e-05, + "loss": 3.4345, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703406725660936e-05, + "loss": 3.4318, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769503715695415e-05, + "loss": 3.4251, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686651209443625e-05, + "loss": 3.4274, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678265261933105e-05, + "loss": 3.4407, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669879314422585e-05, + "loss": 3.4374, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661509745715797e-05, + "loss": 3.4434, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7653123798205277e-05, + "loss": 3.4129, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644737850694757e-05, + "loss": 3.4417, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636351903184237e-05, + "loss": 3.4302, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7627982334477446e-05, + "loss": 3.4409, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619596386966926e-05, + "loss": 3.4264, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611210439456406e-05, + "loss": 3.4287, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.760282449194589e-05, + "loss": 3.4368, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.75944549232391e-05, + "loss": 3.4518, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758606897572858e-05, + "loss": 3.4298, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757768302821806e-05, + "loss": 3.4384, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569313459511268e-05, + "loss": 3.4271, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.756092751200075e-05, + "loss": 3.4381, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.755254156449023e-05, + "loss": 3.4299, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.754415561697971e-05, + "loss": 3.43, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.753578604827292e-05, + "loss": 3.4365, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.75274001007624e-05, + "loss": 3.4272, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.751901415325188e-05, + "loss": 3.4387, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.880690336227417, + "eval_runtime": 303.5504, + "eval_samples_per_second": 1257.093, + "eval_steps_per_second": 39.285, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.751062820574136e-05, + "loss": 3.4265, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502258637034572e-05, + "loss": 3.4224, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493872689524052e-05, + "loss": 3.435, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485486742013532e-05, + "loss": 3.4327, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477100794503012e-05, + "loss": 3.4458, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.746873122579622e-05, + "loss": 3.4299, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.74603452782857e-05, + "loss": 3.4305, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451959330775185e-05, + "loss": 3.4407, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443573383264665e-05, + "loss": 3.4264, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435203814557874e-05, + "loss": 3.425, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426817867047354e-05, + "loss": 3.4363, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418431919536834e-05, + "loss": 3.4355, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7410062350830046e-05, + "loss": 3.4369, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7401676403319526e-05, + "loss": 3.4175, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393290455809006e-05, + "loss": 3.4271, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384904508298486e-05, + "loss": 3.4111, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376518560787966e-05, + "loss": 3.4264, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368132613277446e-05, + "loss": 3.434, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7359746665766922e-05, + "loss": 3.4169, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351360718256406e-05, + "loss": 3.4432, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7342991149549618e-05, + "loss": 3.4398, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334605202039098e-05, + "loss": 3.4387, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326219254528575e-05, + "loss": 3.4321, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317833307018055e-05, + "loss": 3.4327, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309463738311267e-05, + "loss": 3.4378, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7301077790800747e-05, + "loss": 3.4298, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7292691843290227e-05, + "loss": 3.4246, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7284305895779707e-05, + "loss": 3.4371, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727593632707292e-05, + "loss": 3.4189, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267550379562396e-05, + "loss": 3.418, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259164432051876e-05, + "loss": 3.4312, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.725077848454136e-05, + "loss": 3.4289, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242408915834572e-05, + "loss": 3.4341, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.723402296832405e-05, + "loss": 3.438, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.722563702081353e-05, + "loss": 3.4228, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.721725107330301e-05, + "loss": 3.4212, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.720888150459622e-05, + "loss": 3.4295, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.72004955570857e-05, + "loss": 3.4182, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.719210960957518e-05, + "loss": 3.4271, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.718372366206466e-05, + "loss": 3.4281, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717535409335787e-05, + "loss": 3.421, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716696814584735e-05, + "loss": 3.4306, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.715858219833683e-05, + "loss": 3.4372, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.715019625082631e-05, + "loss": 3.4292, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141826682119522e-05, + "loss": 3.4287, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133440734609002e-05, + "loss": 3.4239, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125054787098482e-05, + "loss": 3.4286, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7116668839587962e-05, + "loss": 3.4263, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108299270881175e-05, + "loss": 3.4116, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099913323370655e-05, + "loss": 3.4362, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091527375860134e-05, + "loss": 3.422, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7083141428349614e-05, + "loss": 3.4291, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7074771859642824e-05, + "loss": 3.421, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066385912132303e-05, + "loss": 3.4145, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7057999964621783e-05, + "loss": 3.4109, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7049630395914996e-05, + "loss": 3.4145, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7041244448404476e-05, + "loss": 3.4387, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7032858500893956e-05, + "loss": 3.4184, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7024472553383436e-05, + "loss": 3.4357, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016102984676645e-05, + "loss": 3.4265, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7007717037166125e-05, + "loss": 3.407, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999331089655608e-05, + "loss": 3.4274, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6990945142145088e-05, + "loss": 3.4157, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982575573438297e-05, + "loss": 3.4132, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974189625927777e-05, + "loss": 3.4263, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965803678417257e-05, + "loss": 3.4268, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957417730906737e-05, + "loss": 3.4137, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694904816219995e-05, + "loss": 3.4241, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.694066221468943e-05, + "loss": 3.4087, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.693227626717891e-05, + "loss": 3.417, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692389031966839e-05, + "loss": 3.4249, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.69155207509616e-05, + "loss": 3.4257, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.690713480345108e-05, + "loss": 3.4278, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898748855940562e-05, + "loss": 3.427, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890362908430042e-05, + "loss": 3.4373, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.688199333972325e-05, + "loss": 3.4206, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687360739221273e-05, + "loss": 3.4357, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686522144470221e-05, + "loss": 3.411, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.685683549719169e-05, + "loss": 3.4198, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848465928484903e-05, + "loss": 3.4283, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840079980974383e-05, + "loss": 3.4292, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831694033463863e-05, + "loss": 3.4317, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823308085953343e-05, + "loss": 3.4315, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6814938517246552e-05, + "loss": 3.4121, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806552569736032e-05, + "loss": 3.4064, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798166622225516e-05, + "loss": 3.4277, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789780674714995e-05, + "loss": 3.4274, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781411106008205e-05, + "loss": 3.4206, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6773025158497685e-05, + "loss": 3.4269, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764639210987164e-05, + "loss": 3.4222, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756253263476644e-05, + "loss": 3.421, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6747883694769857e-05, + "loss": 3.4196, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739497747259337e-05, + "loss": 3.4205, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6731111799748817e-05, + "loss": 3.4316, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6722725852238293e-05, + "loss": 3.435, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714356283531506e-05, + "loss": 3.4353, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6705970336020986e-05, + "loss": 3.4097, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669758438851047e-05, + "loss": 3.4251, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6689198440999946e-05, + "loss": 3.4245, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680828872293158e-05, + "loss": 3.4243, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672442924782638e-05, + "loss": 3.4232, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664056977272118e-05, + "loss": 3.4224, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6655671029761598e-05, + "loss": 3.4216, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.664730146105481e-05, + "loss": 3.4166, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.663891551354429e-05, + "loss": 3.4193, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630529566033767e-05, + "loss": 3.4222, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6622143618523247e-05, + "loss": 3.4156, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.661377404981646e-05, + "loss": 3.4248, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.660538810230594e-05, + "loss": 3.4225, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.659700215479542e-05, + "loss": 3.4171, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.65886162072849e-05, + "loss": 3.4247, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580246638578112e-05, + "loss": 3.4182, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6571860691067592e-05, + "loss": 3.4262, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.656347474355707e-05, + "loss": 3.4225, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.655508879604655e-05, + "loss": 3.4261, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6546719227339764e-05, + "loss": 3.4363, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653833327982924e-05, + "loss": 3.4254, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652994733231872e-05, + "loss": 3.4201, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.65215613848082e-05, + "loss": 3.425, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6513191816101413e-05, + "loss": 3.4155, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6504805868590893e-05, + "loss": 3.425, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496419921080373e-05, + "loss": 3.4205, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488033973569853e-05, + "loss": 3.412, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479664404863066e-05, + "loss": 3.4311, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471278457352542e-05, + "loss": 3.4285, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6462892509842022e-05, + "loss": 3.4246, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454522941135238e-05, + "loss": 3.4212, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6446136993624715e-05, + "loss": 3.4169, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437751046114195e-05, + "loss": 3.4161, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429365098603674e-05, + "loss": 3.43, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6420995529896887e-05, + "loss": 3.4264, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6412609582386364e-05, + "loss": 3.4317, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6404223634875847e-05, + "loss": 3.4023, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6395837687365327e-05, + "loss": 3.4323, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638746811865854e-05, + "loss": 3.4171, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6379082171148016e-05, + "loss": 3.4351, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370696223637496e-05, + "loss": 3.415, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362310276126976e-05, + "loss": 3.4199, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6353940707420188e-05, + "loss": 3.427, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6345554759909668e-05, + "loss": 3.4436, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6337168812399148e-05, + "loss": 3.4194, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6328782864888628e-05, + "loss": 3.4314, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320413296181837e-05, + "loss": 3.4145, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6312027348671317e-05, + "loss": 3.4293, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.63036414011608e-05, + "loss": 3.4189, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.629525545365028e-05, + "loss": 3.4227, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.628688588494349e-05, + "loss": 3.4249, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627849993743297e-05, + "loss": 3.4193, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.627011398992245e-05, + "loss": 3.4288, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.882960081100464, + "eval_runtime": 304.4287, + "eval_samples_per_second": 1253.466, + "eval_steps_per_second": 39.172, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.626172804241193e-05, + "loss": 3.4221, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625334209490141e-05, + "loss": 3.4116, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244956147390893e-05, + "loss": 3.4265, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.623657019988037e-05, + "loss": 3.4181, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228200631173582e-05, + "loss": 3.4359, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219814683663062e-05, + "loss": 3.4211, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211428736152542e-05, + "loss": 3.4214, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6203042788642018e-05, + "loss": 3.4291, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194673219935234e-05, + "loss": 3.4175, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186287272424714e-05, + "loss": 3.4142, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617790132491419e-05, + "loss": 3.4284, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616951537740367e-05, + "loss": 3.4239, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6161162187500616e-05, + "loss": 3.4311, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152776239990096e-05, + "loss": 3.4081, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144390292479576e-05, + "loss": 3.4125, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6136004344969056e-05, + "loss": 3.4073, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127618397458535e-05, + "loss": 3.4179, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119232449948015e-05, + "loss": 3.418, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110846502437492e-05, + "loss": 3.4124, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102460554926972e-05, + "loss": 3.4266, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6094090986220188e-05, + "loss": 3.4341, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085705038709664e-05, + "loss": 3.4269, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077319091199144e-05, + "loss": 3.4234, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068933143688624e-05, + "loss": 3.4223, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060563574981837e-05, + "loss": 3.4305, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052177627471317e-05, + "loss": 3.4178, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6043791679960797e-05, + "loss": 3.4155, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035405732450277e-05, + "loss": 3.4261, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602703616374349e-05, + "loss": 3.408, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018650216232966e-05, + "loss": 3.4087, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010264268722446e-05, + "loss": 3.418, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001878321211926e-05, + "loss": 3.4176, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993508752505138e-05, + "loss": 3.4254, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5985122804994618e-05, + "loss": 3.4269, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5976736857484098e-05, + "loss": 3.4157, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968350909973578e-05, + "loss": 3.4135, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959981341266787e-05, + "loss": 3.4169, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.595159539375627e-05, + "loss": 3.4094, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594320944624575e-05, + "loss": 3.4202, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.593482349873523e-05, + "loss": 3.4126, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592645393002844e-05, + "loss": 3.4134, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591806798251792e-05, + "loss": 3.4203, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.59096820350074e-05, + "loss": 3.4306, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.590129608749688e-05, + "loss": 3.4141, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892926518790092e-05, + "loss": 3.4217, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884540571279572e-05, + "loss": 3.4185, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587615462376905e-05, + "loss": 3.4147, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.586776867625853e-05, + "loss": 3.417, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585939910755174e-05, + "loss": 3.4026, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5851013160041224e-05, + "loss": 3.4256, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842627212530704e-05, + "loss": 3.4141, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834241265020184e-05, + "loss": 3.4216, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825871696313393e-05, + "loss": 3.4109, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5817485748802873e-05, + "loss": 3.4026, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5809099801292353e-05, + "loss": 3.4029, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5800713853781833e-05, + "loss": 3.4027, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792344285075045e-05, + "loss": 3.4282, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783958337564525e-05, + "loss": 3.4092, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775572390054005e-05, + "loss": 3.4257, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767186442543485e-05, + "loss": 3.4136, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5758816873836694e-05, + "loss": 3.4016, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5750430926326178e-05, + "loss": 3.4158, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5742044978815658e-05, + "loss": 3.4072, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733675410108867e-05, + "loss": 3.4036, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725289462598347e-05, + "loss": 3.4152, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716903515087827e-05, + "loss": 3.4186, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708517567577307e-05, + "loss": 3.4057, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.570014799887052e-05, + "loss": 3.414, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.569176205136e-05, + "loss": 3.395, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568337610384948e-05, + "loss": 3.4078, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567499015633896e-05, + "loss": 3.4142, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666620587632168e-05, + "loss": 3.4191, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5658234640121648e-05, + "loss": 3.4168, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.564984869261113e-05, + "loss": 3.4141, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.564146274510061e-05, + "loss": 3.4266, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.563309317639382e-05, + "loss": 3.4129, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.56247072288833e-05, + "loss": 3.4249, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561632128137278e-05, + "loss": 3.4044, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560793533386226e-05, + "loss": 3.4102, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599565765155473e-05, + "loss": 3.4156, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591179817644953e-05, + "loss": 3.4168, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5582793870134433e-05, + "loss": 3.4192, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574407922623913e-05, + "loss": 3.4244, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5566038353917122e-05, + "loss": 3.4023, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557652406406602e-05, + "loss": 3.3954, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549266458896085e-05, + "loss": 3.4129, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.554088051138556e-05, + "loss": 3.4196, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532510942678774e-05, + "loss": 3.4107, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524124995168254e-05, + "loss": 3.4165, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5515739047657734e-05, + "loss": 3.4123, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550735310014721e-05, + "loss": 3.4116, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498983531440426e-05, + "loss": 3.4105, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490597583929906e-05, + "loss": 3.413, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5482211636419386e-05, + "loss": 3.4182, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473825688908863e-05, + "loss": 3.4266, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465456120202075e-05, + "loss": 3.4241, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5457070172691555e-05, + "loss": 3.3995, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5448684225181035e-05, + "loss": 3.4193, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440298277670515e-05, + "loss": 3.4132, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431928708963728e-05, + "loss": 3.4161, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423542761453208e-05, + "loss": 3.4129, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5415156813942684e-05, + "loss": 3.4117, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406770866432164e-05, + "loss": 3.4089, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539840129772538e-05, + "loss": 3.4083, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.539001535021486e-05, + "loss": 3.409, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381629402704337e-05, + "loss": 3.4126, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373243455193817e-05, + "loss": 3.4072, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.536487388648703e-05, + "loss": 3.4139, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.535648793897651e-05, + "loss": 3.4149, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534810199146599e-05, + "loss": 3.4053, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.533971604395547e-05, + "loss": 3.4125, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.533134647524868e-05, + "loss": 3.4108, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322960527738158e-05, + "loss": 3.4184, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314574580227638e-05, + "loss": 3.4125, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306188632717118e-05, + "loss": 3.4114, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297819064010334e-05, + "loss": 3.4263, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.528943311649981e-05, + "loss": 3.4221, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.528104716898929e-05, + "loss": 3.4095, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527266122147877e-05, + "loss": 3.4159, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.526429165277198e-05, + "loss": 3.4047, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255905705261461e-05, + "loss": 3.415, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247519757750941e-05, + "loss": 3.4101, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239133810240423e-05, + "loss": 3.4016, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5230764241533632e-05, + "loss": 3.4211, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222378294023112e-05, + "loss": 3.4186, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213992346512593e-05, + "loss": 3.4129, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205622777805806e-05, + "loss": 3.4145, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197236830295284e-05, + "loss": 3.4054, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188850882784764e-05, + "loss": 3.4036, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180464935274244e-05, + "loss": 3.4198, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172095366567455e-05, + "loss": 3.4169, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163709419056935e-05, + "loss": 3.4249, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155323471546415e-05, + "loss": 3.3959, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5146937524035895e-05, + "loss": 3.4165, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138567955329105e-05, + "loss": 3.4121, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130182007818585e-05, + "loss": 3.4197, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121796060308065e-05, + "loss": 3.4071, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113410112797547e-05, + "loss": 3.4082, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105040544090756e-05, + "loss": 3.4169, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096654596580238e-05, + "loss": 3.4316, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088268649069718e-05, + "loss": 3.4097, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079882701559198e-05, + "loss": 3.4189, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071513132852408e-05, + "loss": 3.405, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063127185341888e-05, + "loss": 3.4171, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054741237831368e-05, + "loss": 3.4099, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046355290320848e-05, + "loss": 3.4118, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037985721614059e-05, + "loss": 3.4142, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029599774103539e-05, + "loss": 3.4133, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021213826593019e-05, + "loss": 3.4155, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8839986324310303, + "eval_runtime": 305.8987, + "eval_samples_per_second": 1247.442, + "eval_steps_per_second": 38.983, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.50128278790825e-05, + "loss": 3.4111, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.500445831037571e-05, + "loss": 3.3965, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.499607236286519e-05, + "loss": 3.4156, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987686415354671e-05, + "loss": 3.4126, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979300467844151e-05, + "loss": 3.4204, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970930899137362e-05, + "loss": 3.4158, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962544951626842e-05, + "loss": 3.4088, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954159004116322e-05, + "loss": 3.4195, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4945773056605802e-05, + "loss": 3.406, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937403487899013e-05, + "loss": 3.4101, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4929017540388493e-05, + "loss": 3.4151, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920631592877973e-05, + "loss": 3.4152, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912262024171183e-05, + "loss": 3.4194, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903876076660663e-05, + "loss": 3.398, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895490129150143e-05, + "loss": 3.4013, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887104181639625e-05, + "loss": 3.3979, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4878718234129105e-05, + "loss": 3.4097, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870332286618582e-05, + "loss": 3.4067, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861946339108063e-05, + "loss": 3.4063, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853560391597543e-05, + "loss": 3.4133, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845190822890756e-05, + "loss": 3.4254, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836804875380234e-05, + "loss": 3.4159, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828418927869714e-05, + "loss": 3.4141, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820032980359194e-05, + "loss": 3.4123, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811663411652405e-05, + "loss": 3.4244, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803277464141885e-05, + "loss": 3.4033, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794891516631365e-05, + "loss": 3.4036, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786505569120846e-05, + "loss": 3.4181, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778136000414055e-05, + "loss": 3.3965, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769750052903535e-05, + "loss": 3.4005, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761364105393017e-05, + "loss": 3.4095, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752978157882497e-05, + "loss": 3.4079, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744608589175708e-05, + "loss": 3.4163, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736222641665188e-05, + "loss": 3.4143, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727836694154668e-05, + "loss": 3.4073, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719450746644147e-05, + "loss": 3.4028, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711081177937358e-05, + "loss": 3.4084, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702695230426838e-05, + "loss": 3.3972, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694309282916318e-05, + "loss": 3.4103, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.46859233354058e-05, + "loss": 3.4027, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677553766699009e-05, + "loss": 3.4044, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669167819188489e-05, + "loss": 3.4084, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.466078187167797e-05, + "loss": 3.4229, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.465239592416745e-05, + "loss": 3.4025, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644026355460661e-05, + "loss": 3.4109, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635640407950141e-05, + "loss": 3.4095, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627254460439621e-05, + "loss": 3.405, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618868512929101e-05, + "loss": 3.4087, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610498944222312e-05, + "loss": 3.3951, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4602112996711792e-05, + "loss": 3.4106, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593727049201272e-05, + "loss": 3.4064, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585341101690752e-05, + "loss": 3.4072, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576971532983963e-05, + "loss": 3.4025, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568585585473443e-05, + "loss": 3.3959, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560199637962924e-05, + "loss": 3.3903, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551813690452404e-05, + "loss": 3.3914, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543444121745613e-05, + "loss": 3.4217, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535058174235095e-05, + "loss": 3.3977, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526672226724575e-05, + "loss": 3.4143, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518286279214055e-05, + "loss": 3.4055, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509916710507266e-05, + "loss": 3.3922, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501530762996746e-05, + "loss": 3.4039, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493144815486226e-05, + "loss": 3.3974, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484758867975705e-05, + "loss": 3.3964, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476389299268916e-05, + "loss": 3.4021, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4468003351758396e-05, + "loss": 3.4092, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459617404247878e-05, + "loss": 3.3974, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4451247835541087e-05, + "loss": 3.401, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442861888030567e-05, + "loss": 3.3861, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434475940520049e-05, + "loss": 3.3979, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4426089993009529e-05, + "loss": 3.4023, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.441772042430274e-05, + "loss": 3.4102, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.440933447679222e-05, + "loss": 3.4077, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.44009485292817e-05, + "loss": 3.407, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.439256258177118e-05, + "loss": 3.4122, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.438419301306439e-05, + "loss": 3.4026, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.437580706555387e-05, + "loss": 3.4124, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.436742111804335e-05, + "loss": 3.3983, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359035170532832e-05, + "loss": 3.4045, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.435066560182604e-05, + "loss": 3.4048, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.434227965431552e-05, + "loss": 3.4061, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333893706805002e-05, + "loss": 3.4116, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325507759294479e-05, + "loss": 3.4135, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317138190587693e-05, + "loss": 3.3951, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308752243077173e-05, + "loss": 3.3817, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300366295566653e-05, + "loss": 3.4053, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291980348056131e-05, + "loss": 3.4084, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283610779349344e-05, + "loss": 3.4002, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275224831838824e-05, + "loss": 3.4054, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266838884328302e-05, + "loss": 3.4044, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258452936817782e-05, + "loss": 3.3995, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250083368110994e-05, + "loss": 3.4016, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241697420600474e-05, + "loss": 3.4003, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233311473089953e-05, + "loss": 3.407, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224925525579432e-05, + "loss": 3.4169, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216555956872647e-05, + "loss": 3.4158, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208170009362127e-05, + "loss": 3.3895, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199784061851603e-05, + "loss": 3.4065, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191398114341085e-05, + "loss": 3.4057, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4183028545634297e-05, + "loss": 3.4066, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174642598123774e-05, + "loss": 3.4049, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166256650613256e-05, + "loss": 3.4039, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157870703102735e-05, + "loss": 3.3974, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149501134395948e-05, + "loss": 3.4018, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141115186885426e-05, + "loss": 3.4001, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132729239374906e-05, + "loss": 3.4006, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124343291864386e-05, + "loss": 3.3976, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115973723157599e-05, + "loss": 3.4041, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107587775647077e-05, + "loss": 3.4049, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099201828136557e-05, + "loss": 3.394, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090815880626037e-05, + "loss": 3.4063, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082446311919248e-05, + "loss": 3.3951, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074060364408728e-05, + "loss": 3.409, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.406567441689821e-05, + "loss": 3.4039, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.405728846938769e-05, + "loss": 3.4046, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.40489189006809e-05, + "loss": 3.4093, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.404053295317038e-05, + "loss": 3.4139, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.403214700565986e-05, + "loss": 3.4001, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.402376105814934e-05, + "loss": 3.4049, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.401539148944255e-05, + "loss": 3.3943, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.400700554193203e-05, + "loss": 3.4033, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399861959442151e-05, + "loss": 3.4014, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.399023364691099e-05, + "loss": 3.3885, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981864078204201e-05, + "loss": 3.4081, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973478130693681e-05, + "loss": 3.4104, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3965092183183163e-05, + "loss": 3.4066, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956706235672643e-05, + "loss": 3.402, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948336666965852e-05, + "loss": 3.3926, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3939950719455334e-05, + "loss": 3.3953, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931564771944814e-05, + "loss": 3.4134, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923178824434293e-05, + "loss": 3.4057, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914809255727504e-05, + "loss": 3.4174, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906423308216984e-05, + "loss": 3.385, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898037360706464e-05, + "loss": 3.4051, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889651413195944e-05, + "loss": 3.4053, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881281844489155e-05, + "loss": 3.4054, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872895896978635e-05, + "loss": 3.3989, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864509949468117e-05, + "loss": 3.3986, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856124001957596e-05, + "loss": 3.4069, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847754433250806e-05, + "loss": 3.4212, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839368485740287e-05, + "loss": 3.4036, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830982538229767e-05, + "loss": 3.4079, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822612969522978e-05, + "loss": 3.4, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814227022012458e-05, + "loss": 3.4072, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805841074501938e-05, + "loss": 3.3983, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797455126991418e-05, + "loss": 3.4071, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789085558284629e-05, + "loss": 3.3994, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780699610774109e-05, + "loss": 3.4028, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772313663263589e-05, + "loss": 3.4059, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.884648084640503, + "eval_runtime": 305.3973, + "eval_samples_per_second": 1249.491, + "eval_steps_per_second": 39.048, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.376392771575307e-05, + "loss": 3.413, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.375554176824255e-05, + "loss": 3.3893, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747155820732027e-05, + "loss": 3.4037, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738769873221508e-05, + "loss": 3.4089, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730400304514721e-05, + "loss": 3.4054, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.37220143570042e-05, + "loss": 3.4088, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713628409493679e-05, + "loss": 3.3977, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705242461983159e-05, + "loss": 3.4102, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696872893276372e-05, + "loss": 3.3959, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.368848694576585e-05, + "loss": 3.4, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.368010099825533e-05, + "loss": 3.4051, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.367171505074481e-05, + "loss": 3.4061, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663361860841753e-05, + "loss": 3.415, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654975913331233e-05, + "loss": 3.3878, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646589965820713e-05, + "loss": 3.3881, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638204018310195e-05, + "loss": 3.392, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629818070799671e-05, + "loss": 3.3994, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621432123289151e-05, + "loss": 3.3938, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3613046175778633e-05, + "loss": 3.3966, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604660228268113e-05, + "loss": 3.406, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596290659561322e-05, + "loss": 3.4125, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587904712050803e-05, + "loss": 3.4101, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579518764540283e-05, + "loss": 3.4028, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571132817029763e-05, + "loss": 3.4039, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562763248322974e-05, + "loss": 3.4115, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554377300812454e-05, + "loss": 3.3961, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545991353301934e-05, + "loss": 3.3939, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537605405791414e-05, + "loss": 3.4112, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529235837084625e-05, + "loss": 3.384, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520849889574105e-05, + "loss": 3.3914, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512463942063586e-05, + "loss": 3.3918, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3504077994553066e-05, + "loss": 3.4038, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495708425846275e-05, + "loss": 3.4065, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487322478335757e-05, + "loss": 3.404, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478936530825237e-05, + "loss": 3.3991, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470550583314717e-05, + "loss": 3.3938, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462181014607928e-05, + "loss": 3.396, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453795067097408e-05, + "loss": 3.385, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445409119586888e-05, + "loss": 3.405, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437023172076368e-05, + "loss": 3.3903, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428653603369578e-05, + "loss": 3.3976, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420267655859058e-05, + "loss": 3.3966, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.341188170834854e-05, + "loss": 3.4127, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.340349576083802e-05, + "loss": 3.3973, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395126192131229e-05, + "loss": 3.4008, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.338674024462071e-05, + "loss": 3.4007, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.337835429711019e-05, + "loss": 3.3964, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.336996834959967e-05, + "loss": 3.3957, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361598780892881e-05, + "loss": 3.3865, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353212833382361e-05, + "loss": 3.3993, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344826885871841e-05, + "loss": 3.4019, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336440938361321e-05, + "loss": 3.3942, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328071369654532e-05, + "loss": 3.393, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319685422144012e-05, + "loss": 3.3835, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311299474633494e-05, + "loss": 3.3859, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302913527122974e-05, + "loss": 3.3785, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294543958416183e-05, + "loss": 3.4143, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286158010905664e-05, + "loss": 3.3872, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277772063395144e-05, + "loss": 3.4077, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269402494688355e-05, + "loss": 3.3915, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3261016547177835e-05, + "loss": 3.3824, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252630599667315e-05, + "loss": 3.3899, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244244652156795e-05, + "loss": 3.3878, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235875083450006e-05, + "loss": 3.3893, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227489135939486e-05, + "loss": 3.388, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219103188428966e-05, + "loss": 3.4005, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210717240918446e-05, + "loss": 3.3903, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202347672211657e-05, + "loss": 3.3888, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193961724701136e-05, + "loss": 3.3798, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185575777190618e-05, + "loss": 3.3891, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177189829680098e-05, + "loss": 3.3908, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168820260973307e-05, + "loss": 3.4023, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160434313462789e-05, + "loss": 3.3964, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3152048365952269e-05, + "loss": 3.398, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143662418441745e-05, + "loss": 3.3999, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.313529284973496e-05, + "loss": 3.3958, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.312690690222444e-05, + "loss": 3.3982, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.311852095471392e-05, + "loss": 3.3869, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110135007203398e-05, + "loss": 3.3962, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.310176543849661e-05, + "loss": 3.3924, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.309337949098609e-05, + "loss": 3.396, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084993543475572e-05, + "loss": 3.4079, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076607595965048e-05, + "loss": 3.4019, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.306823802725826e-05, + "loss": 3.387, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059852079747742e-05, + "loss": 3.3685, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051466132237219e-05, + "loss": 3.3992, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043080184726699e-05, + "loss": 3.3953, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034710616019913e-05, + "loss": 3.3942, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026324668509393e-05, + "loss": 3.3905, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017938720998871e-05, + "loss": 3.3997, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009552773488351e-05, + "loss": 3.3867, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001183204781564e-05, + "loss": 3.391, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992797257271042e-05, + "loss": 3.3921, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984411309760522e-05, + "loss": 3.3977, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2976025362250002e-05, + "loss": 3.4057, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967655793543215e-05, + "loss": 3.4058, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959269846032693e-05, + "loss": 3.3837, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950883898522173e-05, + "loss": 3.3917, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942497951011653e-05, + "loss": 3.3961, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934128382304867e-05, + "loss": 3.3964, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925742434794343e-05, + "loss": 3.392, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917356487283825e-05, + "loss": 3.3944, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908970539773305e-05, + "loss": 3.3856, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900600971066514e-05, + "loss": 3.39, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892215023555996e-05, + "loss": 3.3934, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883829076045476e-05, + "loss": 3.3866, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875443128534956e-05, + "loss": 3.3891, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867073559828166e-05, + "loss": 3.3946, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858687612317646e-05, + "loss": 3.391, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850301664807126e-05, + "loss": 3.3888, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841915717296606e-05, + "loss": 3.3991, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833546148589817e-05, + "loss": 3.3829, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825160201079297e-05, + "loss": 3.3972, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816774253568779e-05, + "loss": 3.3945, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808388306058259e-05, + "loss": 3.3896, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800018737351468e-05, + "loss": 3.4023, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.279163278984095e-05, + "loss": 3.406, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.278324684233043e-05, + "loss": 3.3936, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.277486089481991e-05, + "loss": 3.3961, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.276649132611312e-05, + "loss": 3.3853, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.27581053786026e-05, + "loss": 3.393, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.274971943109208e-05, + "loss": 3.3902, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.274133348358156e-05, + "loss": 3.3842, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.273296391487477e-05, + "loss": 3.3936, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.272457796736425e-05, + "loss": 3.4009, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.271619201985373e-05, + "loss": 3.3948, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707806072343212e-05, + "loss": 3.3916, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699436503636421e-05, + "loss": 3.3841, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691050556125903e-05, + "loss": 3.3851, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682664608615383e-05, + "loss": 3.4001, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674278661104863e-05, + "loss": 3.3962, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665909092398074e-05, + "loss": 3.4081, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657523144887554e-05, + "loss": 3.3769, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649137197377034e-05, + "loss": 3.3953, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640751249866514e-05, + "loss": 3.3967, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632381681159724e-05, + "loss": 3.3956, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623995733649204e-05, + "loss": 3.3881, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615609786138684e-05, + "loss": 3.3886, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607223838628166e-05, + "loss": 3.4032, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598854269921375e-05, + "loss": 3.4085, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590468322410857e-05, + "loss": 3.3943, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582082374900337e-05, + "loss": 3.3951, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573696427389817e-05, + "loss": 3.3897, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565326858683027e-05, + "loss": 3.3963, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556940911172507e-05, + "loss": 3.3876, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548554963661987e-05, + "loss": 3.3994, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540185394955198e-05, + "loss": 3.3873, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531799447444678e-05, + "loss": 3.3944, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523413499934158e-05, + "loss": 3.3956, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.886136531829834, + "eval_runtime": 303.0361, + "eval_samples_per_second": 1259.226, + "eval_steps_per_second": 39.352, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2515027552423638e-05, + "loss": 3.3904, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506657983716849e-05, + "loss": 3.3846, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498272036206329e-05, + "loss": 3.3908, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489886088695809e-05, + "loss": 3.3997, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481500141185289e-05, + "loss": 3.3951, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.24731305724785e-05, + "loss": 3.4024, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464744624967981e-05, + "loss": 3.3866, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.245635867745746e-05, + "loss": 3.3991, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.244797272994694e-05, + "loss": 3.3866, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2439603161240152e-05, + "loss": 3.3901, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431217213729632e-05, + "loss": 3.3911, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.242283126621911e-05, + "loss": 3.395, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2414461697512323e-05, + "loss": 3.4045, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2406075750001803e-05, + "loss": 3.3833, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.239768980249128e-05, + "loss": 3.3731, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2389303854980762e-05, + "loss": 3.3843, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2380917907470242e-05, + "loss": 3.3862, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372531959959722e-05, + "loss": 3.3862, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364146012449202e-05, + "loss": 3.3865, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355760064938682e-05, + "loss": 3.3934, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347390496231893e-05, + "loss": 3.405, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2339004548721373e-05, + "loss": 3.3958, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330618601210853e-05, + "loss": 3.3979, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2322232653700333e-05, + "loss": 3.394, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313863084993545e-05, + "loss": 3.4036, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305477137483024e-05, + "loss": 3.3839, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297091189972504e-05, + "loss": 3.3889, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288705242461984e-05, + "loss": 3.3967, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2280335673755194e-05, + "loss": 3.3776, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2271949726244674e-05, + "loss": 3.3794, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263563778734154e-05, + "loss": 3.3842, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2255177831223636e-05, + "loss": 3.3925, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2246808262516845e-05, + "loss": 3.3985, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238422315006327e-05, + "loss": 3.3895, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2230036367495807e-05, + "loss": 3.3971, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221650419985285e-05, + "loss": 3.3837, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213280851278497e-05, + "loss": 3.3834, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204894903767977e-05, + "loss": 3.3797, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2196508956257457e-05, + "loss": 3.3947, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2188123008746937e-05, + "loss": 3.3801, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179753440040148e-05, + "loss": 3.3878, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171367492529628e-05, + "loss": 3.3886, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162981545019108e-05, + "loss": 3.4024, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154595597508588e-05, + "loss": 3.3851, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146226028801799e-05, + "loss": 3.3914, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.213784008129128e-05, + "loss": 3.3922, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129454133780759e-05, + "loss": 3.3817, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121068186270239e-05, + "loss": 3.388, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112698617563451e-05, + "loss": 3.3779, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104312670052931e-05, + "loss": 3.3857, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.209592672254241e-05, + "loss": 3.394, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.208754077503189e-05, + "loss": 3.3832, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079171206325102e-05, + "loss": 3.3824, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070785258814582e-05, + "loss": 3.3688, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062399311304062e-05, + "loss": 3.3824, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2054013363793542e-05, + "loss": 3.3652, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045643795086752e-05, + "loss": 3.4048, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037257847576232e-05, + "loss": 3.3791, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028871900065712e-05, + "loss": 3.3994, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020485952555192e-05, + "loss": 3.3804, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2012116383848405e-05, + "loss": 3.3693, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2003730436337883e-05, + "loss": 3.3822, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995344488827363e-05, + "loss": 3.3843, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986958541316843e-05, + "loss": 3.3783, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978588972610055e-05, + "loss": 3.3719, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970203025099534e-05, + "loss": 3.3953, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961817077589015e-05, + "loss": 3.3857, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953431130078495e-05, + "loss": 3.3727, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1945061561371704e-05, + "loss": 3.3698, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1936675613861186e-05, + "loss": 3.3774, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1928289666350666e-05, + "loss": 3.3808, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919903718840146e-05, + "loss": 3.391, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911534150133357e-05, + "loss": 3.3839, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1903148202622837e-05, + "loss": 3.3888, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1894762255112317e-05, + "loss": 3.3901, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1886376307601797e-05, + "loss": 3.3863, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1878006738895007e-05, + "loss": 3.3896, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869620791384487e-05, + "loss": 3.3777, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861234843873969e-05, + "loss": 3.388, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852865275167178e-05, + "loss": 3.385, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844479327656658e-05, + "loss": 3.3817, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.183609338014614e-05, + "loss": 3.3958, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.182770743263562e-05, + "loss": 3.3939, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.181933786392883e-05, + "loss": 3.3765, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.181095191641831e-05, + "loss": 3.3607, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.180256596890779e-05, + "loss": 3.3882, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794180021397269e-05, + "loss": 3.3825, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785810452690481e-05, + "loss": 3.3881, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777424505179961e-05, + "loss": 3.38, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1769038557669441e-05, + "loss": 3.3878, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760652610158921e-05, + "loss": 3.3812, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752283041452132e-05, + "loss": 3.3773, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743897093941612e-05, + "loss": 3.3811, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1735511146431093e-05, + "loss": 3.3863, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1727125198920572e-05, + "loss": 3.3967, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718755630213784e-05, + "loss": 3.3966, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710369682703264e-05, + "loss": 3.3744, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1701983735192742e-05, + "loss": 3.3844, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693597787682222e-05, + "loss": 3.3888, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1685228218975435e-05, + "loss": 3.3873, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1676842271464915e-05, + "loss": 3.3804, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668456323954393e-05, + "loss": 3.3859, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1660070376443875e-05, + "loss": 3.3782, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1651700807737085e-05, + "loss": 3.3777, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643314860226565e-05, + "loss": 3.3871, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1634928912716045e-05, + "loss": 3.3716, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626542965205525e-05, + "loss": 3.3783, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1618173396498738e-05, + "loss": 3.3902, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1609787448988216e-05, + "loss": 3.38, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1601401501477696e-05, + "loss": 3.3764, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1593015553967176e-05, + "loss": 3.3926, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1584645985260388e-05, + "loss": 3.3727, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1576260037749867e-05, + "loss": 3.3872, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567874090239347e-05, + "loss": 3.3847, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559488142728828e-05, + "loss": 3.3843, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1551118574022037e-05, + "loss": 3.3893, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542732626511519e-05, + "loss": 3.3935, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1534346679000999e-05, + "loss": 3.3856, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525960731490479e-05, + "loss": 3.3838, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.151759116278369e-05, + "loss": 3.378, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.150920521527317e-05, + "loss": 3.3871, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.150081926776265e-05, + "loss": 3.3784, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492433320252128e-05, + "loss": 3.3789, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.148406375154534e-05, + "loss": 3.3821, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.147567780403482e-05, + "loss": 3.3928, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.14672918565243e-05, + "loss": 3.3846, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.145890590901378e-05, + "loss": 3.3847, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450536340306991e-05, + "loss": 3.3774, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1442150392796473e-05, + "loss": 3.3755, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433764445285953e-05, + "loss": 3.3848, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425378497775431e-05, + "loss": 3.3891, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1417008929068643e-05, + "loss": 3.3948, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408622981558123e-05, + "loss": 3.3704, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400237034047602e-05, + "loss": 3.3878, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391851086537082e-05, + "loss": 3.3839, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383481517830294e-05, + "loss": 3.3866, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1375095570319774e-05, + "loss": 3.3749, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1366709622809254e-05, + "loss": 3.3824, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1358323675298734e-05, + "loss": 3.3921, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1349954106591945e-05, + "loss": 3.3979, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341568159081425e-05, + "loss": 3.384, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1333182211570905e-05, + "loss": 3.3845, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1324796264060385e-05, + "loss": 3.3827, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316426695353597e-05, + "loss": 3.3839, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1308040747843075e-05, + "loss": 3.3784, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1299654800332555e-05, + "loss": 3.3922, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1291268852822035e-05, + "loss": 3.3764, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1282899284115248e-05, + "loss": 3.3914, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1274513336604726e-05, + "loss": 3.3788, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.887615203857422, + "eval_runtime": 304.2288, + "eval_samples_per_second": 1254.29, + "eval_steps_per_second": 39.197, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1266127389094208e-05, + "loss": 3.366, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1257741441583688e-05, + "loss": 3.375, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1249355494073166e-05, + "loss": 3.3787, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1240969546562646e-05, + "loss": 3.3888, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1232599977855858e-05, + "loss": 3.386, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224214030345338e-05, + "loss": 3.3904, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1215828082834816e-05, + "loss": 3.3764, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207442135324298e-05, + "loss": 3.3913, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1199072566617509e-05, + "loss": 3.3741, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190686619106989e-05, + "loss": 3.3848, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1182300671596469e-05, + "loss": 3.3824, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1173914724085949e-05, + "loss": 3.387, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.116554515537916e-05, + "loss": 3.39, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1157175586672372e-05, + "loss": 3.3803, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.114878963916185e-05, + "loss": 3.3665, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1140403691651332e-05, + "loss": 3.374, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1132017744140812e-05, + "loss": 3.3705, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.112363179663029e-05, + "loss": 3.3757, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.111524584911977e-05, + "loss": 3.3817, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106859901609252e-05, + "loss": 3.3778, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098490332902463e-05, + "loss": 3.3977, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1090104385391943e-05, + "loss": 3.385, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081718437881422e-05, + "loss": 3.3887, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073332490370902e-05, + "loss": 3.3857, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064962921664113e-05, + "loss": 3.3958, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1056576974153593e-05, + "loss": 3.3709, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1048191026643073e-05, + "loss": 3.3823, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039805079132551e-05, + "loss": 3.3845, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031435510425764e-05, + "loss": 3.3735, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1023049562915244e-05, + "loss": 3.3659, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1014663615404724e-05, + "loss": 3.3738, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1006277667894204e-05, + "loss": 3.3859, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0997908099187415e-05, + "loss": 3.3867, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989522151676896e-05, + "loss": 3.3823, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0981136204166376e-05, + "loss": 3.3856, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0972750256655854e-05, + "loss": 3.3727, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0964380687949067e-05, + "loss": 3.372, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0955994740438547e-05, + "loss": 3.368, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0947608792928025e-05, + "loss": 3.385, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0939222845417505e-05, + "loss": 3.3691, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0930853276710718e-05, + "loss": 3.3801, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922467329200198e-05, + "loss": 3.376, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0914081381689677e-05, + "loss": 3.3938, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905695434179157e-05, + "loss": 3.3751, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0897325865472368e-05, + "loss": 3.3806, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0888939917961848e-05, + "loss": 3.3857, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0880553970451328e-05, + "loss": 3.3738, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0872168022940808e-05, + "loss": 3.3802, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.086379845423402e-05, + "loss": 3.3671, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855412506723499e-05, + "loss": 3.3776, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0847026559212979e-05, + "loss": 3.3787, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838640611702459e-05, + "loss": 3.3753, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830271042995671e-05, + "loss": 3.3757, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.082188509548515e-05, + "loss": 3.3575, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0813499147974631e-05, + "loss": 3.3738, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0805113200464111e-05, + "loss": 3.356, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0796743631757322e-05, + "loss": 3.3935, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0788357684246802e-05, + "loss": 3.3706, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0779971736736282e-05, + "loss": 3.3856, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771585789225762e-05, + "loss": 3.3776, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0763216220518973e-05, + "loss": 3.3628, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754830273008452e-05, + "loss": 3.3674, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746444325497932e-05, + "loss": 3.3741, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0738058377987412e-05, + "loss": 3.367, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729688809280623e-05, + "loss": 3.3596, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0721302861770103e-05, + "loss": 3.3848, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712916914259583e-05, + "loss": 3.3812, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704530966749063e-05, + "loss": 3.3643, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0696161398042274e-05, + "loss": 3.3577, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687775450531755e-05, + "loss": 3.3673, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0679389503021235e-05, + "loss": 3.3731, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0671003555510714e-05, + "loss": 3.3855, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0662633986803926e-05, + "loss": 3.3762, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0654248039293406e-05, + "loss": 3.3788, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0645862091782886e-05, + "loss": 3.3761, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0637476144272366e-05, + "loss": 3.3825, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0629106575565577e-05, + "loss": 3.3769, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0620720628055057e-05, + "loss": 3.3692, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0612334680544537e-05, + "loss": 3.3825, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0603948733034017e-05, + "loss": 3.3736, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595579164327228e-05, + "loss": 3.3748, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.058719321681671e-05, + "loss": 3.3859, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0578807269306187e-05, + "loss": 3.3828, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570437700599398e-05, + "loss": 3.3682, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.056205175308888e-05, + "loss": 3.3532, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.055366580557836e-05, + "loss": 3.3759, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545279858067838e-05, + "loss": 3.3755, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.053691028936105e-05, + "loss": 3.3746, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.052852434185053e-05, + "loss": 3.3735, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0520138394340009e-05, + "loss": 3.3778, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.051175244682949e-05, + "loss": 3.3733, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503382878122701e-05, + "loss": 3.3658, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0494996930612181e-05, + "loss": 3.373, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486610983101661e-05, + "loss": 3.3784, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478225035591141e-05, + "loss": 3.386, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469855466884352e-05, + "loss": 3.3831, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461469519373834e-05, + "loss": 3.3763, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0453083571863312e-05, + "loss": 3.3699, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444697624352792e-05, + "loss": 3.3775, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436328055646004e-05, + "loss": 3.3787, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427942108135482e-05, + "loss": 3.3743, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419556160624962e-05, + "loss": 3.3752, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411170213114444e-05, + "loss": 3.3706, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0402800644407655e-05, + "loss": 3.3656, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394414696897133e-05, + "loss": 3.381, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0386028749386615e-05, + "loss": 3.3596, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377642801876095e-05, + "loss": 3.3712, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369273233169306e-05, + "loss": 3.3789, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0360887285658786e-05, + "loss": 3.3738, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352501338148265e-05, + "loss": 3.366, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0344115390637745e-05, + "loss": 3.3787, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0335745821930956e-05, + "loss": 3.3694, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0327359874420436e-05, + "loss": 3.3757, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0318973926909916e-05, + "loss": 3.374, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0310587979399396e-05, + "loss": 3.3745, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302218410692607e-05, + "loss": 3.3797, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0293832463182087e-05, + "loss": 3.3854, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285446515671568e-05, + "loss": 3.3738, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0277060568161047e-05, + "loss": 3.3724, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.026869099945426e-05, + "loss": 3.3694, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.026030505194374e-05, + "loss": 3.3756, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0251919104433219e-05, + "loss": 3.3667, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0243533156922697e-05, + "loss": 3.3692, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.023516358821591e-05, + "loss": 3.3738, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.022677764070539e-05, + "loss": 3.3842, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.021839169319487e-05, + "loss": 3.3741, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.021000574568435e-05, + "loss": 3.3759, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.020163617697756e-05, + "loss": 3.3685, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.019325022946704e-05, + "loss": 3.3702, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.018486428195652e-05, + "loss": 3.3701, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0176478334446e-05, + "loss": 3.3837, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0168108765739213e-05, + "loss": 3.3834, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159722818228693e-05, + "loss": 3.3613, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0151336870718171e-05, + "loss": 3.3722, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0142950923207651e-05, + "loss": 3.3798, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0134581354500864e-05, + "loss": 3.375, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0126195406990342e-05, + "loss": 3.3688, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117809459479822e-05, + "loss": 3.3691, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0109423511969303e-05, + "loss": 3.384, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0101053943262514e-05, + "loss": 3.3882, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092667995751994e-05, + "loss": 3.3753, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0084282048241474e-05, + "loss": 3.3765, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075896100730954e-05, + "loss": 3.3731, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067526532024167e-05, + "loss": 3.3734, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0059140584513645e-05, + "loss": 3.3705, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0050754637003125e-05, + "loss": 3.3863, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042368689492605e-05, + "loss": 3.3654, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0033999120785816e-05, + "loss": 3.381, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025613173275295e-05, + "loss": 3.369, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0017227225764775e-05, + "loss": 3.3735, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.888455867767334, + "eval_runtime": 316.1667, + "eval_samples_per_second": 1206.93, + "eval_steps_per_second": 37.717, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0008841278254257e-05, + "loss": 3.3626, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000471709547466e-05, + "loss": 3.3699, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.992085762036948e-06, + "loss": 3.3826, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.983699814526428e-06, + "loss": 3.3716, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.975313867015906e-06, + "loss": 3.3861, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.966944298309119e-06, + "loss": 3.3658, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958558350798598e-06, + "loss": 3.3804, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.950172403288078e-06, + "loss": 3.3685, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.941786455777557e-06, + "loss": 3.3737, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.93341688707077e-06, + "loss": 3.3716, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.925030939560249e-06, + "loss": 3.3767, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.916644992049729e-06, + "loss": 3.3806, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.90827542334294e-06, + "loss": 3.3708, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.89988947583242e-06, + "loss": 3.3582, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.891503528321901e-06, + "loss": 3.3676, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.88311758081138e-06, + "loss": 3.3571, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.87473163330086e-06, + "loss": 3.3666, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.86634568579034e-06, + "loss": 3.3716, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.857959738279821e-06, + "loss": 3.3683, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.84959016957303e-06, + "loss": 3.3906, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.84120422206251e-06, + "loss": 3.3773, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.832818274551992e-06, + "loss": 3.3801, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.82443232704147e-06, + "loss": 3.3735, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.816062758334683e-06, + "loss": 3.3849, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.807676810824163e-06, + "loss": 3.3655, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.799290863313643e-06, + "loss": 3.3682, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.790904915803121e-06, + "loss": 3.3748, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.782535347096333e-06, + "loss": 3.3664, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.774149399585813e-06, + "loss": 3.3522, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.765763452075293e-06, + "loss": 3.3664, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.757377504564773e-06, + "loss": 3.3729, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.749007935857984e-06, + "loss": 3.3763, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.740621988347464e-06, + "loss": 3.3765, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.732236040836944e-06, + "loss": 3.3767, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.723850093326424e-06, + "loss": 3.3597, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.715480524619636e-06, + "loss": 3.3665, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.707094577109116e-06, + "loss": 3.3559, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.698708629598595e-06, + "loss": 3.376, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.690322682088075e-06, + "loss": 3.3626, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.681953113381287e-06, + "loss": 3.3691, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.673567165870765e-06, + "loss": 3.3664, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.665181218360245e-06, + "loss": 3.3802, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.656795270849727e-06, + "loss": 3.374, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648425702142938e-06, + "loss": 3.3683, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.640039754632418e-06, + "loss": 3.377, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.631653807121898e-06, + "loss": 3.3642, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.623267859611378e-06, + "loss": 3.3716, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.61489829090459e-06, + "loss": 3.3562, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606512343394068e-06, + "loss": 3.3641, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.598126395883548e-06, + "loss": 3.3742, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.589740448373028e-06, + "loss": 3.3634, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.581370879666239e-06, + "loss": 3.3669, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.572984932155719e-06, + "loss": 3.3516, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.564598984645199e-06, + "loss": 3.3656, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.55621303713468e-06, + "loss": 3.3473, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.54784346842789e-06, + "loss": 3.3825, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.539457520917371e-06, + "loss": 3.3612, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.531071573406851e-06, + "loss": 3.3763, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.52268562589633e-06, + "loss": 3.368, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.514316057189542e-06, + "loss": 3.3542, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.505930109679022e-06, + "loss": 3.3578, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.497544162168502e-06, + "loss": 3.3668, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.48915821465798e-06, + "loss": 3.3588, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.480788645951193e-06, + "loss": 3.3503, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472402698440673e-06, + "loss": 3.3766, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.464016750930153e-06, + "loss": 3.3697, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.455630803419633e-06, + "loss": 3.3546, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.447261234712843e-06, + "loss": 3.3522, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.438875287202325e-06, + "loss": 3.3572, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.430489339691803e-06, + "loss": 3.3652, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.422103392181283e-06, + "loss": 3.3711, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.413733823474496e-06, + "loss": 3.3672, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.405347875963976e-06, + "loss": 3.3704, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.396961928453454e-06, + "loss": 3.3691, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.388575980942934e-06, + "loss": 3.3735, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.380206412236146e-06, + "loss": 3.3633, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.371820464725626e-06, + "loss": 3.3637, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363434517215106e-06, + "loss": 3.3699, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.355048569704586e-06, + "loss": 3.364, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.346679000997797e-06, + "loss": 3.364, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.338293053487277e-06, + "loss": 3.373, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.329907105976757e-06, + "loss": 3.3783, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.321521158466237e-06, + "loss": 3.3591, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.31315158975945e-06, + "loss": 3.3469, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.304765642248928e-06, + "loss": 3.3633, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.296379694738408e-06, + "loss": 3.3667, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.28801012603162e-06, + "loss": 3.3671, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.2796241785211e-06, + "loss": 3.3625, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.271238231010578e-06, + "loss": 3.3688, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.26285228350006e-06, + "loss": 3.3636, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.25448271479327e-06, + "loss": 3.3566, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.246096767282749e-06, + "loss": 3.3639, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.23771081977223e-06, + "loss": 3.3655, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.22932487226171e-06, + "loss": 3.3775, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.220955303554921e-06, + "loss": 3.3746, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.212569356044401e-06, + "loss": 3.3714, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.204183408533881e-06, + "loss": 3.3543, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.195797461023361e-06, + "loss": 3.3695, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.187427892316574e-06, + "loss": 3.3659, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.179041944806052e-06, + "loss": 3.3678, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.170655997295532e-06, + "loss": 3.3638, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.162270049785014e-06, + "loss": 3.36, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.153900481078223e-06, + "loss": 3.3591, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.145514533567703e-06, + "loss": 3.3737, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.137128586057184e-06, + "loss": 3.3493, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.128742638546664e-06, + "loss": 3.364, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.120373069839875e-06, + "loss": 3.3686, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.111987122329355e-06, + "loss": 3.3613, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.103601174818835e-06, + "loss": 3.3568, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.095215227308313e-06, + "loss": 3.3706, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.086845658601526e-06, + "loss": 3.3574, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.078459711091006e-06, + "loss": 3.3677, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.070073763580486e-06, + "loss": 3.3676, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.061687816069966e-06, + "loss": 3.363, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053318247363176e-06, + "loss": 3.3679, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.044932299852656e-06, + "loss": 3.3784, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036546352342136e-06, + "loss": 3.364, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.028160404831616e-06, + "loss": 3.3623, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.019790836124827e-06, + "loss": 3.3621, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011404888614309e-06, + "loss": 3.3637, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.003018941103787e-06, + "loss": 3.3614, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.994632993593267e-06, + "loss": 3.356, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.98626342488648e-06, + "loss": 3.364, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.97787747737596e-06, + "loss": 3.3742, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.969491529865438e-06, + "loss": 3.3668, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.96110558235492e-06, + "loss": 3.365, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.95273601364813e-06, + "loss": 3.3593, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.94435006613761e-06, + "loss": 3.3586, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.93596411862709e-06, + "loss": 3.3621, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.92757817111657e-06, + "loss": 3.377, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.91920860240978e-06, + "loss": 3.3749, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.91082265489926e-06, + "loss": 3.3552, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.90243670738874e-06, + "loss": 3.3608, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.89405075987822e-06, + "loss": 3.3688, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.885681191171433e-06, + "loss": 3.3611, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.877295243660911e-06, + "loss": 3.3683, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.868909296150391e-06, + "loss": 3.3576, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.860523348639873e-06, + "loss": 3.3741, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.852153779933082e-06, + "loss": 3.374, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.843767832422564e-06, + "loss": 3.3673, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.835381884912044e-06, + "loss": 3.3681, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.826995937401524e-06, + "loss": 3.3662, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.818626368694734e-06, + "loss": 3.3622, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.810240421184214e-06, + "loss": 3.3616, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.801854473673694e-06, + "loss": 3.3774, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.793468526163173e-06, + "loss": 3.3566, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.785098957456385e-06, + "loss": 3.369, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.776713009945865e-06, + "loss": 3.3637, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.768327062435345e-06, + "loss": 3.3616, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.8882076740264893, + "eval_runtime": 316.9586, + "eval_samples_per_second": 1203.914, + "eval_steps_per_second": 37.623, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.759941114924825e-06, + "loss": 3.3514, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.751555167414305e-06, + "loss": 3.3621, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.743169219903785e-06, + "loss": 3.3743, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.734783272393265e-06, + "loss": 3.3593, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.726413703686476e-06, + "loss": 3.3767, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.718027756175956e-06, + "loss": 3.3542, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.709641808665435e-06, + "loss": 3.3722, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.701272239958646e-06, + "loss": 3.36, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.692886292448126e-06, + "loss": 3.3632, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.684500344937608e-06, + "loss": 3.3652, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.676114397427088e-06, + "loss": 3.3642, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.667744828720299e-06, + "loss": 3.3713, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.65937526001351e-06, + "loss": 3.3602, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.65098931250299e-06, + "loss": 3.3526, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.64260336499247e-06, + "loss": 3.3569, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.63421741748195e-06, + "loss": 3.3546, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.62583146997143e-06, + "loss": 3.3535, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.61744552246091e-06, + "loss": 3.3625, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.609059574950389e-06, + "loss": 3.3586, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.600673627439869e-06, + "loss": 3.3844, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.59230405873308e-06, + "loss": 3.3673, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.583918111222562e-06, + "loss": 3.3695, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.57553216371204e-06, + "loss": 3.365, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.56716259500525e-06, + "loss": 3.3713, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.558776647494732e-06, + "loss": 3.3586, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.55039069998421e-06, + "loss": 3.3629, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.54200475247369e-06, + "loss": 3.3633, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.533635183766903e-06, + "loss": 3.3598, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.525249236256383e-06, + "loss": 3.3438, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.516863288745861e-06, + "loss": 3.3602, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.508477341235343e-06, + "loss": 3.3621, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.500107772528554e-06, + "loss": 3.3683, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.491721825018034e-06, + "loss": 3.3683, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.483335877507514e-06, + "loss": 3.3643, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.474949929996993e-06, + "loss": 3.3535, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.466580361290204e-06, + "loss": 3.358, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.458194413779684e-06, + "loss": 3.3487, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.449808466269164e-06, + "loss": 3.3646, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.441422518758644e-06, + "loss": 3.3548, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.433052950051857e-06, + "loss": 3.356, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.424667002541335e-06, + "loss": 3.3574, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.416281055030815e-06, + "loss": 3.3681, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.407895107520296e-06, + "loss": 3.3628, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.399525538813506e-06, + "loss": 3.3609, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.391139591302986e-06, + "loss": 3.3705, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.382753643792467e-06, + "loss": 3.3551, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.374367696281947e-06, + "loss": 3.3591, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.365998127575158e-06, + "loss": 3.3511, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.357612180064638e-06, + "loss": 3.3543, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.349226232554118e-06, + "loss": 3.3639, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.340840285043596e-06, + "loss": 3.3538, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.332470716336809e-06, + "loss": 3.354, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.324084768826289e-06, + "loss": 3.3472, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.315698821315769e-06, + "loss": 3.3544, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.307312873805248e-06, + "loss": 3.3393, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.29894330509846e-06, + "loss": 3.3692, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.29055735758794e-06, + "loss": 3.3539, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.282171410077421e-06, + "loss": 3.3604, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.273785462566899e-06, + "loss": 3.3612, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.265415893860112e-06, + "loss": 3.3484, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.257029946349592e-06, + "loss": 3.3466, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.24864399883907e-06, + "loss": 3.3563, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.24025805132855e-06, + "loss": 3.3486, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.231888482621762e-06, + "loss": 3.3451, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.223502535111242e-06, + "loss": 3.3627, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.215116587600722e-06, + "loss": 3.3632, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.206730640090202e-06, + "loss": 3.3455, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.198361071383413e-06, + "loss": 3.3438, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.189975123872893e-06, + "loss": 3.3466, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.181589176362373e-06, + "loss": 3.3571, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.173203228851853e-06, + "loss": 3.3569, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.164833660145065e-06, + "loss": 3.3576, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.156447712634544e-06, + "loss": 3.3625, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.148061765124023e-06, + "loss": 3.3594, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.139675817613503e-06, + "loss": 3.3675, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.131306248906716e-06, + "loss": 3.3511, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.122920301396194e-06, + "loss": 3.3561, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.114534353885674e-06, + "loss": 3.3611, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.106148406375156e-06, + "loss": 3.3523, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.097778837668367e-06, + "loss": 3.3608, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.089392890157847e-06, + "loss": 3.3626, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.081006942647326e-06, + "loss": 3.369, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.072620995136806e-06, + "loss": 3.3457, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.064251426430017e-06, + "loss": 3.3403, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.055865478919497e-06, + "loss": 3.3527, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.047479531408977e-06, + "loss": 3.3601, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.03910996270219e-06, + "loss": 3.3622, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.030724015191668e-06, + "loss": 3.351, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.022338067681148e-06, + "loss": 3.3536, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.013952120170628e-06, + "loss": 3.354, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.00558255146384e-06, + "loss": 3.3468, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.997196603953319e-06, + "loss": 3.3521, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.9888106564428e-06, + "loss": 3.3563, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.98042470893228e-06, + "loss": 3.3665, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.97205514022549e-06, + "loss": 3.3658, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.963669192714971e-06, + "loss": 3.3614, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.955283245204451e-06, + "loss": 3.3491, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.94689729769393e-06, + "loss": 3.3603, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.938527728987142e-06, + "loss": 3.3535, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.930141781476622e-06, + "loss": 3.3635, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.921755833966102e-06, + "loss": 3.3528, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.913369886455581e-06, + "loss": 3.3485, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.905000317748792e-06, + "loss": 3.3487, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.896614370238272e-06, + "loss": 3.366, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.888228422727754e-06, + "loss": 3.3409, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.879842475217232e-06, + "loss": 3.3586, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.871472906510443e-06, + "loss": 3.3576, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.863086958999925e-06, + "loss": 3.3501, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.854701011489405e-06, + "loss": 3.3479, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.846315063978883e-06, + "loss": 3.3652, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.837945495272095e-06, + "loss": 3.3475, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.829559547761575e-06, + "loss": 3.3538, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.821173600251053e-06, + "loss": 3.3604, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.812787652740535e-06, + "loss": 3.3526, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.804418084033746e-06, + "loss": 3.361, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.796032136523226e-06, + "loss": 3.3691, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.787646189012706e-06, + "loss": 3.3559, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.779260241502186e-06, + "loss": 3.3565, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.770890672795397e-06, + "loss": 3.356, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.762504725284877e-06, + "loss": 3.3524, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.754118777774357e-06, + "loss": 3.3495, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.745732830263836e-06, + "loss": 3.3473, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.737363261557049e-06, + "loss": 3.3525, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.728977314046527e-06, + "loss": 3.3678, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.720591366536007e-06, + "loss": 3.3566, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.712205419025489e-06, + "loss": 3.3574, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.7038358503187e-06, + "loss": 3.3503, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.695449902808178e-06, + "loss": 3.3466, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.68706395529766e-06, + "loss": 3.3497, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.67867800778714e-06, + "loss": 3.3685, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.67030843908035e-06, + "loss": 3.3659, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.66192249156983e-06, + "loss": 3.3459, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.65353654405931e-06, + "loss": 3.3496, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.64515059654879e-06, + "loss": 3.3596, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.636781027842001e-06, + "loss": 3.3518, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.628395080331481e-06, + "loss": 3.3611, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.620009132820962e-06, + "loss": 3.3492, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.61162318531044e-06, + "loss": 3.3626, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.603253616603652e-06, + "loss": 3.3651, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.594867669093132e-06, + "loss": 3.358, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.586481721582612e-06, + "loss": 3.3585, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.5780957740720914e-06, + "loss": 3.3587, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.569726205365303e-06, + "loss": 3.3533, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.561340257854783e-06, + "loss": 3.3512, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.552954310344264e-06, + "loss": 3.3666, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.544568362833743e-06, + "loss": 3.3496, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.536198794126955e-06, + "loss": 3.361, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.5278128466164345e-06, + "loss": 3.3552, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.519426899105914e-06, + "loss": 3.3489, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.8890140056610107, + "eval_runtime": 310.678, + "eval_samples_per_second": 1228.252, + "eval_steps_per_second": 38.384, + "step": 2594880 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.7961572426395853e+18, + "trial_name": null, + "trial_params": null +}