diff --git "a/checkpoint-2823840/trainer_state.json" "b/checkpoint-2823840/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2823840/trainer_state.json" @@ -0,0 +1,33411 @@ +{ + "best_metric": 3.8492636680603027, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/1/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2823840, + "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": 10.9931, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8206, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.2067, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.0045, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8356, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7277, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6144, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5429, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4633, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4028, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.364, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.316, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.269, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.2209, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.1951, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.1482, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1226, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0968, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.064, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0333, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0177, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.986, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9694, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9416, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9363, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.901, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8872, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8597, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8517, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8274, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8213, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.8086, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7926, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7812, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7671, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970659010995419e-05, + "loss": 4.7526, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7505, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7196, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7092, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6879, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6908, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6757, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6789, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 4.6558, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6507, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6451, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6392, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6264, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6105, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.6, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6196, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.6088, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5851, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5728, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5805, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5585, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5683, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5391, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5604, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5444, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5224, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5168, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.53, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.4904, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5044, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5108, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.495, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4886, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.471, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4701, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4657, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.483, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.458, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.468, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4616, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4608, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4439, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4426, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4391, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.435, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4266, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4196, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4218, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4218, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4004, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.4067, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4066, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.4098, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3933, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3914, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3841, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3783, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3791, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3816, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3752, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3825, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3724, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3567, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3554, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3648, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3604, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3596, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3484, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3395, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3523, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3292, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3351, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3313, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3313, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.321, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3209, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.315, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.322, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3163, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3067, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3196, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.323, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.3104, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.2994, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.2952, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.2948, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.3004, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.2969, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2846, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2939, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2869, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2863, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2799, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2802, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2728, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2827, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2813, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2799, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2573, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2724, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2666, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2693, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2594, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2672, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2572, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2737, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2439, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2614, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2468, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2432, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2471, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2341, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2379, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2444, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2329, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.200936317443848, + "eval_runtime": 303.3774, + "eval_samples_per_second": 1257.81, + "eval_steps_per_second": 39.307, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2284, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2245, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2383, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2284, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2377, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2149, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2172, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.2077, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2168, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2138, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2097, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2144, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1946, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.2068, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1924, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.193, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1975, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.1908, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1948, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.2094, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.1843, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1883, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1875, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1935, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.1843, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1848, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1704, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1762, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1656, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.175, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.1702, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1736, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1779, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1655, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1719, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1682, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1574, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1509, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.1432, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.1506, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.1483, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.1594, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.1446, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.1449, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.1496, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.1418, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.1443, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.1306, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.1282, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.152, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.1481, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.131, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.1331, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.1391, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.1196, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.1384, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.1138, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.1401, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.1346, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.1165, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823958979613631e-05, + "loss": 4.1145, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823120384862579e-05, + "loss": 4.1289, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.0973, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821443195360475e-05, + "loss": 4.1129, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820606238489796e-05, + "loss": 4.1245, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819767643738744e-05, + "loss": 4.1161, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818929048987692e-05, + "loss": 4.1088, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.0975, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.1041, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.1054, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.1117, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.1015, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.1116, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130621614910745e-05, + "loss": 4.1126, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122235667400224e-05, + "loss": 4.1107, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.0946, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.1032, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097094203672393e-05, + "loss": 4.1025, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088708256161873e-05, + "loss": 4.0981, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.0955, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.0918, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806356679243404e-05, + "loss": 4.1002, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805518084492352e-05, + "loss": 4.095, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046794897413e-05, + "loss": 4.0801, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.0878, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.80300393811957e-05, + "loss": 4.0892, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802165343368518e-05, + "loss": 4.0959, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801326748617466e-05, + "loss": 4.0873, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800488153866413e-05, + "loss": 4.0824, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799649559115361e-05, + "loss": 4.0816, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798812602244683e-05, + "loss": 4.0728, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.79797400749363e-05, + "loss": 4.0769, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797135412742578e-05, + "loss": 4.0861, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796296817991526e-05, + "loss": 4.0831, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954598611208476e-05, + "loss": 4.0915, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946212663697956e-05, + "loss": 4.081, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937826716187436e-05, + "loss": 4.0724, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929440768676916e-05, + "loss": 4.071, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921054821166396e-05, + "loss": 4.0783, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912685252459605e-05, + "loss": 4.0827, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904299304949085e-05, + "loss": 4.082, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895913357438565e-05, + "loss": 4.0721, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887527409928045e-05, + "loss": 4.0617, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.0815, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.0601, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.0673, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785401637749343e-05, + "loss": 4.0671, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784563042998291e-05, + "loss": 4.0657, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783724448247239e-05, + "loss": 4.0545, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782885853496187e-05, + "loss": 4.0638, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782047258745135e-05, + "loss": 4.0539, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781208663994083e-05, + "loss": 4.0633, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780370069243031e-05, + "loss": 4.0609, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779531474491979e-05, + "loss": 4.0529, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786945176213e-05, + "loss": 4.0737, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777855922870248e-05, + "loss": 4.072, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777017328119196e-05, + "loss": 4.064, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776178733368144e-05, + "loss": 4.0552, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775340138617092e-05, + "loss": 4.0483, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7745031817464134e-05, + "loss": 4.0548, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736645869953614e-05, + "loss": 4.0513, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728259922443094e-05, + "loss": 4.061, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719873974932574e-05, + "loss": 4.043, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.0527, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770311845871526e-05, + "loss": 4.0543, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769473251120474e-05, + "loss": 4.0552, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768634656369422e-05, + "loss": 4.0429, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767797699498743e-05, + "loss": 4.0489, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766959104747691e-05, + "loss": 4.0479, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766120509996639e-05, + "loss": 4.0496, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765281915245587e-05, + "loss": 4.0541, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0545, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763606363623857e-05, + "loss": 4.0322, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762767768872805e-05, + "loss": 4.0452, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.0486, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.0459, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760253622500022e-05, + "loss": 4.0417, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941502774897e-05, + "loss": 4.0482, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758576432997918e-05, + "loss": 4.0414, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757737838246866e-05, + "loss": 4.0585, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7568992434958137e-05, + "loss": 4.0316, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560622866251346e-05, + "loss": 4.0462, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552236918740826e-05, + "loss": 4.0367, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543850971230306e-05, + "loss": 4.0306, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753548140252352e-05, + "loss": 4.0378, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527095455013e-05, + "loss": 4.0289, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751870950750248e-05, + "loss": 4.0302, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751032355999196e-05, + "loss": 4.0317, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501937612481435e-05, + "loss": 4.0289, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.030747413635254, + "eval_runtime": 317.6174, + "eval_samples_per_second": 1201.417, + "eval_steps_per_second": 37.545, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493551664970914e-05, + "loss": 4.0236, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485165717460394e-05, + "loss": 4.0207, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476779769949874e-05, + "loss": 4.0383, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468393822439354e-05, + "loss": 4.0271, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460007874928834e-05, + "loss": 4.0439, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451621927418314e-05, + "loss": 4.0167, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443235979907794e-05, + "loss": 4.0239, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434850032397274e-05, + "loss": 4.0108, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426464084886754e-05, + "loss": 4.0255, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418078137376234e-05, + "loss": 4.0209, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740969218986572e-05, + "loss": 4.0158, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740132262115893e-05, + "loss": 4.0285, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 4.0052, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 4.022, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 4.0038, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 4.0067, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735940926241006e-05, + "loss": 4.005, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735102331489954e-05, + "loss": 4.0143, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734263736738902e-05, + "loss": 4.0088, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.73342514198785e-05, + "loss": 4.0286, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732588185117171e-05, + "loss": 4.0062, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731749590366119e-05, + "loss": 4.0108, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309109956150674e-05, + "loss": 4.0087, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300724008640154e-05, + "loss": 4.0156, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292354439933364e-05, + "loss": 4.0045, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283968492422844e-05, + "loss": 4.0103, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275582544912323e-05, + "loss": 3.9977, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.72671965974018e-05, + "loss": 4.0036, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725882702869501e-05, + "loss": 3.991, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725044108118449e-05, + "loss": 4.0048, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724205513367397e-05, + "loss": 4.0034, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723368556496718e-05, + "loss": 4.0037, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722529961745666e-05, + "loss": 4.0112, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721691366994614e-05, + "loss": 3.9987, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9976, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720015815372884e-05, + "loss": 4.0052, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719177220621832e-05, + "loss": 3.9932, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833862587078e-05, + "loss": 3.9868, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717500031119727e-05, + "loss": 3.9785, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716661436368675e-05, + "loss": 3.9864, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715822841617623e-05, + "loss": 3.987, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714984246866571e-05, + "loss": 3.9975, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714147289995892e-05, + "loss": 3.9872, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71330869524484e-05, + "loss": 3.9797, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712470100493788e-05, + "loss": 3.9943, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116315057427366e-05, + "loss": 3.9865, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107945488720575e-05, + "loss": 3.9843, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099559541210055e-05, + "loss": 3.9756, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091173593699535e-05, + "loss": 3.9697, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082787646189015e-05, + "loss": 3.996, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074418077482224e-05, + "loss": 3.9941, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7066032129971704e-05, + "loss": 3.9787, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057646182461184e-05, + "loss": 3.9796, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704927661375439e-05, + "loss": 3.9874, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704089066624387e-05, + "loss": 3.9647, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703250471873335e-05, + "loss": 3.9848, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702411877122283e-05, + "loss": 3.9652, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701573282371232e-05, + "loss": 3.9849, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.70073468762018e-05, + "loss": 3.9901, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699896092869128e-05, + "loss": 3.9705, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699059135998449e-05, + "loss": 3.9634, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698220541247397e-05, + "loss": 3.9835, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697381946496345e-05, + "loss": 3.9542, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696543351745293e-05, + "loss": 3.9682, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695706394874614e-05, + "loss": 3.9779, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694867800123562e-05, + "loss": 3.9753, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.69402920537251e-05, + "loss": 3.9671, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693190610621458e-05, + "loss": 3.9555, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692355291631152e-05, + "loss": 3.9593, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.9619, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.9722, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689839507377996e-05, + "loss": 3.9602, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689000912626944e-05, + "loss": 3.9732, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688162317875892e-05, + "loss": 3.9726, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.68732372312484e-05, + "loss": 3.9722, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686485128373788e-05, + "loss": 3.9563, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685648171503109e-05, + "loss": 3.9632, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684809576752057e-05, + "loss": 3.9677, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683970982001005e-05, + "loss": 3.9595, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683132387249953e-05, + "loss": 3.9614, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682295430379274e-05, + "loss": 3.9611, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681456835628222e-05, + "loss": 3.9591, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680618240877171e-05, + "loss": 3.9637, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679779646126119e-05, + "loss": 3.9452, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.9573, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781040945043876e-05, + "loss": 3.9553, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772654997533356e-05, + "loss": 3.9647, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764269050022836e-05, + "loss": 3.9546, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755899481316045e-05, + "loss": 3.9523, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9498, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.9457, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730741638784485e-05, + "loss": 3.9438, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9537, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.963, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670560017505666e-05, + "loss": 3.9611, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.953, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9447, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9478, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9482, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.9573, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9552, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664691492128675e-05, + "loss": 3.9473, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663852897377623e-05, + "loss": 3.9376, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9587, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9363, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9467, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660500156253788e-05, + "loss": 3.9397, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9446, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.9359, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657987647761378e-05, + "loss": 3.9447, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.936, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656310458259274e-05, + "loss": 3.9367, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655471863508222e-05, + "loss": 3.9474, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.9315, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.9549, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.9524, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652119122384387e-05, + "loss": 3.9445, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651280527633335e-05, + "loss": 3.9369, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650441932882283e-05, + "loss": 3.9336, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649603338131231e-05, + "loss": 3.9352, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648766381260553e-05, + "loss": 3.9354, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479277865095e-05, + "loss": 3.9426, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647089191758448e-05, + "loss": 3.9261, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646250597007396e-05, + "loss": 3.9374, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645413640136718e-05, + "loss": 3.9411, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9379, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643736450634613e-05, + "loss": 3.9298, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642897855883561e-05, + "loss": 3.9321, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642060899012882e-05, + "loss": 3.9357, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9365, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403837095107786e-05, + "loss": 3.938, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395451147597266e-05, + "loss": 3.9427, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.9188, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378695631379955e-05, + "loss": 3.9358, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9372, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.9319, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9297, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9416, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633679865143482e-05, + "loss": 3.9316, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632841270392429e-05, + "loss": 3.9469, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632002675641377e-05, + "loss": 3.9236, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.9321, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9288, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9222, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628649934517543e-05, + "loss": 3.9267, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627811339766491e-05, + "loss": 3.922, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626972745015439e-05, + "loss": 3.9201, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9239, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9231, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9575917720794678, + "eval_runtime": 314.063, + "eval_samples_per_second": 1215.014, + "eval_steps_per_second": 37.97, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.9228, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623618366011231e-05, + "loss": 3.9151, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622781409140552e-05, + "loss": 3.9298, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9221, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9399, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.9147, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.9202, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.9068, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.9216, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9181, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616075926892882e-05, + "loss": 3.9119, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9192, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614400375271151e-05, + "loss": 3.9072, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613561780520099e-05, + "loss": 3.921, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612723185769047e-05, + "loss": 3.9053, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.9044, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.905, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.9112, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.9075, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.9276, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.9086, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9177, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060177035213776e-05, + "loss": 3.9075, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051791087703256e-05, + "loss": 3.914, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043405140192735e-05, + "loss": 3.9064, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035019192682215e-05, + "loss": 3.9112, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026633245171695e-05, + "loss": 3.9041, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.9008, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009861350150655e-05, + "loss": 3.8976, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001491781443864e-05, + "loss": 3.9059, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993105833933344e-05, + "loss": 3.9092, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598471988642283e-05, + "loss": 3.9063, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.9164, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.9058, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595959480149873e-05, + "loss": 3.9005, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595120885398821e-05, + "loss": 3.9064, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.9055, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.8898, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592605101145665e-05, + "loss": 3.8859, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591768144274986e-05, + "loss": 3.8902, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590929549523934e-05, + "loss": 3.898, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.9028, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.58925236002183e-05, + "loss": 3.8989, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884137652707785e-05, + "loss": 3.8852, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587575170519726e-05, + "loss": 3.9008, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586736575768674e-05, + "loss": 3.8954, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585897981017622e-05, + "loss": 3.8932, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585061024146943e-05, + "loss": 3.8831, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584222429395891e-05, + "loss": 3.8722, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583383834644839e-05, + "loss": 3.9127, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582545239893787e-05, + "loss": 3.8991, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817082830231076e-05, + "loss": 3.8909, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808696882720556e-05, + "loss": 3.8924, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580032731401377e-05, + "loss": 3.8925, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579194136650325e-05, + "loss": 3.8765, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578355541899273e-05, + "loss": 3.8941, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577516947148221e-05, + "loss": 3.8809, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576678352397169e-05, + "loss": 3.8902, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575839757646117e-05, + "loss": 3.9042, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575001162895065e-05, + "loss": 3.8822, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574162568144013e-05, + "loss": 3.8724, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573325611273334e-05, + "loss": 3.9005, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572487016522282e-05, + "loss": 3.8671, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.57164842177123e-05, + "loss": 3.8764, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570811464900551e-05, + "loss": 3.8939, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569972870149499e-05, + "loss": 3.8871, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691342753984476e-05, + "loss": 3.8798, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682973185277685e-05, + "loss": 3.8737, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674587237767165e-05, + "loss": 3.8682, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666201290256645e-05, + "loss": 3.8745, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657815342746125e-05, + "loss": 3.8885, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649429395235605e-05, + "loss": 3.8708, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641043447725085e-05, + "loss": 3.8905, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632673879018294e-05, + "loss": 3.8834, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624287931507774e-05, + "loss": 3.8909, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615901983997254e-05, + "loss": 3.8741, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607516036486734e-05, + "loss": 3.8738, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599130088976214e-05, + "loss": 3.8831, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590744141465694e-05, + "loss": 3.8721, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558237457275891e-05, + "loss": 3.8838, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557398862524839e-05, + "loss": 3.8749, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556560267773787e-05, + "loss": 3.8748, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555721673022735e-05, + "loss": 3.8784, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554883078271683e-05, + "loss": 3.8641, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554044483520631e-05, + "loss": 3.8723, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553205888769579e-05, + "loss": 3.8738, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552367294018526e-05, + "loss": 3.8815, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551530337147848e-05, + "loss": 3.8698, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550691742396796e-05, + "loss": 3.8726, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549853147645744e-05, + "loss": 3.8682, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549014552894691e-05, + "loss": 3.8626, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548175958143639e-05, + "loss": 3.8632, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547337363392588e-05, + "loss": 3.8706, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546498768641536e-05, + "loss": 3.8803, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545660173890484e-05, + "loss": 3.8838, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544823217019805e-05, + "loss": 3.8735, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543984622268753e-05, + "loss": 3.861, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543146027517701e-05, + "loss": 3.8659, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423090706470216e-05, + "loss": 3.8706, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414704758959696e-05, + "loss": 3.8765, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406318811449176e-05, + "loss": 3.8757, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397932863938656e-05, + "loss": 3.8704, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389546916428136e-05, + "loss": 3.8585, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381177347721345e-05, + "loss": 3.8828, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537279140021083e-05, + "loss": 3.8539, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536440545270031e-05, + "loss": 3.871, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535601950518979e-05, + "loss": 3.8599, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534763355767927e-05, + "loss": 3.8679, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533926398897248e-05, + "loss": 3.8579, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533087804146196e-05, + "loss": 3.8651, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532249209395144e-05, + "loss": 3.8592, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531410614644092e-05, + "loss": 3.8593, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.53057201989304e-05, + "loss": 3.8671, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529733425141988e-05, + "loss": 3.8571, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528896468271309e-05, + "loss": 3.8744, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528057873520257e-05, + "loss": 3.8761, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527219278769205e-05, + "loss": 3.8703, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526380684018153e-05, + "loss": 3.8587, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255420892671017e-05, + "loss": 3.8597, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247034945160496e-05, + "loss": 3.8575, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238648997649976e-05, + "loss": 3.8583, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523026305013945e-05, + "loss": 3.8683, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221893481432665e-05, + "loss": 3.845, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213507533922145e-05, + "loss": 3.8636, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205121586411625e-05, + "loss": 3.8611, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.51967356389011e-05, + "loss": 3.8667, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188366070194314e-05, + "loss": 3.8536, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8582, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171610553977003e-05, + "loss": 3.8549, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163224606466483e-05, + "loss": 3.8685, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515483865895597e-05, + "loss": 3.859, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514645271144545e-05, + "loss": 3.8704, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513808314273866e-05, + "loss": 3.8451, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512969719522814e-05, + "loss": 3.8616, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512131124771762e-05, + "loss": 3.8634, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.51129253002071e-05, + "loss": 3.855, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510455573150031e-05, + "loss": 3.8563, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509616978398979e-05, + "loss": 3.8665, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508778383647927e-05, + "loss": 3.8614, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507939788896874e-05, + "loss": 3.8753, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507102832026196e-05, + "loss": 3.8487, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506264237275144e-05, + "loss": 3.8618, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054256425240924e-05, + "loss": 3.852, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.50458704777304e-05, + "loss": 3.8532, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503748453021988e-05, + "loss": 3.8576, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502911496151309e-05, + "loss": 3.8503, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502072901400257e-05, + "loss": 3.8487, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012343066492046e-05, + "loss": 3.8482, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5003957118981526e-05, + "loss": 3.8535, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9170939922332764, + "eval_runtime": 317.3907, + "eval_samples_per_second": 1202.275, + "eval_steps_per_second": 37.572, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995571171471006e-05, + "loss": 3.8477, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987185223960486e-05, + "loss": 3.8429, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978799276449966e-05, + "loss": 3.8618, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970413328939446e-05, + "loss": 3.851, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962027381428926e-05, + "loss": 3.8663, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953641433918406e-05, + "loss": 3.8479, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945255486407886e-05, + "loss": 3.8482, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493686953889737e-05, + "loss": 3.8356, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492849997019058e-05, + "loss": 3.8504, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492011402268006e-05, + "loss": 3.8477, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491172807516954e-05, + "loss": 3.8462, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490334212765902e-05, + "loss": 3.8461, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489497255895223e-05, + "loss": 3.8373, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488658661144171e-05, + "loss": 3.8526, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487820066393119e-05, + "loss": 3.8354, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486981471642067e-05, + "loss": 3.8349, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486142876891015e-05, + "loss": 3.8358, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485304282139963e-05, + "loss": 3.8464, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484465687388911e-05, + "loss": 3.8378, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483627092637859e-05, + "loss": 3.8572, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482788497886807e-05, + "loss": 3.8415, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481949903135755e-05, + "loss": 3.8499, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481112946265076e-05, + "loss": 3.8395, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480274351514024e-05, + "loss": 3.8417, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479435756762972e-05, + "loss": 3.8392, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.47859716201192e-05, + "loss": 3.8444, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477758567260868e-05, + "loss": 3.8362, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476919972509816e-05, + "loss": 3.8379, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476081377758764e-05, + "loss": 3.8296, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475244420888085e-05, + "loss": 3.8379, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474405826137033e-05, + "loss": 3.8439, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473567231385981e-05, + "loss": 3.8419, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727286366349295e-05, + "loss": 3.8463, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718900418838775e-05, + "loss": 3.836, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710514471328255e-05, + "loss": 3.8366, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702144902621464e-05, + "loss": 3.8454, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693758955110944e-05, + "loss": 3.8418, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685373007600424e-05, + "loss": 3.8195, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4676987060089903e-05, + "loss": 3.8259, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466861749138311e-05, + "loss": 3.8237, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466023154387259e-05, + "loss": 3.8283, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465184559636207e-05, + "loss": 3.8407, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464345964885155e-05, + "loss": 3.8305, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463507370134103e-05, + "loss": 3.8262, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462670413263425e-05, + "loss": 3.8335, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461831818512373e-05, + "loss": 3.8268, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460993223761321e-05, + "loss": 3.8316, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460154629010269e-05, + "loss": 3.8215, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459316034259217e-05, + "loss": 3.8017, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458477439508165e-05, + "loss": 3.8499, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457638844757112e-05, + "loss": 3.8353, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.45680025000606e-05, + "loss": 3.8325, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455963293135382e-05, + "loss": 3.827, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551263362647026e-05, + "loss": 3.8276, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542877415136506e-05, + "loss": 3.8155, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534491467625986e-05, + "loss": 3.8281, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526105520115466e-05, + "loss": 3.8218, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451773595140868e-05, + "loss": 3.8242, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450935000389816e-05, + "loss": 3.8401, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450096405638764e-05, + "loss": 3.8177, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449257810887712e-05, + "loss": 3.8133, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448420854017033e-05, + "loss": 3.8366, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447582259265981e-05, + "loss": 3.806, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446743664514929e-05, + "loss": 3.8164, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459050697638764e-05, + "loss": 3.8284, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445068112893198e-05, + "loss": 3.8251, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444229518142146e-05, + "loss": 3.8167, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443390923391094e-05, + "loss": 3.8144, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442552328640042e-05, + "loss": 3.8041, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.44171373388899e-05, + "loss": 3.8131, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440875139137938e-05, + "loss": 3.8246, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400381822672595e-05, + "loss": 3.8135, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439199587516207e-05, + "loss": 3.8237, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438360992765155e-05, + "loss": 3.8243, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437522398014103e-05, + "loss": 3.8312, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436683803263051e-05, + "loss": 3.8134, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435846846392372e-05, + "loss": 3.8104, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.43500825164132e-05, + "loss": 3.8221, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434169656890268e-05, + "loss": 3.8094, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433331062139216e-05, + "loss": 3.8279, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432494105268537e-05, + "loss": 3.8159, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431655510517485e-05, + "loss": 3.8144, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430816915766433e-05, + "loss": 3.8212, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429978321015381e-05, + "loss": 3.8054, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429139726264329e-05, + "loss": 3.8109, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.42830276939365e-05, + "loss": 3.8129, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427464174642598e-05, + "loss": 3.8226, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426625579891546e-05, + "loss": 3.8072, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425786985140494e-05, + "loss": 3.8136, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424948390389442e-05, + "loss": 3.8088, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424111433518763e-05, + "loss": 3.8094, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423272838767711e-05, + "loss": 3.8003, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422434244016659e-05, + "loss": 3.8132, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421595649265607e-05, + "loss": 3.8213, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420757054514556e-05, + "loss": 3.8213, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419920097643877e-05, + "loss": 3.8186, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419081502892825e-05, + "loss": 3.8015, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418242908141773e-05, + "loss": 3.8061, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417404313390721e-05, + "loss": 3.812, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165673565200416e-05, + "loss": 3.8184, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157287617689896e-05, + "loss": 3.8164, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148901670179376e-05, + "loss": 3.8111, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140515722668856e-05, + "loss": 3.8041, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132129775158336e-05, + "loss": 3.8238, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123760206451545e-05, + "loss": 3.7982, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115374258941025e-05, + "loss": 3.8117, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410698831143051e-05, + "loss": 3.8019, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409860236391999e-05, + "loss": 3.8112, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409021641640947e-05, + "loss": 3.7997, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408183046889895e-05, + "loss": 3.8099, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407346090019216e-05, + "loss": 3.7995, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406507495268164e-05, + "loss": 3.8061, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405668900517112e-05, + "loss": 3.8089, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.40483030576606e-05, + "loss": 3.8022, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403993348895381e-05, + "loss": 3.816, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403154754144329e-05, + "loss": 3.8183, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402316159393277e-05, + "loss": 3.8102, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401477564642225e-05, + "loss": 3.8078, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006406077715465e-05, + "loss": 3.7998, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3998020130204945e-05, + "loss": 3.8045, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989634182694425e-05, + "loss": 3.801, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981248235183905e-05, + "loss": 3.8137, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397286228767338e-05, + "loss": 3.7871, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396447634016286e-05, + "loss": 3.8074, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956106771456074e-05, + "loss": 3.8037, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394772082394555e-05, + "loss": 3.8101, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393933487643503e-05, + "loss": 3.801, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393094892892451e-05, + "loss": 3.8036, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392257936021772e-05, + "loss": 3.7984, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.39141934127072e-05, + "loss": 3.8126, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390580746519668e-05, + "loss": 3.8067, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389742151768616e-05, + "loss": 3.8112, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388905194897937e-05, + "loss": 3.792, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388066600146885e-05, + "loss": 3.8077, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387228005395833e-05, + "loss": 3.8083, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386389410644781e-05, + "loss": 3.8002, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385552453774102e-05, + "loss": 3.8022, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.38471385902305e-05, + "loss": 3.8104, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383875264271998e-05, + "loss": 3.8038, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383036669520946e-05, + "loss": 3.8236, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382199712650267e-05, + "loss": 3.7942, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813611178992157e-05, + "loss": 3.8058, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805225231481637e-05, + "loss": 3.7971, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796839283971116e-05, + "loss": 3.7989, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788453336460596e-05, + "loss": 3.8038, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780083767753806e-05, + "loss": 3.7975, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771697820243285e-05, + "loss": 3.7996, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763311872732765e-05, + "loss": 3.7862, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754925925222245e-05, + "loss": 3.804, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8917667865753174, + "eval_runtime": 304.2835, + "eval_samples_per_second": 1254.064, + "eval_steps_per_second": 39.19, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746539977711725e-05, + "loss": 3.8007, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738170409004934e-05, + "loss": 3.7878, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729784461494414e-05, + "loss": 3.8045, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721398513983894e-05, + "loss": 3.8023, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3713012566473374e-05, + "loss": 3.8089, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370464299776659e-05, + "loss": 3.7938, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369625705025607e-05, + "loss": 3.7965, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368787110274555e-05, + "loss": 3.7848, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367948515523503e-05, + "loss": 3.7985, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367111558652824e-05, + "loss": 3.7956, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366272963901772e-05, + "loss": 3.7965, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.36543436915072e-05, + "loss": 3.7901, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364597412280041e-05, + "loss": 3.7896, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363758817528989e-05, + "loss": 3.7923, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362920222777937e-05, + "loss": 3.7851, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362081628026885e-05, + "loss": 3.7796, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361243033275833e-05, + "loss": 3.785, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360404438524781e-05, + "loss": 3.7925, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359565843773729e-05, + "loss": 3.7855, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587272490226775e-05, + "loss": 3.8048, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3578902921519984e-05, + "loss": 3.7923, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570516974009464e-05, + "loss": 3.7994, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562131026498944e-05, + "loss": 3.7866, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553745078988424e-05, + "loss": 3.7892, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354537551028163e-05, + "loss": 3.786, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353698956277111e-05, + "loss": 3.7967, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352860361526059e-05, + "loss": 3.7864, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352021766775007e-05, + "loss": 3.7844, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351184809904328e-05, + "loss": 3.7797, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350346215153276e-05, + "loss": 3.7886, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349507620402224e-05, + "loss": 3.7898, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348669025651173e-05, + "loss": 3.791, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347832068780494e-05, + "loss": 3.7941, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.346993474029442e-05, + "loss": 3.7902, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.34615487927839e-05, + "loss": 3.786, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345316284527338e-05, + "loss": 3.7947, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444793276566586e-05, + "loss": 3.7896, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436407329056066e-05, + "loss": 3.7747, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428021381545546e-05, + "loss": 3.7753, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419635434035026e-05, + "loss": 3.7711, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411249486524506e-05, + "loss": 3.7762, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402879917817715e-05, + "loss": 3.7909, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394493970307195e-05, + "loss": 3.7841, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338610802279668e-05, + "loss": 3.7742, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377722075286155e-05, + "loss": 3.7848, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369336127775635e-05, + "loss": 3.7773, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360950180265115e-05, + "loss": 3.7841, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335258061155833e-05, + "loss": 3.7711, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344194664047804e-05, + "loss": 3.7528, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335808716537284e-05, + "loss": 3.8019, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327422769026764e-05, + "loss": 3.7832, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3319036821516244e-05, + "loss": 3.7872, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331066725280945e-05, + "loss": 3.774, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330229768410267e-05, + "loss": 3.7829, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329391173659215e-05, + "loss": 3.7655, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328552578908163e-05, + "loss": 3.7765, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327713984157111e-05, + "loss": 3.7768, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326875389406059e-05, + "loss": 3.775, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326036794655007e-05, + "loss": 3.7957, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325198199903955e-05, + "loss": 3.7686, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324359605152903e-05, + "loss": 3.7628, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323522648282224e-05, + "loss": 3.79, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322684053531172e-05, + "loss": 3.7569, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.32184545878012e-05, + "loss": 3.766, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321006864029068e-05, + "loss": 3.782, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320169907158389e-05, + "loss": 3.7817, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193313124073373e-05, + "loss": 3.763, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318492717656285e-05, + "loss": 3.7723, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317654122905233e-05, + "loss": 3.7545, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316817166034554e-05, + "loss": 3.7693, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315978571283502e-05, + "loss": 3.7754, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.31513997653245e-05, + "loss": 3.764, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314301381781398e-05, + "loss": 3.7775, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313464424910719e-05, + "loss": 3.7752, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312625830159667e-05, + "loss": 3.7866, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311787235408615e-05, + "loss": 3.764, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310948640657563e-05, + "loss": 3.77, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310110045906511e-05, + "loss": 3.7747, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309273089035833e-05, + "loss": 3.763, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308434494284781e-05, + "loss": 3.7763, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307595899533729e-05, + "loss": 3.7706, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306757304782677e-05, + "loss": 3.7679, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3059203479119976e-05, + "loss": 3.7758, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050817531609456e-05, + "loss": 3.7595, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042431584098936e-05, + "loss": 3.7606, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034045636588416e-05, + "loss": 3.7691, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025676067881625e-05, + "loss": 3.7738, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017290120371105e-05, + "loss": 3.764, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008904172860585e-05, + "loss": 3.766, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000518225350065e-05, + "loss": 3.7566, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299214865664328e-05, + "loss": 3.7653, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298376270913276e-05, + "loss": 3.7567, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297537676162224e-05, + "loss": 3.7645, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296699081411172e-05, + "loss": 3.7789, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295862124540493e-05, + "loss": 3.7696, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295023529789441e-05, + "loss": 3.7727, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294184935038389e-05, + "loss": 3.7575, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293346340287337e-05, + "loss": 3.7608, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292509383416658e-05, + "loss": 3.763, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291670788665606e-05, + "loss": 3.7759, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290832193914554e-05, + "loss": 3.7683, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289993599163502e-05, + "loss": 3.7725, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289156642292823e-05, + "loss": 3.7595, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883180475417714e-05, + "loss": 3.7752, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874794527907194e-05, + "loss": 3.7557, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866408580396674e-05, + "loss": 3.7674, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858039011689883e-05, + "loss": 3.7524, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284965306417936e-05, + "loss": 3.7702, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284126711666884e-05, + "loss": 3.7555, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283288116915832e-05, + "loss": 3.7618, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.28244952216478e-05, + "loss": 3.7578, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281612565294101e-05, + "loss": 3.7596, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280773970543049e-05, + "loss": 3.761, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279935375791997e-05, + "loss": 3.7595, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279096781040945e-05, + "loss": 3.7692, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278259824170267e-05, + "loss": 3.7714, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277421229419215e-05, + "loss": 3.7676, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276582634668163e-05, + "loss": 3.7675, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275744039917111e-05, + "loss": 3.753, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274907083046432e-05, + "loss": 3.7584, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.27406848829538e-05, + "loss": 3.7603, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273229893544328e-05, + "loss": 3.7671, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272391298793276e-05, + "loss": 3.7441, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715543419225966e-05, + "loss": 3.7621, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707157471715446e-05, + "loss": 3.7629, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698771524204926e-05, + "loss": 3.7613, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690385576694406e-05, + "loss": 3.7577, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268201600798762e-05, + "loss": 3.7602, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.26736300604771e-05, + "loss": 3.7579, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266524411296658e-05, + "loss": 3.7688, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656858165456055e-05, + "loss": 3.7655, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264848859674927e-05, + "loss": 3.7671, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264010264923875e-05, + "loss": 3.7493, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263171670172823e-05, + "loss": 3.7632, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623330754217704e-05, + "loss": 3.7653, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261496118551092e-05, + "loss": 3.756, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.26065752380004e-05, + "loss": 3.7602, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259818929048988e-05, + "loss": 3.7663, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258980334297936e-05, + "loss": 3.7632, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581433774272575e-05, + "loss": 3.7751, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2573047826762055e-05, + "loss": 3.7555, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256466187925153e-05, + "loss": 3.7617, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255627593174101e-05, + "loss": 3.7563, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2547906363034224e-05, + "loss": 3.7582, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539520415523704e-05, + "loss": 3.7557, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253113446801318e-05, + "loss": 3.7529, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252274852050266e-05, + "loss": 3.7591, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251437895179587e-05, + "loss": 3.7419, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250599300428535e-05, + "loss": 3.7641, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8763163089752197, + "eval_runtime": 303.2875, + "eval_samples_per_second": 1258.182, + "eval_steps_per_second": 39.319, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497607056774826e-05, + "loss": 3.7587, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248922110926431e-05, + "loss": 3.7461, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248083516175379e-05, + "loss": 3.7597, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247244921424327e-05, + "loss": 3.7584, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246406326673275e-05, + "loss": 3.7676, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245567731922223e-05, + "loss": 3.7518, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244729137171171e-05, + "loss": 3.7552, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243890542420119e-05, + "loss": 3.7416, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.24305358554944e-05, + "loss": 3.7554, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242214990798388e-05, + "loss": 3.7548, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241376396047336e-05, + "loss": 3.7532, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240537801296284e-05, + "loss": 3.7472, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239702482305978e-05, + "loss": 3.7468, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238863887554927e-05, + "loss": 3.7493, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238025292803875e-05, + "loss": 3.7473, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237186698052823e-05, + "loss": 3.7373, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236348103301771e-05, + "loss": 3.7427, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235509508550719e-05, + "loss": 3.7497, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234670913799667e-05, + "loss": 3.7461, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338323190486147e-05, + "loss": 3.7605, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2329953621779356e-05, + "loss": 3.7535, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321567674268836e-05, + "loss": 3.7593, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313181726758316e-05, + "loss": 3.7408, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304795779247796e-05, + "loss": 3.7478, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296426210541005e-05, + "loss": 3.7458, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288040263030485e-05, + "loss": 3.7551, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279654315519965e-05, + "loss": 3.744, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227126836800945e-05, + "loss": 3.7474, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226289879930266e-05, + "loss": 3.7402, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225451285179214e-05, + "loss": 3.7435, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224612690428162e-05, + "loss": 3.7451, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.22377409567711e-05, + "loss": 3.7547, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222937138806431e-05, + "loss": 3.7538, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222098544055379e-05, + "loss": 3.7509, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221259949304327e-05, + "loss": 3.7445, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220422992433648e-05, + "loss": 3.7485, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219584397682596e-05, + "loss": 3.7505, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218745802931544e-05, + "loss": 3.7372, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217907208180492e-05, + "loss": 3.7323, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.21706861342944e-05, + "loss": 3.7307, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162300186783885e-05, + "loss": 3.7396, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153914239273365e-05, + "loss": 3.7456, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214552829176284e-05, + "loss": 3.7437, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137158723056054e-05, + "loss": 3.7363, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128772775545534e-05, + "loss": 3.739, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120386828035014e-05, + "loss": 3.7391, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211200088052449e-05, + "loss": 3.7437, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.21036313118177e-05, + "loss": 3.7313, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209524536430718e-05, + "loss": 3.7129, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208685941679666e-05, + "loss": 3.7568, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078473469286136e-05, + "loss": 3.7417, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207010390057935e-05, + "loss": 3.7504, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206171795306884e-05, + "loss": 3.7376, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205334838436205e-05, + "loss": 3.7413, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204496243685153e-05, + "loss": 3.7275, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203657648934101e-05, + "loss": 3.7359, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202819054183049e-05, + "loss": 3.7401, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201980459431996e-05, + "loss": 3.7337, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201141864680944e-05, + "loss": 3.7555, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200303269929892e-05, + "loss": 3.7329, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.19946467517884e-05, + "loss": 3.7243, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198627718308161e-05, + "loss": 3.7503, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197789123557109e-05, + "loss": 3.7189, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969505288060576e-05, + "loss": 3.7219, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961119340550056e-05, + "loss": 3.7467, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952749771843265e-05, + "loss": 3.7431, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944363824332745e-05, + "loss": 3.7229, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1935977876822225e-05, + "loss": 3.7347, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927591929311705e-05, + "loss": 3.7157, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919222360604914e-05, + "loss": 3.7319, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910836413094394e-05, + "loss": 3.7342, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902450465583874e-05, + "loss": 3.7291, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894064518073354e-05, + "loss": 3.7373, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188569494936656e-05, + "loss": 3.7362, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187730900185604e-05, + "loss": 3.7461, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186892305434553e-05, + "loss": 3.7297, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186053710683501e-05, + "loss": 3.7325, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185216753812822e-05, + "loss": 3.7347, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.18437815906177e-05, + "loss": 3.7246, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183539564310718e-05, + "loss": 3.7369, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182700969559666e-05, + "loss": 3.7326, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181864012688987e-05, + "loss": 3.7269, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181025417937935e-05, + "loss": 3.7434, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180186823186883e-05, + "loss": 3.7167, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179349866316204e-05, + "loss": 3.7215, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178511271565152e-05, + "loss": 3.7325, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776726768141e-05, + "loss": 3.7369, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768340820630484e-05, + "loss": 3.7273, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175997125192369e-05, + "loss": 3.7314, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175158530441317e-05, + "loss": 3.7169, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174319935690265e-05, + "loss": 3.7299, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173481340939213e-05, + "loss": 3.7189, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172644384068534e-05, + "loss": 3.7276, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171805789317482e-05, + "loss": 3.7399, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.17096719456643e-05, + "loss": 3.7324, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170128599815378e-05, + "loss": 3.7349, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169291642944699e-05, + "loss": 3.7216, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168453048193647e-05, + "loss": 3.7245, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167614453442595e-05, + "loss": 3.7242, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166775858691544e-05, + "loss": 3.7401, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659389018208646e-05, + "loss": 3.7318, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651003070698126e-05, + "loss": 3.7348, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642617123187606e-05, + "loss": 3.7199, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634231175677086e-05, + "loss": 3.7353, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625861606970295e-05, + "loss": 3.7219, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617475659459775e-05, + "loss": 3.7295, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609089711949255e-05, + "loss": 3.7156, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600703764438735e-05, + "loss": 3.7306, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592350574535674e-05, + "loss": 3.7182, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158396462702516e-05, + "loss": 3.728, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157557867951464e-05, + "loss": 3.7167, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156719273200412e-05, + "loss": 3.7295, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.15588067844936e-05, + "loss": 3.7216, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155042083698308e-05, + "loss": 3.7204, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154203488947256e-05, + "loss": 3.7346, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153364894196204e-05, + "loss": 3.7371, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152527937325525e-05, + "loss": 3.7313, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151689342574473e-05, + "loss": 3.726, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150850747823421e-05, + "loss": 3.722, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150012153072369e-05, + "loss": 3.7216, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.14917519620169e-05, + "loss": 3.7241, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148336601450638e-05, + "loss": 3.7276, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147498006699586e-05, + "loss": 3.71, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466594119485345e-05, + "loss": 3.7263, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458224550778554e-05, + "loss": 3.728, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449838603268034e-05, + "loss": 3.7257, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441452655757514e-05, + "loss": 3.7224, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433066708246994e-05, + "loss": 3.7221, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.14246971395402e-05, + "loss": 3.7192, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141631119202968e-05, + "loss": 3.7329, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140792524451916e-05, + "loss": 3.7309, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139953929700864e-05, + "loss": 3.7298, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139116972830185e-05, + "loss": 3.7145, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138278378079133e-05, + "loss": 3.7279, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137439783328081e-05, + "loss": 3.7281, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136601188577029e-05, + "loss": 3.7203, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135764231706351e-05, + "loss": 3.7257, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134925636955299e-05, + "loss": 3.7264, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134087042204247e-05, + "loss": 3.7256, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133248447453195e-05, + "loss": 3.741, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324114905825156e-05, + "loss": 3.7174, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315728958314636e-05, + "loss": 3.7266, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307343010804116e-05, + "loss": 3.7238, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298957063293596e-05, + "loss": 3.7231, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290587494586805e-05, + "loss": 3.7173, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282201547076285e-05, + "loss": 3.7172, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273815599565765e-05, + "loss": 3.722, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265429652055245e-05, + "loss": 3.7107, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125704370454473e-05, + "loss": 3.7275, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8657584190368652, + "eval_runtime": 303.1251, + "eval_samples_per_second": 1258.857, + "eval_steps_per_second": 39.34, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.124865775703421e-05, + "loss": 3.7247, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240271809523685e-05, + "loss": 3.7104, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231885862013165e-05, + "loss": 3.7234, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1223499914502645e-05, + "loss": 3.7231, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215113966992125e-05, + "loss": 3.733, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206728019481605e-05, + "loss": 3.7165, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1198342071971085e-05, + "loss": 3.7244, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.1189956124460565e-05, + "loss": 3.7109, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.1181586555753774e-05, + "loss": 3.7139, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.1173200608243254e-05, + "loss": 3.7251, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.1164814660732734e-05, + "loss": 3.7178, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156428713222214e-05, + "loss": 3.7107, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114807552331916e-05, + "loss": 3.7214, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113968957580864e-05, + "loss": 3.71, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113130362829812e-05, + "loss": 3.7068, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.11229176807876e-05, + "loss": 3.7041, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111453173327708e-05, + "loss": 3.7072, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110614578576656e-05, + "loss": 3.7184, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109775983825604e-05, + "loss": 3.7044, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108937389074552e-05, + "loss": 3.7281, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108100432203873e-05, + "loss": 3.7192, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107261837452821e-05, + "loss": 3.7243, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106423242701769e-05, + "loss": 3.7106, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105584647950717e-05, + "loss": 3.7124, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104747691080038e-05, + "loss": 3.7172, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103909096328986e-05, + "loss": 3.7186, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103070501577934e-05, + "loss": 3.7111, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102231906826882e-05, + "loss": 3.7133, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101394949956203e-05, + "loss": 3.7026, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100556355205151e-05, + "loss": 3.7101, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099717760454099e-05, + "loss": 3.7115, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098879165703047e-05, + "loss": 3.72, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098042208832368e-05, + "loss": 3.7191, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097203614081316e-05, + "loss": 3.7171, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096365019330264e-05, + "loss": 3.7126, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095526424579212e-05, + "loss": 3.7156, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094689467708534e-05, + "loss": 3.7158, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093850872957482e-05, + "loss": 3.7042, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930139160868026e-05, + "loss": 3.7014, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921753213357506e-05, + "loss": 3.6969, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0913367265846986e-05, + "loss": 3.7043, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0904981318336466e-05, + "loss": 3.7061, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896595370825946e-05, + "loss": 3.7137, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0888209423315426e-05, + "loss": 3.7074, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.0879823475804906e-05, + "loss": 3.7045, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871453907098115e-05, + "loss": 3.7079, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0863067959587595e-05, + "loss": 3.7125, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.0854682012077075e-05, + "loss": 3.6967, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084629606456656e-05, + "loss": 3.6817, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083792649585977e-05, + "loss": 3.7181, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082954054834925e-05, + "loss": 3.7105, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082115460083873e-05, + "loss": 3.7181, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081276865332821e-05, + "loss": 3.7043, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080439908462142e-05, + "loss": 3.7066, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.07960131371109e-05, + "loss": 3.6956, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078762718960038e-05, + "loss": 3.7025, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077924124208986e-05, + "loss": 3.7109, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077085529457934e-05, + "loss": 3.6959, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076246934706881e-05, + "loss": 3.7246, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.07540833995583e-05, + "loss": 3.7043, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074569745204778e-05, + "loss": 3.686, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.0737327883340995e-05, + "loss": 3.7185, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072894193583047e-05, + "loss": 3.689, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072055598831995e-05, + "loss": 3.6895, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071217004080943e-05, + "loss": 3.7133, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.0703800472102644e-05, + "loss": 3.7092, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069541452459212e-05, + "loss": 3.6922, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.06870285770816e-05, + "loss": 3.7002, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067864262957108e-05, + "loss": 3.687, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670273060864286e-05, + "loss": 3.6957, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0661887113353766e-05, + "loss": 3.7028, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065351754464698e-05, + "loss": 3.6959, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064513159713646e-05, + "loss": 3.7059, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063674564962594e-05, + "loss": 3.7005, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062835970211542e-05, + "loss": 3.7142, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.06199737546049e-05, + "loss": 3.6965, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061160418589812e-05, + "loss": 3.7031, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060321823838759e-05, + "loss": 3.7005, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059483229087707e-05, + "loss": 3.6935, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058644634336655e-05, + "loss": 3.7064, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057806039585603e-05, + "loss": 3.7022, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056967444834551e-05, + "loss": 3.6912, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056128850083499e-05, + "loss": 3.7107, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055290255332447e-05, + "loss": 3.6852, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054453298461769e-05, + "loss": 3.6882, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.0536147037107167e-05, + "loss": 3.7028, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.0527761089596647e-05, + "loss": 3.7016, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0519375142086127e-05, + "loss": 3.6955, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0511005573379336e-05, + "loss": 3.7013, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0502619625868816e-05, + "loss": 3.6854, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.0494233678358296e-05, + "loss": 3.6951, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0485847730847775e-05, + "loss": 3.69, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0477478162140985e-05, + "loss": 3.6941, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0469092214630465e-05, + "loss": 3.7081, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.0460706267119944e-05, + "loss": 3.7007, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0452320319609424e-05, + "loss": 3.7053, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044395075090264e-05, + "loss": 3.6895, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043556480339212e-05, + "loss": 3.6931, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.04271788558816e-05, + "loss": 3.6927, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041879290837108e-05, + "loss": 3.7033, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041042333966429e-05, + "loss": 3.7001, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040203739215377e-05, + "loss": 3.7044, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039365144464325e-05, + "loss": 3.6915, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038526549713273e-05, + "loss": 3.6986, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037689592842594e-05, + "loss": 3.694, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036850998091542e-05, + "loss": 3.6966, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.03601240334049e-05, + "loss": 3.6847, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035173808589438e-05, + "loss": 3.7037, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034338489599132e-05, + "loss": 3.6866, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.03349989484808e-05, + "loss": 3.6944, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032661300097028e-05, + "loss": 3.6863, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031822705345976e-05, + "loss": 3.6956, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030984110594924e-05, + "loss": 3.6934, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030145515843872e-05, + "loss": 3.6903, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.02930692109282e-05, + "loss": 3.7008, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028468326341768e-05, + "loss": 3.7038, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027631369471089e-05, + "loss": 3.7064, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026792774720037e-05, + "loss": 3.6933, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025954179968985e-05, + "loss": 3.6909, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025115585217933e-05, + "loss": 3.6888, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024278628347255e-05, + "loss": 3.6923, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023440033596203e-05, + "loss": 3.6943, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022601438845151e-05, + "loss": 3.6815, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021762844094099e-05, + "loss": 3.6945, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209258872234197e-05, + "loss": 3.6992, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0200872924723677e-05, + "loss": 3.6905, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0192486977213157e-05, + "loss": 3.6923, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.0184101029702636e-05, + "loss": 3.6938, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175731460995846e-05, + "loss": 3.6881, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167345513485326e-05, + "loss": 3.7002, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0158959565974805e-05, + "loss": 3.6979, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.0150573618464285e-05, + "loss": 3.7016, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.01422040497575e-05, + "loss": 3.6826, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013381810224698e-05, + "loss": 3.6967, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012543215473646e-05, + "loss": 3.6965, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011704620722594e-05, + "loss": 3.6892, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010867663851915e-05, + "loss": 3.6953, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010030706981236e-05, + "loss": 3.6945, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009192112230184e-05, + "loss": 3.6959, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008353517479132e-05, + "loss": 3.7144, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.00751492272808e-05, + "loss": 3.6826, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006676327977028e-05, + "loss": 3.6995, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005837733225976e-05, + "loss": 3.6908, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.004999138474924e-05, + "loss": 3.6926, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.0041621816042455e-05, + "loss": 3.688, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.0033235868531935e-05, + "loss": 3.6849, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.0024849921021415e-05, + "loss": 3.6933, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0016463973510895e-05, + "loss": 3.6787, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000807802600037e-05, + "loss": 3.696, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.859010934829712, + "eval_runtime": 304.7053, + "eval_samples_per_second": 1252.328, + "eval_steps_per_second": 39.136, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.999969207848985e-05, + "loss": 3.6903, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999130613097933e-05, + "loss": 3.683, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998292018346881e-05, + "loss": 3.6923, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997455061476202e-05, + "loss": 3.6941, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.99661646672515e-05, + "loss": 3.7006, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995777871974098e-05, + "loss": 3.6879, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994939277223046e-05, + "loss": 3.6963, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.994102320352367e-05, + "loss": 3.6793, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.993263725601315e-05, + "loss": 3.6845, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992425130850263e-05, + "loss": 3.6964, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991586536099211e-05, + "loss": 3.6877, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990749579228532e-05, + "loss": 3.6788, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989912622357854e-05, + "loss": 3.6928, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989074027606802e-05, + "loss": 3.6769, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988235432855749e-05, + "loss": 3.6795, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987396838104697e-05, + "loss": 3.6697, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.986558243353645e-05, + "loss": 3.6802, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.985719648602593e-05, + "loss": 3.6901, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984881053851541e-05, + "loss": 3.6755, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.984042459100489e-05, + "loss": 3.6963, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.9832055022298106e-05, + "loss": 3.6926, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.9823669074787586e-05, + "loss": 3.6921, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.9815283127277066e-05, + "loss": 3.6842, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.9806897179766546e-05, + "loss": 3.6831, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.9798527611059755e-05, + "loss": 3.6867, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.9790141663549235e-05, + "loss": 3.688, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.9781755716038715e-05, + "loss": 3.6807, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.9773369768528195e-05, + "loss": 3.6866, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.9765000199821404e-05, + "loss": 3.6733, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.9756614252310884e-05, + "loss": 3.6812, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.9748228304800364e-05, + "loss": 3.6817, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.9739842357289844e-05, + "loss": 3.6862, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973147278858306e-05, + "loss": 3.6902, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.972308684107254e-05, + "loss": 3.6915, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971470089356202e-05, + "loss": 3.6775, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.97063149460515e-05, + "loss": 3.6857, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.969794537734471e-05, + "loss": 3.6917, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.968955942983419e-05, + "loss": 3.6718, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.96811898611274e-05, + "loss": 3.6749, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967280391361688e-05, + "loss": 3.6702, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.966441796610636e-05, + "loss": 3.6722, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.965603201859584e-05, + "loss": 3.6785, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964764607108532e-05, + "loss": 3.6866, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.96392601235748e-05, + "loss": 3.6779, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963087417606428e-05, + "loss": 3.6748, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.9622488228553764e-05, + "loss": 3.6748, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.9614118659846974e-05, + "loss": 3.6874, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.9605732712336454e-05, + "loss": 3.6669, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.9597346764825933e-05, + "loss": 3.6557, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958897719611914e-05, + "loss": 3.6881, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.958059124860862e-05, + "loss": 3.6813, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.95722053010981e-05, + "loss": 3.6883, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956381935358758e-05, + "loss": 3.6753, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955544978488079e-05, + "loss": 3.6772, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954706383737027e-05, + "loss": 3.6697, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953867788985975e-05, + "loss": 3.6754, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953029194234923e-05, + "loss": 3.6839, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952190599483872e-05, + "loss": 3.6654, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.95135200473282e-05, + "loss": 3.6992, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950513409981768e-05, + "loss": 3.6727, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949674815230715e-05, + "loss": 3.6572, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948837858360037e-05, + "loss": 3.6902, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.947999263608985e-05, + "loss": 3.6673, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947160668857933e-05, + "loss": 3.6583, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.94632207410688e-05, + "loss": 3.6828, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.9454851172362016e-05, + "loss": 3.6822, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.9446481603655225e-05, + "loss": 3.666, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.9438095656144705e-05, + "loss": 3.6706, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.9429709708634185e-05, + "loss": 3.6555, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.942132376112367e-05, + "loss": 3.6678, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.941293781361315e-05, + "loss": 3.6774, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940456824490636e-05, + "loss": 3.6682, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939618229739584e-05, + "loss": 3.6753, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.938779634988532e-05, + "loss": 3.6706, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.93794104023748e-05, + "loss": 3.6862, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937104083366801e-05, + "loss": 3.6684, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936265488615749e-05, + "loss": 3.6759, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935426893864697e-05, + "loss": 3.6721, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934588299113644e-05, + "loss": 3.6672, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933749704362592e-05, + "loss": 3.6797, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932912747491914e-05, + "loss": 3.6725, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.9320741527408625e-05, + "loss": 3.6682, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.93123555798981e-05, + "loss": 3.6817, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930396963238758e-05, + "loss": 3.6583, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.9295600063680794e-05, + "loss": 3.6627, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.9287214116170274e-05, + "loss": 3.6713, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.927882816865975e-05, + "loss": 3.676, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.927044222114923e-05, + "loss": 3.6625, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.926205627363871e-05, + "loss": 3.6764, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925367032612819e-05, + "loss": 3.6628, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924528437861767e-05, + "loss": 3.6653, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923689843110715e-05, + "loss": 3.6596, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922852886240036e-05, + "loss": 3.6668, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.922014291488984e-05, + "loss": 3.681, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.921175696737932e-05, + "loss": 3.671, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.92033710198688e-05, + "loss": 3.6767, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919500145116201e-05, + "loss": 3.6641, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918661550365149e-05, + "loss": 3.6636, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.91782459349447e-05, + "loss": 3.665, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.916985998743418e-05, + "loss": 3.6758, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.916147403992366e-05, + "loss": 3.6723, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.915308809241314e-05, + "loss": 3.6744, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.914470214490262e-05, + "loss": 3.6706, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.91363161973921e-05, + "loss": 3.6684, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912793024988158e-05, + "loss": 3.6678, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911954430237106e-05, + "loss": 3.6673, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911117473366428e-05, + "loss": 3.6588, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910278878615376e-05, + "loss": 3.6734, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909440283864324e-05, + "loss": 3.6606, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908601689113272e-05, + "loss": 3.666, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.90776309436222e-05, + "loss": 3.6629, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906924499611168e-05, + "loss": 3.6634, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.9060859048601157e-05, + "loss": 3.6674, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.9052473101090637e-05, + "loss": 3.6625, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.9044103532383846e-05, + "loss": 3.6767, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.9035717584873326e-05, + "loss": 3.6778, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.9027331637362806e-05, + "loss": 3.6753, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.901894568985228e-05, + "loss": 3.664, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.9010576121145495e-05, + "loss": 3.6681, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.900219017363498e-05, + "loss": 3.6614, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899380422612446e-05, + "loss": 3.6677, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898543465741767e-05, + "loss": 3.6691, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897704870990715e-05, + "loss": 3.6543, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896866276239663e-05, + "loss": 3.666, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.896027681488611e-05, + "loss": 3.6703, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.8951890867375583e-05, + "loss": 3.6683, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.8943504919865063e-05, + "loss": 3.6622, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893511897235454e-05, + "loss": 3.6641, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892673302484402e-05, + "loss": 3.6608, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891836345613723e-05, + "loss": 3.6754, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.890997750862672e-05, + "loss": 3.6671, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.89015915611162e-05, + "loss": 3.6786, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889320561360568e-05, + "loss": 3.6571, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.888483604489889e-05, + "loss": 3.6661, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.887645009738837e-05, + "loss": 3.6722, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.886806414987785e-05, + "loss": 3.6651, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.885967820236733e-05, + "loss": 3.666, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885130863366054e-05, + "loss": 3.6693, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884292268615002e-05, + "loss": 3.6683, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.88345367386395e-05, + "loss": 3.6852, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.882615079112898e-05, + "loss": 3.6624, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881776484361846e-05, + "loss": 3.6708, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880939527491167e-05, + "loss": 3.6681, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880100932740115e-05, + "loss": 3.6625, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879262337989063e-05, + "loss": 3.664, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878423743238011e-05, + "loss": 3.6587, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877585148486959e-05, + "loss": 3.6659, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876746553735907e-05, + "loss": 3.6577, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.875907958984855e-05, + "loss": 3.6663, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.8544273376464844, + "eval_runtime": 304.6113, + "eval_samples_per_second": 1252.715, + "eval_steps_per_second": 39.148, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.875069364233803e-05, + "loss": 3.6651, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874230769482751e-05, + "loss": 3.6559, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873392174731699e-05, + "loss": 3.6619, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.8725535799806466e-05, + "loss": 3.6707, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.8717149852295946e-05, + "loss": 3.6785, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.8708763904785425e-05, + "loss": 3.6602, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.8700377957274905e-05, + "loss": 3.6649, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.8691992009764385e-05, + "loss": 3.6564, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.86836224410576e-05, + "loss": 3.6584, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867523649354708e-05, + "loss": 3.6665, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866685054603656e-05, + "loss": 3.6644, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865846459852604e-05, + "loss": 3.6552, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.8650111408622986e-05, + "loss": 3.6685, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8641725461112466e-05, + "loss": 3.65, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.863333951360194e-05, + "loss": 3.6533, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862495356609142e-05, + "loss": 3.6421, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.86165676185809e-05, + "loss": 3.6586, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860818167107038e-05, + "loss": 3.6643, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859979572355986e-05, + "loss": 3.6493, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859140977604934e-05, + "loss": 3.6676, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.8583040207342555e-05, + "loss": 3.6652, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.8574654259832035e-05, + "loss": 3.6683, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.8566268312321515e-05, + "loss": 3.6569, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.8557882364810995e-05, + "loss": 3.6575, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8549512796104204e-05, + "loss": 3.6594, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854114322739741e-05, + "loss": 3.6664, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853275727988689e-05, + "loss": 3.6497, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852437133237637e-05, + "loss": 3.6619, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851598538486585e-05, + "loss": 3.647, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850759943735533e-05, + "loss": 3.6541, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849921348984481e-05, + "loss": 3.6596, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849084392113803e-05, + "loss": 3.6645, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848245797362751e-05, + "loss": 3.6577, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847407202611699e-05, + "loss": 3.6695, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846568607860647e-05, + "loss": 3.6539, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845730013109595e-05, + "loss": 3.6598, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844891418358543e-05, + "loss": 3.6622, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.844052823607491e-05, + "loss": 3.6439, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843215866736812e-05, + "loss": 3.6489, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.84237727198576e-05, + "loss": 3.6494, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841538677234708e-05, + "loss": 3.6455, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840700082483656e-05, + "loss": 3.6509, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839861487732604e-05, + "loss": 3.6633, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839022892981552e-05, + "loss": 3.6507, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.8381842982305e-05, + "loss": 3.6503, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837345703479448e-05, + "loss": 3.6511, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836508746608769e-05, + "loss": 3.6585, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835670151857717e-05, + "loss": 3.6421, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834833194987038e-05, + "loss": 3.6317, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833994600235986e-05, + "loss": 3.664, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833156005484934e-05, + "loss": 3.656, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832317410733882e-05, + "loss": 3.6663, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.83147881598283e-05, + "loss": 3.6472, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830641859112151e-05, + "loss": 3.652, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829803264361099e-05, + "loss": 3.6436, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828964669610047e-05, + "loss": 3.6469, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828126074858995e-05, + "loss": 3.664, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827289117988317e-05, + "loss": 3.6374, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826450523237265e-05, + "loss": 3.6746, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825611928486213e-05, + "loss": 3.6525, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.82477333373516e-05, + "loss": 3.6312, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823934738984108e-05, + "loss": 3.6602, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.8230977821134296e-05, + "loss": 3.6454, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.8222591873623776e-05, + "loss": 3.6333, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821420592611325e-05, + "loss": 3.6556, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820581997860273e-05, + "loss": 3.66, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819743403109221e-05, + "loss": 3.6394, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818904808358169e-05, + "loss": 3.6476, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818066213607117e-05, + "loss": 3.6298, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817227618856065e-05, + "loss": 3.6437, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.8163906619853864e-05, + "loss": 3.6505, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8155537051147074e-05, + "loss": 3.6412, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8147151103636554e-05, + "loss": 3.6549, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.8138765156126033e-05, + "loss": 3.6417, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.8130379208615513e-05, + "loss": 3.6666, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812200963990872e-05, + "loss": 3.6438, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.81136236923982e-05, + "loss": 3.6539, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810523774488768e-05, + "loss": 3.6449, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809685179737716e-05, + "loss": 3.642, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808846584986664e-05, + "loss": 3.6539, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808009628115986e-05, + "loss": 3.6467, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807171033364934e-05, + "loss": 3.6494, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806332438613882e-05, + "loss": 3.6527, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.80549384386283e-05, + "loss": 3.6416, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804655249111778e-05, + "loss": 3.6326, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803818292241099e-05, + "loss": 3.6442, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802979697490047e-05, + "loss": 3.6535, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802141102738995e-05, + "loss": 3.6401, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801302507987943e-05, + "loss": 3.6484, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800463913236891e-05, + "loss": 3.637, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799625318485839e-05, + "loss": 3.6415, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798786723734787e-05, + "loss": 3.6367, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.7979497668641076e-05, + "loss": 3.6438, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.7971111721130556e-05, + "loss": 3.6539, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796274215242377e-05, + "loss": 3.6475, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795435620491325e-05, + "loss": 3.6537, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794597025740273e-05, + "loss": 3.6388, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793758430989221e-05, + "loss": 3.6405, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792919836238169e-05, + "loss": 3.6413, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.79208287936749e-05, + "loss": 3.6514, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791244284616438e-05, + "loss": 3.6498, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790405689865386e-05, + "loss": 3.6518, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789567095114334e-05, + "loss": 3.6445, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788728500363282e-05, + "loss": 3.6411, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787891543492603e-05, + "loss": 3.6498, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787052948741551e-05, + "loss": 3.642, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786214353990499e-05, + "loss": 3.6373, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7853757592394476e-05, + "loss": 3.6481, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7845371644883956e-05, + "loss": 3.6375, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.7837002076177165e-05, + "loss": 3.6398, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.7828616128666645e-05, + "loss": 3.638, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.7820230181156125e-05, + "loss": 3.6375, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.7811844233645605e-05, + "loss": 3.6464, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.7803458286135085e-05, + "loss": 3.6383, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779507233862456e-05, + "loss": 3.649, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778668639111404e-05, + "loss": 3.6527, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.7778316822407254e-05, + "loss": 3.6538, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.7769930874896734e-05, + "loss": 3.6415, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.7761544927386214e-05, + "loss": 3.6449, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.7753158979875694e-05, + "loss": 3.6345, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7744773032365174e-05, + "loss": 3.6458, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.7736387084854654e-05, + "loss": 3.6449, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772801751614786e-05, + "loss": 3.6302, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771963156863734e-05, + "loss": 3.6415, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771124562112682e-05, + "loss": 3.6441, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.77028596736163e-05, + "loss": 3.6474, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769447372610578e-05, + "loss": 3.6396, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768608777859526e-05, + "loss": 3.6391, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767770183108474e-05, + "loss": 3.6363, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766933226237795e-05, + "loss": 3.6542, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766094631486743e-05, + "loss": 3.6454, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765256036735691e-05, + "loss": 3.6524, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.76441744198464e-05, + "loss": 3.6357, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763578847233588e-05, + "loss": 3.6436, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762740252482536e-05, + "loss": 3.6483, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761901657731484e-05, + "loss": 3.6397, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761063062980432e-05, + "loss": 3.6442, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.7602277439901257e-05, + "loss": 3.641, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.7593891492390737e-05, + "loss": 3.6495, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.7585505544880216e-05, + "loss": 3.6544, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.7577119597369696e-05, + "loss": 3.6421, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7568733649859176e-05, + "loss": 3.6442, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.7560364081152385e-05, + "loss": 3.6444, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.7551978133641865e-05, + "loss": 3.6401, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754359218613135e-05, + "loss": 3.6404, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753520623862083e-05, + "loss": 3.6343, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752682029111031e-05, + "loss": 3.641, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751843434359979e-05, + "loss": 3.6347, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751004839608927e-05, + "loss": 3.6421, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8514771461486816, + "eval_runtime": 302.4908, + "eval_samples_per_second": 1261.496, + "eval_steps_per_second": 39.423, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750167882738248e-05, + "loss": 3.6422, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749329287987196e-05, + "loss": 3.6318, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748490693236144e-05, + "loss": 3.6378, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747652098485092e-05, + "loss": 3.6473, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.7468135037340394e-05, + "loss": 3.6552, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745976546863361e-05, + "loss": 3.637, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745137952112309e-05, + "loss": 3.646, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744299357361257e-05, + "loss": 3.6348, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743460762610205e-05, + "loss": 3.634, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742622167859153e-05, + "loss": 3.6389, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.7417852109884746e-05, + "loss": 3.6433, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740946616237422e-05, + "loss": 3.6326, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.7401096593667435e-05, + "loss": 3.6436, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.7392710646156915e-05, + "loss": 3.6273, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.7384324698646395e-05, + "loss": 3.6288, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737593875113587e-05, + "loss": 3.6179, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736755280362535e-05, + "loss": 3.6353, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735916685611483e-05, + "loss": 3.6388, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735078090860431e-05, + "loss": 3.626, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734239496109379e-05, + "loss": 3.6426, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733400901358327e-05, + "loss": 3.6461, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.7325623066072754e-05, + "loss": 3.6456, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7317237118562234e-05, + "loss": 3.6351, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7308851171051714e-05, + "loss": 3.6316, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.730048160234492e-05, + "loss": 3.6391, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729211203363813e-05, + "loss": 3.6422, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728372608612761e-05, + "loss": 3.6272, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727534013861709e-05, + "loss": 3.6379, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726695419110657e-05, + "loss": 3.6281, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725856824359605e-05, + "loss": 3.6269, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.725018229608553e-05, + "loss": 3.6376, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724181272737874e-05, + "loss": 3.64, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723342677986822e-05, + "loss": 3.6376, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722504083235771e-05, + "loss": 3.6456, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721665488484719e-05, + "loss": 3.6331, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720826893733667e-05, + "loss": 3.639, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719988298982615e-05, + "loss": 3.6436, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719149704231563e-05, + "loss": 3.6226, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718312747360884e-05, + "loss": 3.6246, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.717474152609832e-05, + "loss": 3.6273, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.71663555785878e-05, + "loss": 3.6178, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715796963107728e-05, + "loss": 3.6294, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714958368356676e-05, + "loss": 3.6427, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714119773605623e-05, + "loss": 3.6277, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713281178854571e-05, + "loss": 3.628, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.7124442219838926e-05, + "loss": 3.6318, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.7116056272328406e-05, + "loss": 3.634, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.7107670324817886e-05, + "loss": 3.6174, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.7099284377307366e-05, + "loss": 3.6102, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.7090898429796846e-05, + "loss": 3.6365, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.7082512482286326e-05, + "loss": 3.6375, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.7074142913579535e-05, + "loss": 3.6443, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.7065756966069015e-05, + "loss": 3.6268, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.7057371018558495e-05, + "loss": 3.6269, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.7048985071047975e-05, + "loss": 3.6233, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.7040599123537454e-05, + "loss": 3.6244, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.7032213176026934e-05, + "loss": 3.6398, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.7023843607320144e-05, + "loss": 3.6126, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701545765980963e-05, + "loss": 3.6545, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700707171229911e-05, + "loss": 3.6316, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699868576478859e-05, + "loss": 3.611, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699029981727807e-05, + "loss": 3.6362, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698193024857128e-05, + "loss": 3.6241, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697354430106076e-05, + "loss": 3.6124, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696515835355024e-05, + "loss": 3.6328, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695677240603972e-05, + "loss": 3.637, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.69483864585292e-05, + "loss": 3.6151, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694001688982241e-05, + "loss": 3.6324, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693163094231189e-05, + "loss": 3.6078, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692324499480137e-05, + "loss": 3.6219, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691485904729085e-05, + "loss": 3.6231, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6906489478584064e-05, + "loss": 3.6213, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.6898103531073544e-05, + "loss": 3.6283, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.6889717583563024e-05, + "loss": 3.6217, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.6881331636052504e-05, + "loss": 3.6427, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.6872945688541984e-05, + "loss": 3.6237, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686457611983519e-05, + "loss": 3.6337, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685619017232467e-05, + "loss": 3.6208, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684780422481415e-05, + "loss": 3.6201, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683941827730363e-05, + "loss": 3.6326, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683104870859684e-05, + "loss": 3.6227, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682266276108632e-05, + "loss": 3.6263, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.68142768135758e-05, + "loss": 3.633, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680589086606528e-05, + "loss": 3.6196, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679750491855476e-05, + "loss": 3.6109, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678913534984798e-05, + "loss": 3.6221, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678074940233746e-05, + "loss": 3.6321, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677236345482694e-05, + "loss": 3.6149, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676397750731642e-05, + "loss": 3.6301, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675559155980589e-05, + "loss": 3.6199, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674720561229537e-05, + "loss": 3.6146, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673881966478485e-05, + "loss": 3.6169, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673045009607806e-05, + "loss": 3.6223, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.6722080527371275e-05, + "loss": 3.6359, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.6713694579860755e-05, + "loss": 3.627, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.6705308632350235e-05, + "loss": 3.6304, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.6696922684839715e-05, + "loss": 3.6198, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.6688536737329195e-05, + "loss": 3.6166, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.6680150789818675e-05, + "loss": 3.6192, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667178122111189e-05, + "loss": 3.6304, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.6663395273601364e-05, + "loss": 3.6284, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.6655009326090844e-05, + "loss": 3.6296, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.6646623378580324e-05, + "loss": 3.6257, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.6638237431069804e-05, + "loss": 3.6158, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.6629851483559284e-05, + "loss": 3.6295, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662148191485249e-05, + "loss": 3.621, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661309596734197e-05, + "loss": 3.614, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660471001983145e-05, + "loss": 3.621, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659632407232094e-05, + "loss": 3.6201, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658795450361415e-05, + "loss": 3.6183, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657956855610363e-05, + "loss": 3.6162, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657118260859311e-05, + "loss": 3.6144, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656279666108259e-05, + "loss": 3.625, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655441071357207e-05, + "loss": 3.6239, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654602476606155e-05, + "loss": 3.622, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653763881855103e-05, + "loss": 3.6299, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652925287104051e-05, + "loss": 3.6362, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652089968113745e-05, + "loss": 3.6188, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651251373362693e-05, + "loss": 3.626, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650412778611641e-05, + "loss": 3.6168, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.6495741838605893e-05, + "loss": 3.6248, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.6487355891095373e-05, + "loss": 3.621, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647898632238858e-05, + "loss": 3.6126, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.647060037487806e-05, + "loss": 3.6155, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646221442736754e-05, + "loss": 3.6247, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645382847985702e-05, + "loss": 3.6265, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.64454425323465e-05, + "loss": 3.6144, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643705658483598e-05, + "loss": 3.6169, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642867063732546e-05, + "loss": 3.6199, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642030106861867e-05, + "loss": 3.6269, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641191512110815e-05, + "loss": 3.6272, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640352917359763e-05, + "loss": 3.6327, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639514322608711e-05, + "loss": 3.6124, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638675727857659e-05, + "loss": 3.6219, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637837133106608e-05, + "loss": 3.6257, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637000176235929e-05, + "loss": 3.6157, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636161581484877e-05, + "loss": 3.622, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635322986733825e-05, + "loss": 3.6245, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634484391982772e-05, + "loss": 3.6311, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.6336474351120936e-05, + "loss": 3.6336, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6328088403610416e-05, + "loss": 3.6211, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6319702456099896e-05, + "loss": 3.6225, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631131650858937e-05, + "loss": 3.6239, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630293056107885e-05, + "loss": 3.6177, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6294560992372065e-05, + "loss": 3.619, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.6286175044861545e-05, + "loss": 3.6189, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277789097351025e-05, + "loss": 3.6129, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.6269403149840505e-05, + "loss": 3.6181, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6261017202329985e-05, + "loss": 3.6169, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.8503243923187256, + "eval_runtime": 308.5125, + "eval_samples_per_second": 1236.874, + "eval_steps_per_second": 38.653, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.6252647633623194e-05, + "loss": 3.6184, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.6244261686112674e-05, + "loss": 3.6133, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.6235875738602154e-05, + "loss": 3.6216, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.6227489791091634e-05, + "loss": 3.6246, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.6219103843581114e-05, + "loss": 3.6334, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621073427487432e-05, + "loss": 3.6197, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.62023483273638e-05, + "loss": 3.6261, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619396237985328e-05, + "loss": 3.6154, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618557643234277e-05, + "loss": 3.6102, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617719048483225e-05, + "loss": 3.6167, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616882091612546e-05, + "loss": 3.6276, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.616043496861494e-05, + "loss": 3.6089, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615206539990815e-05, + "loss": 3.6252, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614367945239763e-05, + "loss": 3.6054, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.613529350488711e-05, + "loss": 3.608, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612690755737659e-05, + "loss": 3.599, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611852160986607e-05, + "loss": 3.6158, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.611013566235555e-05, + "loss": 3.6146, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610174971484503e-05, + "loss": 3.6118, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609336376733451e-05, + "loss": 3.6142, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608497781982399e-05, + "loss": 3.6279, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.60766082511172e-05, + "loss": 3.6209, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606822230360668e-05, + "loss": 3.6153, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605983635609616e-05, + "loss": 3.6086, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605145040858564e-05, + "loss": 3.6243, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604308083987885e-05, + "loss": 3.6174, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603469489236833e-05, + "loss": 3.6108, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602630894485781e-05, + "loss": 3.6174, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601792299734729e-05, + "loss": 3.6069, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600953704983677e-05, + "loss": 3.6043, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600115110232625e-05, + "loss": 3.6175, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599278153361946e-05, + "loss": 3.6133, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598439558610894e-05, + "loss": 3.6219, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597600963859842e-05, + "loss": 3.6236, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.59676236910879e-05, + "loss": 3.6103, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595923774357739e-05, + "loss": 3.6202, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.5950868174870596e-05, + "loss": 3.6214, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.5942482227360076e-05, + "loss": 3.6045, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.5934096279849556e-05, + "loss": 3.6082, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592571033233903e-05, + "loss": 3.5995, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.5917340763632245e-05, + "loss": 3.6007, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.5908954816121725e-05, + "loss": 3.6092, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.5900568868611205e-05, + "loss": 3.6215, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589218292110068e-05, + "loss": 3.6082, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588379697359016e-05, + "loss": 3.6046, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.5875427404883374e-05, + "loss": 3.6132, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5867041457372854e-05, + "loss": 3.6123, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5858655509862334e-05, + "loss": 3.6001, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.5850269562351814e-05, + "loss": 3.5905, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584189999364503e-05, + "loss": 3.6151, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.58335140461345e-05, + "loss": 3.6209, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582512809862398e-05, + "loss": 3.6209, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581674215111346e-05, + "loss": 3.6073, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580837258240668e-05, + "loss": 3.6065, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.579998663489615e-05, + "loss": 3.6026, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579160068738563e-05, + "loss": 3.6042, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578321473987511e-05, + "loss": 3.6209, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577484517116833e-05, + "loss": 3.5956, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576645922365781e-05, + "loss": 3.6303, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575807327614729e-05, + "loss": 3.6099, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574968732863677e-05, + "loss": 3.5941, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574130138112625e-05, + "loss": 3.6134, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573293181241946e-05, + "loss": 3.6043, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572454586490894e-05, + "loss": 3.5942, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571615991739842e-05, + "loss": 3.6099, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.57077739698879e-05, + "loss": 3.6168, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569938802237738e-05, + "loss": 3.5965, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569100207486686e-05, + "loss": 3.6092, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568261612735634e-05, + "loss": 3.5876, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567423017984582e-05, + "loss": 3.6054, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566586061113903e-05, + "loss": 3.6032, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565747466362851e-05, + "loss": 3.6064, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564908871611799e-05, + "loss": 3.6051, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.564070276860747e-05, + "loss": 3.6037, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563233319990068e-05, + "loss": 3.6213, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562394725239016e-05, + "loss": 3.6055, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561556130487964e-05, + "loss": 3.6117, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560717535736912e-05, + "loss": 3.6025, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559880578866233e-05, + "loss": 3.6002, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559041984115181e-05, + "loss": 3.6135, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558203389364129e-05, + "loss": 3.6038, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557364794613077e-05, + "loss": 3.6035, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556526199862025e-05, + "loss": 3.6137, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.5556892429913466e-05, + "loss": 3.6032, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.5548506482402946e-05, + "loss": 3.5865, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.5540120534892426e-05, + "loss": 3.6041, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.5531734587381906e-05, + "loss": 3.6093, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.5523348639871386e-05, + "loss": 3.5997, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.5514979071164595e-05, + "loss": 3.605, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.5506593123654075e-05, + "loss": 3.6022, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.5498207176143555e-05, + "loss": 3.5952, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.5489821228633035e-05, + "loss": 3.5981, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.5481435281122515e-05, + "loss": 3.6002, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5473065712415724e-05, + "loss": 3.612, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5464679764905204e-05, + "loss": 3.6083, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5456293817394684e-05, + "loss": 3.6131, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5447907869884164e-05, + "loss": 3.5953, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543953830117738e-05, + "loss": 3.5987, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543115235366686e-05, + "loss": 3.6029, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542276640615634e-05, + "loss": 3.6095, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541438045864581e-05, + "loss": 3.6094, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540599451113529e-05, + "loss": 3.6094, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539760856362477e-05, + "loss": 3.6018, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538923899491799e-05, + "loss": 3.5969, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538085304740746e-05, + "loss": 3.6098, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537246709989694e-05, + "loss": 3.6004, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536408115238642e-05, + "loss": 3.6012, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535571158367964e-05, + "loss": 3.6004, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534732563616912e-05, + "loss": 3.5994, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.53389396886586e-05, + "loss": 3.5994, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533055374114808e-05, + "loss": 3.5953, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532216779363756e-05, + "loss": 3.5935, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5313798224930766e-05, + "loss": 3.6059, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.5305412277420246e-05, + "loss": 3.6031, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.5297026329909726e-05, + "loss": 3.5996, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.5288640382399206e-05, + "loss": 3.61, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.5280254434888686e-05, + "loss": 3.6199, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5271868487378166e-05, + "loss": 3.5991, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.5263498918671375e-05, + "loss": 3.6015, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.5255112971160855e-05, + "loss": 3.5997, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524672702365034e-05, + "loss": 3.603, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523834107613982e-05, + "loss": 3.6015, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.522997150743303e-05, + "loss": 3.5937, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522158555992251e-05, + "loss": 3.5974, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521319961241199e-05, + "loss": 3.6053, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520481366490147e-05, + "loss": 3.6008, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519642771739095e-05, + "loss": 3.5992, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518804176988043e-05, + "loss": 3.6012, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517965582236991e-05, + "loss": 3.601, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517128625366312e-05, + "loss": 3.6043, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.51629003061526e-05, + "loss": 3.6081, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515451435864208e-05, + "loss": 3.61, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514612841113156e-05, + "loss": 3.5973, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5137758842424776e-05, + "loss": 3.6014, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.5129372894914256e-05, + "loss": 3.6074, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5120986947403736e-05, + "loss": 3.5954, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5112600999893216e-05, + "loss": 3.5988, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5104231431186425e-05, + "loss": 3.605, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5095845483675905e-05, + "loss": 3.6135, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5087459536165385e-05, + "loss": 3.6133, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5079073588654864e-05, + "loss": 3.6023, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5070687641144344e-05, + "loss": 3.603, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062318072437554e-05, + "loss": 3.603, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5053932124927034e-05, + "loss": 3.6018, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.5045546177416513e-05, + "loss": 3.5957, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.5037160229905993e-05, + "loss": 3.6037, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502879066119921e-05, + "loss": 3.5915, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502040471368869e-05, + "loss": 3.6013, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501201876617817e-05, + "loss": 3.5968, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8492636680603027, + "eval_runtime": 303.1723, + "eval_samples_per_second": 1258.66, + "eval_steps_per_second": 39.334, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.500363281866765e-05, + "loss": 3.6059, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499524687115712e-05, + "loss": 3.588, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498687730245034e-05, + "loss": 3.5973, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497849135493982e-05, + "loss": 3.6096, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497010540742929e-05, + "loss": 3.6076, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496171945991877e-05, + "loss": 3.6057, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495334989121199e-05, + "loss": 3.6053, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494496394370147e-05, + "loss": 3.5951, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.493657799619095e-05, + "loss": 3.5899, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492819204868043e-05, + "loss": 3.6026, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.491980610116991e-05, + "loss": 3.6003, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491143653246312e-05, + "loss": 3.5972, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490306696375633e-05, + "loss": 3.6049, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489468101624581e-05, + "loss": 3.5848, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488629506873529e-05, + "loss": 3.5908, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.4877909121224765e-05, + "loss": 3.5791, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.4869523173714245e-05, + "loss": 3.6009, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4861137226203725e-05, + "loss": 3.5915, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4852751278693205e-05, + "loss": 3.5955, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.4844365331182685e-05, + "loss": 3.5968, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.4835979383672165e-05, + "loss": 3.6083, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482760981496538e-05, + "loss": 3.6027, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481922386745486e-05, + "loss": 3.5966, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481083791994434e-05, + "loss": 3.5921, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480245197243382e-05, + "loss": 3.6064, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479408240372703e-05, + "loss": 3.5971, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478569645621651e-05, + "loss": 3.5905, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477731050870599e-05, + "loss": 3.6005, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476892456119547e-05, + "loss": 3.5833, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476053861368495e-05, + "loss": 3.5923, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475215266617443e-05, + "loss": 3.5997, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.474378309746764e-05, + "loss": 3.5957, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473539714995712e-05, + "loss": 3.5994, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4727011202446605e-05, + "loss": 3.6056, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4718625254936085e-05, + "loss": 3.5918, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4710239307425565e-05, + "loss": 3.6005, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4701853359915045e-05, + "loss": 3.6024, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.4693483791208254e-05, + "loss": 3.5846, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.4685097843697734e-05, + "loss": 3.5897, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.4676711896187214e-05, + "loss": 3.583, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.4668325948676694e-05, + "loss": 3.5834, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.4659940001166174e-05, + "loss": 3.5915, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.4651554053655654e-05, + "loss": 3.6026, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464318448494886e-05, + "loss": 3.589, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463479853743834e-05, + "loss": 3.5881, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462641258992782e-05, + "loss": 3.5937, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.46180266424173e-05, + "loss": 3.5947, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460965707371052e-05, + "loss": 3.582, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.46012711262e-05, + "loss": 3.5708, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459288517868948e-05, + "loss": 3.5937, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458449923117895e-05, + "loss": 3.6059, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457612966247217e-05, + "loss": 3.6, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456774371496165e-05, + "loss": 3.5853, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455935776745113e-05, + "loss": 3.589, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.45509718199406e-05, + "loss": 3.5867, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454260225123382e-05, + "loss": 3.5788, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.45342163037233e-05, + "loss": 3.6097, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452583035621278e-05, + "loss": 3.5736, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.4517444408702257e-05, + "loss": 3.609, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.4509058461191737e-05, + "loss": 3.5915, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450068889248495e-05, + "loss": 3.576, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.4492302944974426e-05, + "loss": 3.5945, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.4483916997463906e-05, + "loss": 3.5867, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.4475531049953386e-05, + "loss": 3.5747, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.44671614812466e-05, + "loss": 3.5926, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.4458775533736075e-05, + "loss": 3.5979, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.4450389586225555e-05, + "loss": 3.5792, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.4442003638715034e-05, + "loss": 3.5899, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.4433617691204514e-05, + "loss": 3.57, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.4425231743693994e-05, + "loss": 3.5865, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.441684579618348e-05, + "loss": 3.5844, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.440847622747669e-05, + "loss": 3.5881, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.440009027996617e-05, + "loss": 3.5839, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439170433245565e-05, + "loss": 3.5866, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438331838494513e-05, + "loss": 3.6027, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.437494881623834e-05, + "loss": 3.587, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436656286872782e-05, + "loss": 3.5908, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.43581769212173e-05, + "loss": 3.5852, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.434979097370678e-05, + "loss": 3.5818, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.434140502619626e-05, + "loss": 3.5944, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433303545748947e-05, + "loss": 3.5845, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432464950997895e-05, + "loss": 3.5923, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.4316263562468435e-05, + "loss": 3.5908, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.4307877614957915e-05, + "loss": 3.5898, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.4299491667447395e-05, + "loss": 3.5655, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4291122098740604e-05, + "loss": 3.588, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.4282736151230084e-05, + "loss": 3.5879, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4274350203719564e-05, + "loss": 3.5814, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4265964256209044e-05, + "loss": 3.5873, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425759468750225e-05, + "loss": 3.5822, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424920873999173e-05, + "loss": 3.5783, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424082279248121e-05, + "loss": 3.5784, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.423243684497069e-05, + "loss": 3.584, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.42240672762639e-05, + "loss": 3.5905, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421568132875338e-05, + "loss": 3.5913, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420729538124287e-05, + "loss": 3.5938, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419890943373235e-05, + "loss": 3.5829, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419053986502556e-05, + "loss": 3.5793, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418215391751504e-05, + "loss": 3.5827, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417376797000452e-05, + "loss": 3.5918, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.4165382022494e-05, + "loss": 3.5904, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415699607498348e-05, + "loss": 3.5904, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.4148626506276686e-05, + "loss": 3.5849, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.4140240558766166e-05, + "loss": 3.5796, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.4131854611255646e-05, + "loss": 3.5913, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.4123468663745126e-05, + "loss": 3.5822, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.4115099095038335e-05, + "loss": 3.581, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410671314752782e-05, + "loss": 3.5844, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.40983272000173e-05, + "loss": 3.581, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.408994125250678e-05, + "loss": 3.5797, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408157168379999e-05, + "loss": 3.5806, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.407318573628947e-05, + "loss": 3.5729, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.406479978877895e-05, + "loss": 3.5862, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405641384126843e-05, + "loss": 3.5906, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404804427256164e-05, + "loss": 3.578, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403965832505112e-05, + "loss": 3.5908, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.40312723775406e-05, + "loss": 3.5987, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402288643003008e-05, + "loss": 3.5816, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401451686132329e-05, + "loss": 3.5845, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.4006130913812776e-05, + "loss": 3.5834, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.3997744966302256e-05, + "loss": 3.5823, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.3989359018791736e-05, + "loss": 3.5824, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398097307128121e-05, + "loss": 3.5779, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397258712377069e-05, + "loss": 3.5816, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.3964217555063905e-05, + "loss": 3.5864, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.3955831607553385e-05, + "loss": 3.5815, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394744566004286e-05, + "loss": 3.5852, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393905971253234e-05, + "loss": 3.5831, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.393067376502182e-05, + "loss": 3.5832, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392230419631503e-05, + "loss": 3.5819, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.3913918248804514e-05, + "loss": 3.5962, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.3905532301293993e-05, + "loss": 3.5909, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.3897146353783473e-05, + "loss": 3.5811, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388877678507668e-05, + "loss": 3.5789, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388039083756616e-05, + "loss": 3.5925, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387200489005564e-05, + "loss": 3.575, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386361894254512e-05, + "loss": 3.586, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.38552329950346e-05, + "loss": 3.5867, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384686342632781e-05, + "loss": 3.5951, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.383847747881729e-05, + "loss": 3.5912, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383009153130677e-05, + "loss": 3.59, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382170558379625e-05, + "loss": 3.5819, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381333601508947e-05, + "loss": 3.5908, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380495006757895e-05, + "loss": 3.5799, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379656412006843e-05, + "loss": 3.578, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378817817255791e-05, + "loss": 3.5843, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3779808603851116e-05, + "loss": 3.5724, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.3771422656340596e-05, + "loss": 3.5858, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.3763036708830076e-05, + "loss": 3.5769, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.849591016769409, + "eval_runtime": 303.1829, + "eval_samples_per_second": 1258.616, + "eval_steps_per_second": 39.333, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3754650761319556e-05, + "loss": 3.5821, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3746264813809036e-05, + "loss": 3.5756, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3737878866298516e-05, + "loss": 3.5809, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3729492918787996e-05, + "loss": 3.595, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721106971277476e-05, + "loss": 3.5903, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3712737402570685e-05, + "loss": 3.5935, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3704351455060165e-05, + "loss": 3.5828, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369596550754965e-05, + "loss": 3.5786, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368757956003913e-05, + "loss": 3.5694, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367920999133234e-05, + "loss": 3.5863, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367082404382182e-05, + "loss": 3.5818, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.36624380963113e-05, + "loss": 3.579, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365406852760451e-05, + "loss": 3.5921, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364568258009399e-05, + "loss": 3.5648, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363729663258347e-05, + "loss": 3.5716, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362891068507295e-05, + "loss": 3.5694, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362052473756243e-05, + "loss": 3.5778, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361213879005191e-05, + "loss": 3.5759, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360375284254139e-05, + "loss": 3.5748, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359536689503087e-05, + "loss": 3.582, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358698094752035e-05, + "loss": 3.586, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578611378813565e-05, + "loss": 3.5855, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3570225431303045e-05, + "loss": 3.5802, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356183948379252e-05, + "loss": 3.572, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3553453536282e-05, + "loss": 3.5926, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3545083967575214e-05, + "loss": 3.5766, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.3536698020064694e-05, + "loss": 3.5733, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352831207255417e-05, + "loss": 3.5822, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.351992612504365e-05, + "loss": 3.5686, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351154017753313e-05, + "loss": 3.5752, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350317060882634e-05, + "loss": 3.5778, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349478466131582e-05, + "loss": 3.5781, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.34863987138053e-05, + "loss": 3.5834, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347801276629478e-05, + "loss": 3.5884, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346964319758799e-05, + "loss": 3.5739, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346125725007747e-05, + "loss": 3.5843, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345287130256695e-05, + "loss": 3.5878, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344448535505643e-05, + "loss": 3.5676, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343611578634964e-05, + "loss": 3.5737, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342772983883912e-05, + "loss": 3.5608, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.34193438913286e-05, + "loss": 3.57, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341095794381808e-05, + "loss": 3.568, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340258837511129e-05, + "loss": 3.59, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339420242760078e-05, + "loss": 3.5679, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338581648009026e-05, + "loss": 3.5709, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337743053257974e-05, + "loss": 3.5755, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369044585069217e-05, + "loss": 3.5779, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3360675016362426e-05, + "loss": 3.5671, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3352289068851906e-05, + "loss": 3.5547, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3343903121341386e-05, + "loss": 3.5772, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3335533552634595e-05, + "loss": 3.5839, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3327147605124075e-05, + "loss": 3.5804, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.3318761657613555e-05, + "loss": 3.5705, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.3310375710103035e-05, + "loss": 3.5665, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3301989762592515e-05, + "loss": 3.5741, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329362019388573e-05, + "loss": 3.5606, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328523424637521e-05, + "loss": 3.5907, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327684829886469e-05, + "loss": 3.56, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326846235135417e-05, + "loss": 3.5915, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326009278264738e-05, + "loss": 3.5787, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325170683513686e-05, + "loss": 3.5573, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324332088762634e-05, + "loss": 3.576, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323493494011582e-05, + "loss": 3.5736, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322656537140903e-05, + "loss": 3.5587, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321817942389851e-05, + "loss": 3.567, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320979347638799e-05, + "loss": 3.5853, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320140752887747e-05, + "loss": 3.5651, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319302158136695e-05, + "loss": 3.5693, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318463563385643e-05, + "loss": 3.5558, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176249686345915e-05, + "loss": 3.5717, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.3167880117639124e-05, + "loss": 3.5631, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.3159494170128604e-05, + "loss": 3.5702, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.3151108222618084e-05, + "loss": 3.568, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.3142722275107564e-05, + "loss": 3.5711, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.3134336327597044e-05, + "loss": 3.5833, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312596675889025e-05, + "loss": 3.5684, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311758081137973e-05, + "loss": 3.5727, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310919486386921e-05, + "loss": 3.5723, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310080891635869e-05, + "loss": 3.5676, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.30924393476519e-05, + "loss": 3.5741, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308405340014138e-05, + "loss": 3.5677, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307566745263087e-05, + "loss": 3.5703, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306728150512035e-05, + "loss": 3.5759, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305891193641356e-05, + "loss": 3.5705, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305052598890304e-05, + "loss": 3.5537, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304214004139252e-05, + "loss": 3.5703, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3033754093882e-05, + "loss": 3.5648, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302536814637147e-05, + "loss": 3.5693, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3016998577664686e-05, + "loss": 3.5673, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.3008612630154166e-05, + "loss": 3.5712, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.3000226682643646e-05, + "loss": 3.5577, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299184073513312e-05, + "loss": 3.5619, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2983471166426335e-05, + "loss": 3.564, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297508521891582e-05, + "loss": 3.577, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.29666992714053e-05, + "loss": 3.5709, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.2958313323894775e-05, + "loss": 3.5806, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.2949927376384255e-05, + "loss": 3.5602, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294155780767747e-05, + "loss": 3.5661, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.2933171860166944e-05, + "loss": 3.5667, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.2924785912656424e-05, + "loss": 3.5748, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.2916399965145904e-05, + "loss": 3.5714, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290803039643912e-05, + "loss": 3.5745, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289964444892859e-05, + "loss": 3.5669, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289125850141807e-05, + "loss": 3.5641, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288287255390756e-05, + "loss": 3.5786, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287448660639704e-05, + "loss": 3.5609, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286611703769025e-05, + "loss": 3.5634, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285773109017973e-05, + "loss": 3.5686, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284934514266921e-05, + "loss": 3.5654, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284095919515869e-05, + "loss": 3.5627, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.28325896264519e-05, + "loss": 3.5676, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282420367894138e-05, + "loss": 3.5563, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281581773143086e-05, + "loss": 3.5703, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280743178392034e-05, + "loss": 3.5711, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279906221521355e-05, + "loss": 3.5606, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279067626770303e-05, + "loss": 3.5762, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278229032019251e-05, + "loss": 3.5806, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2773904372681994e-05, + "loss": 3.5671, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.2765518425171474e-05, + "loss": 3.5693, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275714885646468e-05, + "loss": 3.5651, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274876290895416e-05, + "loss": 3.5648, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274037696144364e-05, + "loss": 3.5634, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273199101393312e-05, + "loss": 3.5618, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272362144522633e-05, + "loss": 3.5641, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271523549771581e-05, + "loss": 3.5726, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270684955020529e-05, + "loss": 3.5685, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269846360269477e-05, + "loss": 3.5636, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.269007765518425e-05, + "loss": 3.5652, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268169170767373e-05, + "loss": 3.5658, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267332213896695e-05, + "loss": 3.5624, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266493619145643e-05, + "loss": 3.5795, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265655024394591e-05, + "loss": 3.5754, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264816429643539e-05, + "loss": 3.5676, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2639794727728596e-05, + "loss": 3.5618, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2631408780218076e-05, + "loss": 3.5706, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2623022832707556e-05, + "loss": 3.5634, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.2614636885197036e-05, + "loss": 3.5669, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.2606250937686516e-05, + "loss": 3.5694, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.2597881368979725e-05, + "loss": 3.5855, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.2589495421469205e-05, + "loss": 3.5679, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.2581109473958685e-05, + "loss": 3.574, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.2572723526448165e-05, + "loss": 3.5659, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256435395774138e-05, + "loss": 3.5742, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255596801023086e-05, + "loss": 3.5639, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254758206272034e-05, + "loss": 3.5595, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253919611520982e-05, + "loss": 3.57, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253082654650303e-05, + "loss": 3.5547, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252244059899251e-05, + "loss": 3.5697, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251405465148199e-05, + "loss": 3.558, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.850817918777466, + "eval_runtime": 303.4458, + "eval_samples_per_second": 1257.526, + "eval_steps_per_second": 39.299, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250566870397147e-05, + "loss": 3.5688, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249729913526468e-05, + "loss": 3.5615, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248891318775416e-05, + "loss": 3.5612, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248052724024364e-05, + "loss": 3.5765, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247214129273312e-05, + "loss": 3.5716, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.2463771724026335e-05, + "loss": 3.5774, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.2455385776515814e-05, + "loss": 3.5634, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.2446999829005294e-05, + "loss": 3.5618, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.2438613881494774e-05, + "loss": 3.5585, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.2430244312787984e-05, + "loss": 3.5681, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.2421858365277463e-05, + "loss": 3.5669, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2413472417766943e-05, + "loss": 3.5636, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240510284906015e-05, + "loss": 3.5753, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239671690154963e-05, + "loss": 3.5507, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238833095403911e-05, + "loss": 3.5505, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.237994500652859e-05, + "loss": 3.5546, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237155905901807e-05, + "loss": 3.5577, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236317311150755e-05, + "loss": 3.5608, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235478716399703e-05, + "loss": 3.5613, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234640121648651e-05, + "loss": 3.5613, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233801526897599e-05, + "loss": 3.5704, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.23296457002692e-05, + "loss": 3.5663, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232125975275868e-05, + "loss": 3.567, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231287380524816e-05, + "loss": 3.5573, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230448785773764e-05, + "loss": 3.576, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229611828903085e-05, + "loss": 3.5614, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228773234152033e-05, + "loss": 3.5617, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227934639400981e-05, + "loss": 3.5602, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.227096044649929e-05, + "loss": 3.5547, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226257449898878e-05, + "loss": 3.5601, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.2254204930281986e-05, + "loss": 3.5602, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.2245818982771466e-05, + "loss": 3.5624, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.2237433035260946e-05, + "loss": 3.5696, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.2229047087750426e-05, + "loss": 3.5707, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2220677519043635e-05, + "loss": 3.5598, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.2212291571533115e-05, + "loss": 3.5681, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.2203905624022595e-05, + "loss": 3.5662, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.2195519676512075e-05, + "loss": 3.5539, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.2187150107805284e-05, + "loss": 3.5577, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.2178764160294764e-05, + "loss": 3.546, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.2170378212784244e-05, + "loss": 3.5567, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216199226527373e-05, + "loss": 3.5536, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215362269656694e-05, + "loss": 3.5714, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214523674905642e-05, + "loss": 3.5533, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.21368508015459e-05, + "loss": 3.5545, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212846485403538e-05, + "loss": 3.5614, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212007890652486e-05, + "loss": 3.5578, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211170933781807e-05, + "loss": 3.558, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210332339030755e-05, + "loss": 3.5328, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209493744279703e-05, + "loss": 3.56, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208655149528651e-05, + "loss": 3.5686, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207818192657972e-05, + "loss": 3.5678, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.20697959790692e-05, + "loss": 3.5539, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206141003155868e-05, + "loss": 3.5508, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.2053024084048164e-05, + "loss": 3.5585, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204465451534137e-05, + "loss": 3.5476, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203626856783085e-05, + "loss": 3.5705, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202788262032033e-05, + "loss": 3.5436, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201949667280981e-05, + "loss": 3.5773, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201112710410302e-05, + "loss": 3.5621, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.20027411565925e-05, + "loss": 3.5407, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199435520908198e-05, + "loss": 3.5575, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198596926157146e-05, + "loss": 3.5622, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197759969286467e-05, + "loss": 3.5414, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.196921374535415e-05, + "loss": 3.5479, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.196082779784363e-05, + "loss": 3.5705, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195244185033312e-05, + "loss": 3.5528, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.19440559028226e-05, + "loss": 3.5523, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193568633411581e-05, + "loss": 3.5373, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192730038660529e-05, + "loss": 3.5557, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191891443909477e-05, + "loss": 3.5481, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191052849158425e-05, + "loss": 3.5578, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.1902158922877456e-05, + "loss": 3.5485, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.1893772975366936e-05, + "loss": 3.5569, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.1885387027856416e-05, + "loss": 3.5639, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.1877001080345896e-05, + "loss": 3.5579, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.1868631511639105e-05, + "loss": 3.5552, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.1860245564128585e-05, + "loss": 3.5533, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185185961661807e-05, + "loss": 3.5556, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184347366910755e-05, + "loss": 3.5577, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183510410040076e-05, + "loss": 3.551, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182671815289024e-05, + "loss": 3.555, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181833220537972e-05, + "loss": 3.5561, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.18099462578692e-05, + "loss": 3.5551, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180157668916241e-05, + "loss": 3.5393, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.179319074165189e-05, + "loss": 3.5553, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178480479414137e-05, + "loss": 3.5502, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177641884663085e-05, + "loss": 3.5539, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176803289912033e-05, + "loss": 3.5556, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.175966333041354e-05, + "loss": 3.555, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1751277382903025e-05, + "loss": 3.5448, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.1742891435392505e-05, + "loss": 3.5447, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.1734505487881985e-05, + "loss": 3.5489, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.1726135919175194e-05, + "loss": 3.5611, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.1717749971664674e-05, + "loss": 3.5557, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.1709364024154154e-05, + "loss": 3.5628, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170097807664363e-05, + "loss": 3.5473, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169260850793684e-05, + "loss": 3.5523, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168422256042632e-05, + "loss": 3.545, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.16758366129158e-05, + "loss": 3.5614, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.1667450665405276e-05, + "loss": 3.5547, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165908109669849e-05, + "loss": 3.56, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.165069514918798e-05, + "loss": 3.5511, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164230920167746e-05, + "loss": 3.5487, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163392325416693e-05, + "loss": 3.5651, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162553730665641e-05, + "loss": 3.5411, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161716773794963e-05, + "loss": 3.5479, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.16087817904391e-05, + "loss": 3.5561, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160039584292858e-05, + "loss": 3.5459, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159200989541806e-05, + "loss": 3.5473, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158364032671128e-05, + "loss": 3.5532, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157525437920075e-05, + "loss": 3.5419, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156686843169023e-05, + "loss": 3.5555, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.1558482484179717e-05, + "loss": 3.5509, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155011291547293e-05, + "loss": 3.5521, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.1541726967962406e-05, + "loss": 3.5599, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1533341020451886e-05, + "loss": 3.5639, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.1524955072941366e-05, + "loss": 3.553, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.1516585504234575e-05, + "loss": 3.5522, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.1508199556724055e-05, + "loss": 3.5496, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.1499813609213535e-05, + "loss": 3.5503, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.1491427661703014e-05, + "loss": 3.5447, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.1483041714192494e-05, + "loss": 3.5507, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.1474672145485704e-05, + "loss": 3.544, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.1466286197975183e-05, + "loss": 3.5584, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145790025046467e-05, + "loss": 3.5513, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.144951430295415e-05, + "loss": 3.5525, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144114473424736e-05, + "loss": 3.5509, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143275878673684e-05, + "loss": 3.5495, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142437283922632e-05, + "loss": 3.5479, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.14159868917158e-05, + "loss": 3.5644, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140761732300901e-05, + "loss": 3.5604, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139923137549849e-05, + "loss": 3.5543, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.139084542798797e-05, + "loss": 3.5412, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.138245948047745e-05, + "loss": 3.5563, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137407353296693e-05, + "loss": 3.5486, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136570396426014e-05, + "loss": 3.5524, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.1357318016749624e-05, + "loss": 3.5561, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.1348932069239104e-05, + "loss": 3.5679, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.1340546121728584e-05, + "loss": 3.5521, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133217655302179e-05, + "loss": 3.5614, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132379060551127e-05, + "loss": 3.5513, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131540465800075e-05, + "loss": 3.5561, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130701871049023e-05, + "loss": 3.545, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129864914178344e-05, + "loss": 3.5474, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.129026319427292e-05, + "loss": 3.5568, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.12818772467624e-05, + "loss": 3.5397, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127349129925188e-05, + "loss": 3.5545, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126512173054509e-05, + "loss": 3.547, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.8513243198394775, + "eval_runtime": 303.1627, + "eval_samples_per_second": 1258.7, + "eval_steps_per_second": 39.335, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125673578303457e-05, + "loss": 3.5527, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124834983552406e-05, + "loss": 3.5462, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.123996388801354e-05, + "loss": 3.5457, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123157794050302e-05, + "loss": 3.5588, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.1223208371796227e-05, + "loss": 3.5596, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.1214822424285706e-05, + "loss": 3.5653, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.1206436476775186e-05, + "loss": 3.5465, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.1198050529264666e-05, + "loss": 3.5484, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.1189664581754146e-05, + "loss": 3.54, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.1181295013047355e-05, + "loss": 3.5558, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.1172909065536835e-05, + "loss": 3.5496, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.1164523118026315e-05, + "loss": 3.5487, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.1156137170515795e-05, + "loss": 3.5524, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114776760180901e-05, + "loss": 3.5432, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113938165429849e-05, + "loss": 3.5412, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113099570678797e-05, + "loss": 3.5392, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112260975927745e-05, + "loss": 3.5371, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111424019057066e-05, + "loss": 3.5432, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110585424306014e-05, + "loss": 3.5467, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109746829554962e-05, + "loss": 3.5414, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.10890823480391e-05, + "loss": 3.5593, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108071277933231e-05, + "loss": 3.551, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107232683182179e-05, + "loss": 3.5489, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106394088431127e-05, + "loss": 3.5448, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105555493680075e-05, + "loss": 3.5597, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1047185368093965e-05, + "loss": 3.543, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1038799420583445e-05, + "loss": 3.5483, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.1030413473072925e-05, + "loss": 3.541, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.1022027525562405e-05, + "loss": 3.5449, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.1013657956855614e-05, + "loss": 3.5434, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.1005272009345094e-05, + "loss": 3.5421, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.0996886061834574e-05, + "loss": 3.5521, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.0988500114324054e-05, + "loss": 3.5539, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098013054561726e-05, + "loss": 3.5505, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097174459810674e-05, + "loss": 3.5462, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096335865059622e-05, + "loss": 3.5513, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.09549727030857e-05, + "loss": 3.5515, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094660313437892e-05, + "loss": 3.5353, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.09382171868684e-05, + "loss": 3.5459, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.092983123935788e-05, + "loss": 3.5281, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092144529184736e-05, + "loss": 3.5423, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091305934433683e-05, + "loss": 3.5361, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090468977563005e-05, + "loss": 3.5583, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089630382811953e-05, + "loss": 3.5425, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088791788060901e-05, + "loss": 3.5384, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087953193309848e-05, + "loss": 3.545, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.0871162364391696e-05, + "loss": 3.5465, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0862776416881176e-05, + "loss": 3.5399, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.0854390469370656e-05, + "loss": 3.5201, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.0846004521860136e-05, + "loss": 3.5406, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083763495315335e-05, + "loss": 3.5554, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082924900564283e-05, + "loss": 3.5502, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.0820863058132305e-05, + "loss": 3.5418, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0812477110621785e-05, + "loss": 3.5343, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0804107541915e-05, + "loss": 3.5463, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0795721594404474e-05, + "loss": 3.5303, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0787335646893954e-05, + "loss": 3.5577, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.0778949699383434e-05, + "loss": 3.5284, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.0770563751872914e-05, + "loss": 3.5569, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076219418316612e-05, + "loss": 3.5508, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075380823565561e-05, + "loss": 3.5271, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074542228814509e-05, + "loss": 3.5427, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073703634063457e-05, + "loss": 3.5483, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072866677192778e-05, + "loss": 3.5243, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072028082441726e-05, + "loss": 3.5332, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071189487690674e-05, + "loss": 3.554, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070350892939622e-05, + "loss": 3.5381, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.06951229818857e-05, + "loss": 3.5349, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068675341317891e-05, + "loss": 3.5283, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067836746566839e-05, + "loss": 3.5401, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.066998151815787e-05, + "loss": 3.5302, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066159557064735e-05, + "loss": 3.5448, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.0653226001940564e-05, + "loss": 3.5321, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.0644840054430044e-05, + "loss": 3.5439, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.0636454106919524e-05, + "loss": 3.5477, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.0628068159409004e-05, + "loss": 3.5415, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.061969859070221e-05, + "loss": 3.5379, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061131264319169e-05, + "loss": 3.5379, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060292669568117e-05, + "loss": 3.5445, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059454074817065e-05, + "loss": 3.5412, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058617117946386e-05, + "loss": 3.539, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057778523195334e-05, + "loss": 3.5385, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056939928444282e-05, + "loss": 3.5411, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.05610133369323e-05, + "loss": 3.5402, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055264376822552e-05, + "loss": 3.5238, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.0544257820715e-05, + "loss": 3.5389, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053587187320448e-05, + "loss": 3.5351, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052748592569396e-05, + "loss": 3.539, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051909997818344e-05, + "loss": 3.5398, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0510730409476646e-05, + "loss": 3.5383, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502344461966126e-05, + "loss": 3.5321, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0493958514455606e-05, + "loss": 3.5257, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0485572566945086e-05, + "loss": 3.5337, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477202998238295e-05, + "loss": 3.5448, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.046881705072778e-05, + "loss": 3.5394, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.046043110321726e-05, + "loss": 3.5484, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.045204515570674e-05, + "loss": 3.5366, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0443675586999948e-05, + "loss": 3.5353, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435289639489428e-05, + "loss": 3.5315, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0426903691978907e-05, + "loss": 3.5464, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0418517744468387e-05, + "loss": 3.5385, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.04101481757616e-05, + "loss": 3.5482, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.040176222825108e-05, + "loss": 3.5339, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.039337628074056e-05, + "loss": 3.5318, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.038499033323004e-05, + "loss": 3.5503, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037662076452325e-05, + "loss": 3.53, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0368234817012732e-05, + "loss": 3.5313, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0359848869502212e-05, + "loss": 3.5383, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0351462921991692e-05, + "loss": 3.5381, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343076974481172e-05, + "loss": 3.5308, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.033470740577438e-05, + "loss": 3.5357, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.032632145826386e-05, + "loss": 3.5274, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.031793551075334e-05, + "loss": 3.5379, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0309549563242824e-05, + "loss": 3.5385, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0301179994536034e-05, + "loss": 3.5361, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0292794047025513e-05, + "loss": 3.5425, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0284408099514993e-05, + "loss": 3.556, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276022152004473e-05, + "loss": 3.5393, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0267652583297686e-05, + "loss": 3.5384, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259266635787166e-05, + "loss": 3.5334, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0250880688276646e-05, + "loss": 3.5337, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0242494740766126e-05, + "loss": 3.5315, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234108793255606e-05, + "loss": 3.5339, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0225739224548815e-05, + "loss": 3.5319, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217353277038295e-05, + "loss": 3.5428, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0208967329527778e-05, + "loss": 3.5354, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200581382017258e-05, + "loss": 3.5389, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192211813310467e-05, + "loss": 3.5338, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0183825865799947e-05, + "loss": 3.5324, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0175439918289427e-05, + "loss": 3.5319, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167053970778907e-05, + "loss": 3.5464, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015868440207212e-05, + "loss": 3.5491, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.01502984545616e-05, + "loss": 3.5424, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.014191250705108e-05, + "loss": 3.5275, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0133526559540553e-05, + "loss": 3.536, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.012515699083377e-05, + "loss": 3.5389, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.011677104332325e-05, + "loss": 3.5389, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.010838509581273e-05, + "loss": 3.5404, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0099999148302205e-05, + "loss": 3.5515, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.009162957959542e-05, + "loss": 3.5384, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.00832436320849e-05, + "loss": 3.55, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.007485768457438e-05, + "loss": 3.5339, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0066471737063857e-05, + "loss": 3.5401, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058102168357073e-05, + "loss": 3.5352, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0049716220846553e-05, + "loss": 3.5283, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0041330273336026e-05, + "loss": 3.5455, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0032944325825506e-05, + "loss": 3.5259, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0024558378314986e-05, + "loss": 3.5352, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016188809608202e-05, + "loss": 3.5337, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.000780286209768e-05, + "loss": 3.5347, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.851925849914551, + "eval_runtime": 303.1057, + "eval_samples_per_second": 1258.937, + "eval_steps_per_second": 39.343, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999941691458716e-05, + "loss": 3.5305, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999103096707664e-05, + "loss": 3.5348, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998264501956612e-05, + "loss": 3.5425, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997427545085933e-05, + "loss": 3.543, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996588950334881e-05, + "loss": 3.5519, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995750355583829e-05, + "loss": 3.532, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994911760832777e-05, + "loss": 3.5318, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994073166081725e-05, + "loss": 3.5289, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993236209211046e-05, + "loss": 3.5412, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992397614459994e-05, + "loss": 3.5333, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991559019708942e-05, + "loss": 3.5345, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907204249578903e-05, + "loss": 3.5337, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9898834680872112e-05, + "loss": 3.5288, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890448733361592e-05, + "loss": 3.5302, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882062785851072e-05, + "loss": 3.5259, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9873676838340552e-05, + "loss": 3.5235, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865307269633765e-05, + "loss": 3.5309, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9856921322123245e-05, + "loss": 3.5324, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848535374612725e-05, + "loss": 3.5289, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840149427102204e-05, + "loss": 3.5477, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9831779858395414e-05, + "loss": 3.5333, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823393910884894e-05, + "loss": 3.5369, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815007963374373e-05, + "loss": 3.5302, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806622015863857e-05, + "loss": 3.5423, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798252447157066e-05, + "loss": 3.5293, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9789866499646546e-05, + "loss": 3.5355, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781480552136026e-05, + "loss": 3.5274, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773094604625506e-05, + "loss": 3.5339, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9764725035918718e-05, + "loss": 3.5241, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756339088408198e-05, + "loss": 3.5314, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9747953140897678e-05, + "loss": 3.5382, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739567193387158e-05, + "loss": 3.534, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731197624680367e-05, + "loss": 3.5384, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9722811677169847e-05, + "loss": 3.5354, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714425729659327e-05, + "loss": 3.5321, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970603978214881e-05, + "loss": 3.5413, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969767021344202e-05, + "loss": 3.525, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.96892842659315e-05, + "loss": 3.5291, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968089831842098e-05, + "loss": 3.5168, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967251237091046e-05, + "loss": 3.5255, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966412642339994e-05, + "loss": 3.5223, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655756854693152e-05, + "loss": 3.5406, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647370907182632e-05, + "loss": 3.5268, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9638984959672112e-05, + "loss": 3.5255, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630599012161592e-05, + "loss": 3.5327, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.96222294434548e-05, + "loss": 3.5315, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961384349594428e-05, + "loss": 3.5243, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605457548433764e-05, + "loss": 3.5131, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597071600923244e-05, + "loss": 3.5198, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588702032216453e-05, + "loss": 3.5416, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580316084705933e-05, + "loss": 3.5385, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9571930137195413e-05, + "loss": 3.5262, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563544189684893e-05, + "loss": 3.5216, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555174620978106e-05, + "loss": 3.5324, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9546788673467586e-05, + "loss": 3.5178, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538402725957065e-05, + "loss": 3.5364, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530016778446545e-05, + "loss": 3.5171, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521647209739755e-05, + "loss": 3.5433, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513261262229234e-05, + "loss": 3.5344, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9504875314718718e-05, + "loss": 3.518, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496489367208198e-05, + "loss": 3.5224, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488103419697678e-05, + "loss": 3.5373, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9479733850990887e-05, + "loss": 3.509, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471347903480367e-05, + "loss": 3.5198, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9462961955969847e-05, + "loss": 3.5387, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454576008459327e-05, + "loss": 3.5272, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944620643975254e-05, + "loss": 3.5211, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943782049224202e-05, + "loss": 3.5149, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.94294345447315e-05, + "loss": 3.5205, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942104859722098e-05, + "loss": 3.5173, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9412679028514188e-05, + "loss": 3.5333, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940429308100367e-05, + "loss": 3.5188, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939590713349315e-05, + "loss": 3.5304, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938752118598263e-05, + "loss": 3.5282, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937915161727584e-05, + "loss": 3.5329, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937076566976532e-05, + "loss": 3.5213, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.93623797222548e-05, + "loss": 3.5267, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935399377474428e-05, + "loss": 3.5281, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345607827233757e-05, + "loss": 3.5282, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337238258526973e-05, + "loss": 3.5252, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9328852311016453e-05, + "loss": 3.5234, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320466363505933e-05, + "loss": 3.528, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931208041599541e-05, + "loss": 3.5241, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9303710847288622e-05, + "loss": 3.5165, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295324899778105e-05, + "loss": 3.5195, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928693895226758e-05, + "loss": 3.5274, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278553004757058e-05, + "loss": 3.5293, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270183436050274e-05, + "loss": 3.5212, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9261797488539754e-05, + "loss": 3.5228, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925341154102923e-05, + "loss": 3.5165, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924502559351871e-05, + "loss": 3.5132, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236656024811926e-05, + "loss": 3.5179, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228270077301406e-05, + "loss": 3.5282, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.921988412979088e-05, + "loss": 3.5258, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211498182280363e-05, + "loss": 3.5362, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203128613573575e-05, + "loss": 3.5306, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194742666063052e-05, + "loss": 3.5157, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186356718552532e-05, + "loss": 3.5197, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9177970771042012e-05, + "loss": 3.5274, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169601202335228e-05, + "loss": 3.5287, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161215254824704e-05, + "loss": 3.5322, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9152829307314184e-05, + "loss": 3.5198, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144443359803664e-05, + "loss": 3.5204, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913607379109688e-05, + "loss": 3.5383, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127687843586353e-05, + "loss": 3.515, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119301896075833e-05, + "loss": 3.5207, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9110915948565313e-05, + "loss": 3.5219, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102546379858526e-05, + "loss": 3.5271, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094160432348006e-05, + "loss": 3.5137, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9085774484837486e-05, + "loss": 3.5219, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077388537326966e-05, + "loss": 3.5167, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069018968620175e-05, + "loss": 3.5265, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060633021109658e-05, + "loss": 3.5214, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052247073599138e-05, + "loss": 3.5209, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9043861126088618e-05, + "loss": 3.5311, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035491557381827e-05, + "loss": 3.5381, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027105609871307e-05, + "loss": 3.5272, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9018719662360787e-05, + "loss": 3.5201, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010333714850267e-05, + "loss": 3.5208, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900194776733975e-05, + "loss": 3.5176, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.899357819863296e-05, + "loss": 3.5225, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898519225112244e-05, + "loss": 3.5202, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897680630361192e-05, + "loss": 3.5169, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.89684203561014e-05, + "loss": 3.5251, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960050787394612e-05, + "loss": 3.5231, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895166483988409e-05, + "loss": 3.523, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894327889237357e-05, + "loss": 3.5206, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893489294486305e-05, + "loss": 3.5187, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892652337615626e-05, + "loss": 3.5197, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891813742864574e-05, + "loss": 3.5315, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.890975148113522e-05, + "loss": 3.5337, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901381912428433e-05, + "loss": 3.5292, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8892995964917913e-05, + "loss": 3.5106, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8884610017407393e-05, + "loss": 3.5258, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876224069896873e-05, + "loss": 3.5226, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8867854501190082e-05, + "loss": 3.5261, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859468553679565e-05, + "loss": 3.522, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851082606169045e-05, + "loss": 3.5374, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8842696658658525e-05, + "loss": 3.5215, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834327089951734e-05, + "loss": 3.5396, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8825941142441214e-05, + "loss": 3.5176, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817555194930694e-05, + "loss": 3.5312, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809169247420174e-05, + "loss": 3.5192, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8800799678713387e-05, + "loss": 3.5168, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792413731202867e-05, + "loss": 3.5286, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784027783692347e-05, + "loss": 3.5153, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775641836181827e-05, + "loss": 3.5218, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767272267475036e-05, + "loss": 3.5186, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875888631996452e-05, + "loss": 3.5203, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8537473678588867, + "eval_runtime": 304.036, + "eval_samples_per_second": 1255.085, + "eval_steps_per_second": 39.222, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750500372454e-05, + "loss": 3.5199, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874211442494348e-05, + "loss": 3.5184, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8733744856236688e-05, + "loss": 3.5309, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725358908726168e-05, + "loss": 3.5294, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8716972961215648e-05, + "loss": 3.5384, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708587013705128e-05, + "loss": 3.5178, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870020106619461e-05, + "loss": 3.5192, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869183149748782e-05, + "loss": 3.5134, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.86834455499773e-05, + "loss": 3.5284, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867505960246678e-05, + "loss": 3.5194, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866669003375999e-05, + "loss": 3.5194, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658304086249473e-05, + "loss": 3.5227, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8649934517542682e-05, + "loss": 3.5126, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641548570032162e-05, + "loss": 3.5203, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633162622521642e-05, + "loss": 3.5095, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862477667501112e-05, + "loss": 3.5114, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.86163907275006e-05, + "loss": 3.5135, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860800477999008e-05, + "loss": 3.5163, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599618832479565e-05, + "loss": 3.5143, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591232884969045e-05, + "loss": 3.5362, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8582863316262254e-05, + "loss": 3.5169, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574477368751734e-05, + "loss": 3.5219, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566091421241214e-05, + "loss": 3.5185, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557705473730694e-05, + "loss": 3.5245, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549335905023906e-05, + "loss": 3.5201, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8540949957513386e-05, + "loss": 3.5259, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532564010002866e-05, + "loss": 3.5111, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524178062492346e-05, + "loss": 3.5193, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8515808493785555e-05, + "loss": 3.5065, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507422546275035e-05, + "loss": 3.5226, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849903659876452e-05, + "loss": 3.5212, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8490650651254e-05, + "loss": 3.522, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482281082547208e-05, + "loss": 3.5274, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8473895135036688e-05, + "loss": 3.5188, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465509187526168e-05, + "loss": 3.5212, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457123240015648e-05, + "loss": 3.5245, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844875367130886e-05, + "loss": 3.5131, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844036772379834e-05, + "loss": 3.5115, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843198177628782e-05, + "loss": 3.503, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.84235958287773e-05, + "loss": 3.5142, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841522626007051e-05, + "loss": 3.512, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840684031255999e-05, + "loss": 3.5273, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.839845436504947e-05, + "loss": 3.5141, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390068417538952e-05, + "loss": 3.5105, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838169884883216e-05, + "loss": 3.5212, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837331290132164e-05, + "loss": 3.5118, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836492695381112e-05, + "loss": 3.5145, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.83565410063006e-05, + "loss": 3.5025, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348171437593814e-05, + "loss": 3.5015, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8339785490083294e-05, + "loss": 3.5289, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331399542572774e-05, + "loss": 3.5243, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323013595062254e-05, + "loss": 3.5098, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314644026355463e-05, + "loss": 3.5129, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306258078844943e-05, + "loss": 3.5168, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8297872131334423e-05, + "loss": 3.5051, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.82894861838239e-05, + "loss": 3.5233, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281116615117115e-05, + "loss": 3.5012, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8272730667606595e-05, + "loss": 3.5275, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264344720096075e-05, + "loss": 3.5247, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825595877258555e-05, + "loss": 3.5073, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824757282507503e-05, + "loss": 3.5078, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239203256368247e-05, + "loss": 3.5226, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8230817308857727e-05, + "loss": 3.4932, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.82224313613472e-05, + "loss": 3.5111, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821404541383668e-05, + "loss": 3.5239, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205675845129896e-05, + "loss": 3.5166, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197289897619373e-05, + "loss": 3.5051, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8188903950108853e-05, + "loss": 3.5008, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180518002598333e-05, + "loss": 3.5091, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817214843389155e-05, + "loss": 3.5068, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8163762486381022e-05, + "loss": 3.5145, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155376538870505e-05, + "loss": 3.5051, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8146990591359985e-05, + "loss": 3.5169, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.81386210226532e-05, + "loss": 3.5185, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130235075142674e-05, + "loss": 3.5203, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8121849127632154e-05, + "loss": 3.507, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113463180121634e-05, + "loss": 3.513, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105093611414847e-05, + "loss": 3.5139, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096707663904326e-05, + "loss": 3.5127, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088321716393806e-05, + "loss": 3.5153, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8079935768883286e-05, + "loss": 3.5122, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071566200176495e-05, + "loss": 3.5152, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063180252665975e-05, + "loss": 3.5108, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805479430515546e-05, + "loss": 3.4997, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804640835764494e-05, + "loss": 3.5058, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038038788938148e-05, + "loss": 3.5102, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8029652841427628e-05, + "loss": 3.5166, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021266893917108e-05, + "loss": 3.5116, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8012880946406588e-05, + "loss": 3.5085, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.80045113776998e-05, + "loss": 3.5033, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799612543018928e-05, + "loss": 3.5009, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798773948267876e-05, + "loss": 3.503, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797935353516824e-05, + "loss": 3.5165, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797098396646145e-05, + "loss": 3.5131, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796259801895093e-05, + "loss": 3.5212, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954212071440412e-05, + "loss": 3.5142, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7945826123929892e-05, + "loss": 3.504, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.79374565552231e-05, + "loss": 3.5074, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792907060771258e-05, + "loss": 3.5119, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.792068466020206e-05, + "loss": 3.5186, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791229871269154e-05, + "loss": 3.5185, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7903929143984754e-05, + "loss": 3.509, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895543196474234e-05, + "loss": 3.5024, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887157248963714e-05, + "loss": 3.5233, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7878771301453194e-05, + "loss": 3.4989, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870401732746403e-05, + "loss": 3.5092, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862015785235883e-05, + "loss": 3.509, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853629837725366e-05, + "loss": 3.5112, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845243890214846e-05, + "loss": 3.4997, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7836874321508055e-05, + "loss": 3.5125, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828488373997535e-05, + "loss": 3.5019, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820102426487015e-05, + "loss": 3.51, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811716478976495e-05, + "loss": 3.5131, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803346910269708e-05, + "loss": 3.5044, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7794960962759187e-05, + "loss": 3.5218, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786575015248667e-05, + "loss": 3.5252, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778189067738147e-05, + "loss": 3.5141, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7769803120227627e-05, + "loss": 3.5084, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761433551520836e-05, + "loss": 3.5087, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775304760401032e-05, + "loss": 3.5089, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.77446616564998e-05, + "loss": 3.5035, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773627570898928e-05, + "loss": 3.5125, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772790614028249e-05, + "loss": 3.4987, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771952019277197e-05, + "loss": 3.5088, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771113424526145e-05, + "loss": 3.513, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770276467655466e-05, + "loss": 3.5153, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769437872904414e-05, + "loss": 3.5022, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768599278153362e-05, + "loss": 3.5045, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.76776068340231e-05, + "loss": 3.513, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766923726531631e-05, + "loss": 3.5116, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766085131780579e-05, + "loss": 3.5205, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652465370295273e-05, + "loss": 3.5167, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644079422784753e-05, + "loss": 3.4978, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635709854077963e-05, + "loss": 3.5114, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627323906567442e-05, + "loss": 3.5121, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7618937959056922e-05, + "loss": 3.5088, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610552011546402e-05, + "loss": 3.5107, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602182442839615e-05, + "loss": 3.5198, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7593796495329095e-05, + "loss": 3.5104, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585410547818575e-05, + "loss": 3.5279, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577024600308055e-05, + "loss": 3.5076, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568655031601264e-05, + "loss": 3.5138, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560269084090744e-05, + "loss": 3.5072, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7551883136580227e-05, + "loss": 3.5045, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543497189069707e-05, + "loss": 3.5122, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535127620362916e-05, + "loss": 3.5067, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7526741672852396e-05, + "loss": 3.5079, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518355725341876e-05, + "loss": 3.5023, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7509969777831356e-05, + "loss": 3.5052, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8550965785980225, + "eval_runtime": 303.9798, + "eval_samples_per_second": 1255.317, + "eval_steps_per_second": 39.23, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501583830320836e-05, + "loss": 3.5061, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493197882810316e-05, + "loss": 3.5062, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.74848119352998e-05, + "loss": 3.5186, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747642598778928e-05, + "loss": 3.5128, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746805641908249e-05, + "loss": 3.5287, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.745967047157197e-05, + "loss": 3.5033, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451284524061448e-05, + "loss": 3.5089, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.744291495535466e-05, + "loss": 3.4983, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743452900784414e-05, + "loss": 3.5157, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742614306033362e-05, + "loss": 3.5102, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.74177571128231e-05, + "loss": 3.5039, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740938754411631e-05, + "loss": 3.5152, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401017975409522e-05, + "loss": 3.4981, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392632027899002e-05, + "loss": 3.5096, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384246080388482e-05, + "loss": 3.4954, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7375860132877962e-05, + "loss": 3.5001, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367474185367442e-05, + "loss": 3.4946, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359088237856922e-05, + "loss": 3.5062, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.73507022903464e-05, + "loss": 3.5016, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734231634283588e-05, + "loss": 3.522, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7333946774129094e-05, + "loss": 3.5074, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325560826618574e-05, + "loss": 3.5076, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317174879108048e-05, + "loss": 3.5039, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7308788931597527e-05, + "loss": 3.5132, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300419362890743e-05, + "loss": 3.5046, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292033415380223e-05, + "loss": 3.5143, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.72836474678697e-05, + "loss": 3.4998, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727526152035918e-05, + "loss": 3.506, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7266891951652396e-05, + "loss": 3.4925, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725850600414187e-05, + "loss": 3.51, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250120056631352e-05, + "loss": 3.5095, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7241750487924568e-05, + "loss": 3.5082, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233364540414048e-05, + "loss": 3.5171, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722497859290352e-05, + "loss": 3.5073, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216592645393e-05, + "loss": 3.5035, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208223076686217e-05, + "loss": 3.5143, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7199837129175697e-05, + "loss": 3.5027, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191451181665174e-05, + "loss": 3.498, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183065234154654e-05, + "loss": 3.4911, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717469566544787e-05, + "loss": 3.4996, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166309717937343e-05, + "loss": 3.4975, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7157923770426823e-05, + "loss": 3.5123, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149537822916306e-05, + "loss": 3.5069, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141168254209522e-05, + "loss": 3.4943, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7132782306698995e-05, + "loss": 3.5103, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124396359188475e-05, + "loss": 3.5013, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116010411677955e-05, + "loss": 3.4965, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107624464167435e-05, + "loss": 3.4919, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099254895460647e-05, + "loss": 3.4857, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7090868947950127e-05, + "loss": 3.5157, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082483000439607e-05, + "loss": 3.511, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074097052929087e-05, + "loss": 3.4982, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7065727484222296e-05, + "loss": 3.5003, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057341536711776e-05, + "loss": 3.5074, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.704895558920126e-05, + "loss": 3.4878, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704056964169074e-05, + "loss": 3.5109, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703220007298395e-05, + "loss": 3.4909, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702381412547343e-05, + "loss": 3.5091, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701542817796291e-05, + "loss": 3.5152, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700704223045239e-05, + "loss": 3.4968, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.69986726617456e-05, + "loss": 3.4899, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.699028671423508e-05, + "loss": 3.509, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698190076672456e-05, + "loss": 3.4837, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697351481921404e-05, + "loss": 3.497, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696514525050725e-05, + "loss": 3.5067, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695675930299673e-05, + "loss": 3.5062, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948373355486213e-05, + "loss": 3.4941, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6939987407975693e-05, + "loss": 3.488, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931617839268902e-05, + "loss": 3.4912, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923231891758382e-05, + "loss": 3.491, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6914845944247862e-05, + "loss": 3.5036, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906459996737342e-05, + "loss": 3.4932, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898090428030555e-05, + "loss": 3.5066, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6889704480520035e-05, + "loss": 3.505, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881318533009515e-05, + "loss": 3.5077, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6872932585498994e-05, + "loss": 3.493, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864563016792204e-05, + "loss": 3.5018, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856177069281684e-05, + "loss": 3.5056, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6847791121771167e-05, + "loss": 3.4981, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839405174260647e-05, + "loss": 3.5039, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831035605553856e-05, + "loss": 3.4998, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822649658043336e-05, + "loss": 3.5, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814263710532816e-05, + "loss": 3.4969, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6805877763022296e-05, + "loss": 3.4856, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797508194315508e-05, + "loss": 3.4977, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789122246804988e-05, + "loss": 3.495, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6780736299294468e-05, + "loss": 3.5047, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772350351783948e-05, + "loss": 3.4994, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6763980783077157e-05, + "loss": 3.4978, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755594835566637e-05, + "loss": 3.4928, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674720888805612e-05, + "loss": 3.4894, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.67388229405456e-05, + "loss": 3.4875, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.673045337183881e-05, + "loss": 3.5015, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672206742432829e-05, + "loss": 3.5082, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671368147681777e-05, + "loss": 3.5056, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670529552930725e-05, + "loss": 3.4998, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6696925960600462e-05, + "loss": 3.4919, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688540013089942e-05, + "loss": 3.4967, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680154065579422e-05, + "loss": 3.4967, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6671768118068902e-05, + "loss": 3.5073, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666339854936211e-05, + "loss": 3.505, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665501260185159e-05, + "loss": 3.4977, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646626654341074e-05, + "loss": 3.4909, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638240706830554e-05, + "loss": 3.5135, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6629871138123763e-05, + "loss": 3.4854, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621485190613243e-05, + "loss": 3.5001, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613099243102723e-05, + "loss": 3.4903, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6604713295592203e-05, + "loss": 3.4999, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596343726885416e-05, + "loss": 3.4901, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6587957779374896e-05, + "loss": 3.5026, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579571831864376e-05, + "loss": 3.493, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571185884353855e-05, + "loss": 3.4927, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6562816315647065e-05, + "loss": 3.5011, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554430368136545e-05, + "loss": 3.4901, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546044420626024e-05, + "loss": 3.5115, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537658473115508e-05, + "loss": 3.5097, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529288904408717e-05, + "loss": 3.5016, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6520902956898197e-05, + "loss": 3.4958, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512517009387677e-05, + "loss": 3.4958, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504131061877157e-05, + "loss": 3.4956, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.649576149317037e-05, + "loss": 3.4933, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648737554565985e-05, + "loss": 3.5002, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647898959814933e-05, + "loss": 3.4872, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.647060365063881e-05, + "loss": 3.4981, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462234081932018e-05, + "loss": 3.5008, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6453848134421498e-05, + "loss": 3.5011, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445462186910978e-05, + "loss": 3.492, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643707623940046e-05, + "loss": 3.4918, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642870667069367e-05, + "loss": 3.5024, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642032072318315e-05, + "loss": 3.5003, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641193477567263e-05, + "loss": 3.5024, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.640354882816211e-05, + "loss": 3.5079, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395179259455323e-05, + "loss": 3.4874, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6386793311944803e-05, + "loss": 3.4994, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378407364434283e-05, + "loss": 3.5004, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370021416923763e-05, + "loss": 3.4954, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361651848216972e-05, + "loss": 3.4978, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353265900706452e-05, + "loss": 3.5096, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6344879953195932e-05, + "loss": 3.4965, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336494005685415e-05, + "loss": 3.516, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328124436978624e-05, + "loss": 3.4946, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6319738489468104e-05, + "loss": 3.4982, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311352541957584e-05, + "loss": 3.4975, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6302966594447064e-05, + "loss": 3.4928, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294597025740277e-05, + "loss": 3.4979, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286211078229757e-05, + "loss": 3.4959, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6277825130719237e-05, + "loss": 3.4944, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269439183208716e-05, + "loss": 3.49, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261069614501926e-05, + "loss": 3.4959, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.854766845703125, + "eval_runtime": 302.7824, + "eval_samples_per_second": 1260.281, + "eval_steps_per_second": 39.385, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6252683666991406e-05, + "loss": 3.4945, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244297719480885e-05, + "loss": 3.4901, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.623591177197037e-05, + "loss": 3.5037, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227525824459842e-05, + "loss": 3.4996, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219156255753058e-05, + "loss": 3.5176, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6210770308242538e-05, + "loss": 3.4926, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202384360732018e-05, + "loss": 3.4967, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6193998413221494e-05, + "loss": 3.4841, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618562884451471e-05, + "loss": 3.502, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.617724289700419e-05, + "loss": 3.4964, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6168856949493663e-05, + "loss": 3.4896, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160471001983143e-05, + "loss": 3.4974, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152117812080092e-05, + "loss": 3.491, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.614373186456957e-05, + "loss": 3.495, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.613534591705905e-05, + "loss": 3.4842, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.612695996954853e-05, + "loss": 3.4862, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611857402203801e-05, + "loss": 3.4824, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611018807452749e-05, + "loss": 3.4917, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6101802127016968e-05, + "loss": 3.4898, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093416179506448e-05, + "loss": 3.5095, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085046610799664e-05, + "loss": 3.494, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6076660663289137e-05, + "loss": 3.5011, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068274715778617e-05, + "loss": 3.4901, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6059888768268097e-05, + "loss": 3.499, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051519199561313e-05, + "loss": 3.4924, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.604313325205079e-05, + "loss": 3.4984, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603474730454027e-05, + "loss": 3.4898, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.602636135702975e-05, + "loss": 3.4878, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6017991788322965e-05, + "loss": 3.4834, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.600960584081244e-05, + "loss": 3.4951, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001219893301922e-05, + "loss": 3.5007, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5992833945791402e-05, + "loss": 3.4951, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598446437708461e-05, + "loss": 3.5066, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597607842957409e-05, + "loss": 3.4956, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596769248206357e-05, + "loss": 3.489, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959322913356787e-05, + "loss": 3.4971, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5950936965846263e-05, + "loss": 3.4973, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5942551018335743e-05, + "loss": 3.4802, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934165070825223e-05, + "loss": 3.4793, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.592579550211844e-05, + "loss": 3.4859, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917409554607912e-05, + "loss": 3.4923, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909023607097392e-05, + "loss": 3.4953, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5900637659586875e-05, + "loss": 3.4953, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892268090880085e-05, + "loss": 3.4816, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5883882143369564e-05, + "loss": 3.4964, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5875496195859044e-05, + "loss": 3.4907, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867110248348524e-05, + "loss": 3.4866, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5858724300838004e-05, + "loss": 3.4787, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850354732131217e-05, + "loss": 3.4682, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5841968784620697e-05, + "loss": 3.5107, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5833582837110177e-05, + "loss": 3.4969, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825196889599657e-05, + "loss": 3.4893, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5816827320892866e-05, + "loss": 3.4895, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5808441373382346e-05, + "loss": 3.4868, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.580005542587183e-05, + "loss": 3.4784, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.579166947836131e-05, + "loss": 3.4946, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783299909654518e-05, + "loss": 3.4837, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5774913962143998e-05, + "loss": 3.4916, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766528014633478e-05, + "loss": 3.5055, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.575815844592669e-05, + "loss": 3.4852, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.574977249841617e-05, + "loss": 3.4769, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.574138655090565e-05, + "loss": 3.5023, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.573300060339513e-05, + "loss": 3.4727, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.572463103468834e-05, + "loss": 3.4807, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.571624508717782e-05, + "loss": 3.4982, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.57078591396673e-05, + "loss": 3.4935, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5699473192156783e-05, + "loss": 3.4823, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691103623449992e-05, + "loss": 3.4827, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5682717675939472e-05, + "loss": 3.476, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674331728428952e-05, + "loss": 3.4797, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5665945780918432e-05, + "loss": 3.4935, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5657576212211644e-05, + "loss": 3.4765, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649190264701124e-05, + "loss": 3.4965, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5640804317190604e-05, + "loss": 3.4878, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632418369680084e-05, + "loss": 3.4997, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624048800973293e-05, + "loss": 3.4831, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5615662853462773e-05, + "loss": 3.4834, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607276905952253e-05, + "loss": 3.4922, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5598890958441733e-05, + "loss": 3.4825, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590521389734946e-05, + "loss": 3.4952, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582135442224425e-05, + "loss": 3.4872, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5573749494713905e-05, + "loss": 3.4859, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565363547203385e-05, + "loss": 3.4873, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5556993978496594e-05, + "loss": 3.4759, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548608030986078e-05, + "loss": 3.4831, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540222083475558e-05, + "loss": 3.4865, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5531836135965038e-05, + "loss": 3.4916, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523466567258247e-05, + "loss": 3.4846, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515080619747727e-05, + "loss": 3.4863, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5506694672237207e-05, + "loss": 3.4791, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498308724726687e-05, + "loss": 3.4768, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.54899391560199e-05, + "loss": 3.4783, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.548155320850938e-05, + "loss": 3.4841, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.547316726099886e-05, + "loss": 3.4959, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.546478131348834e-05, + "loss": 3.4997, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456411744781548e-05, + "loss": 3.4868, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.544802579727103e-05, + "loss": 3.4757, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.543963984976051e-05, + "loss": 3.4843, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.543125390224999e-05, + "loss": 3.4854, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.54228843335432e-05, + "loss": 3.4912, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.541449838603268e-05, + "loss": 3.4926, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.540611243852216e-05, + "loss": 3.4868, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539772649101164e-05, + "loss": 3.4782, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5389356922304853e-05, + "loss": 3.5014, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5380970974794333e-05, + "loss": 3.4704, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5372585027283813e-05, + "loss": 3.4893, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364199079773293e-05, + "loss": 3.4767, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5355829511066502e-05, + "loss": 3.4875, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347443563555985e-05, + "loss": 3.4772, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339057616045465e-05, + "loss": 3.4882, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5330671668534945e-05, + "loss": 3.4819, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322302099828154e-05, + "loss": 3.4803, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5313916152317634e-05, + "loss": 3.4867, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305530204807114e-05, + "loss": 3.4792, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297144257296594e-05, + "loss": 3.4973, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5288774688589807e-05, + "loss": 3.4967, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280388741079286e-05, + "loss": 3.4898, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272002793568766e-05, + "loss": 3.4829, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5263616846058246e-05, + "loss": 3.4861, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255247277351455e-05, + "loss": 3.4809, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524686132984094e-05, + "loss": 3.4825, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.523847538233042e-05, + "loss": 3.4879, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.52300894348199e-05, + "loss": 3.4712, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5221719866113108e-05, + "loss": 3.487, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213333918602588e-05, + "loss": 3.4858, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5204947971092068e-05, + "loss": 3.49, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196562023581548e-05, + "loss": 3.479, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.518819245487476e-05, + "loss": 3.4808, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.517980650736424e-05, + "loss": 3.4835, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517142055985372e-05, + "loss": 3.4954, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.51630346123432e-05, + "loss": 3.4876, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.515466504363641e-05, + "loss": 3.4964, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146279096125892e-05, + "loss": 3.4732, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5137893148615372e-05, + "loss": 3.4895, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5129507201104852e-05, + "loss": 3.4885, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.512113763239806e-05, + "loss": 3.4827, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511275168488754e-05, + "loss": 3.4838, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510436573737702e-05, + "loss": 3.4984, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.50959797898665e-05, + "loss": 3.4864, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087610221159714e-05, + "loss": 3.5059, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079224273649194e-05, + "loss": 3.4808, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5070838326138674e-05, + "loss": 3.4894, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062452378628154e-05, + "loss": 3.481, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054082809921363e-05, + "loss": 3.4822, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5045696862410846e-05, + "loss": 3.4874, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037310914900326e-05, + "loss": 3.4835, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5028924967389806e-05, + "loss": 3.4811, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020555398683015e-05, + "loss": 3.4755, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012169451172495e-05, + "loss": 3.4838, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8566389083862305, + "eval_runtime": 309.8866, + "eval_samples_per_second": 1231.389, + "eval_steps_per_second": 38.482, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.5003783503661975e-05, + "loss": 3.4859, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.4995397556151455e-05, + "loss": 3.4788, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4987027987444668e-05, + "loss": 3.4942, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4978642039934144e-05, + "loss": 3.4882, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4970256092423624e-05, + "loss": 3.5037, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4961870144913104e-05, + "loss": 3.4845, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4953500576206316e-05, + "loss": 3.4838, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4945114628695796e-05, + "loss": 3.4744, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4936728681185276e-05, + "loss": 3.4889, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4928342733674756e-05, + "loss": 3.4846, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4919973164967965e-05, + "loss": 3.4824, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4911587217457445e-05, + "loss": 3.4839, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.490321764875066e-05, + "loss": 3.4768, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.489483170124014e-05, + "loss": 3.4851, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4886445753729618e-05, + "loss": 3.4727, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4878059806219098e-05, + "loss": 3.4739, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4869673858708578e-05, + "loss": 3.473, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4861287911198058e-05, + "loss": 3.4837, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4852901963687538e-05, + "loss": 3.4758, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4844516016177018e-05, + "loss": 3.4953, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.483614644747023e-05, + "loss": 3.4837, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.482776049995971e-05, + "loss": 3.4918, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.481937455244919e-05, + "loss": 3.4768, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.481098860493867e-05, + "loss": 3.4846, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.480261903623188e-05, + "loss": 3.4815, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794233088721362e-05, + "loss": 3.4884, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4785847141210842e-05, + "loss": 3.4773, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4777461193700322e-05, + "loss": 3.4775, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.476909162499353e-05, + "loss": 3.4719, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.476070567748301e-05, + "loss": 3.4804, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.475231972997249e-05, + "loss": 3.4877, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.474393378246197e-05, + "loss": 3.4839, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4735564213755184e-05, + "loss": 3.4927, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727178266244664e-05, + "loss": 3.4804, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4718792318734144e-05, + "loss": 3.4794, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.471040637122362e-05, + "loss": 3.4887, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.4702036802516833e-05, + "loss": 3.4864, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4693650855006316e-05, + "loss": 3.4678, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4685264907495796e-05, + "loss": 3.472, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4676878959985273e-05, + "loss": 3.4706, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4668509391278485e-05, + "loss": 3.4739, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4660123443767965e-05, + "loss": 3.4871, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.465173749625744e-05, + "loss": 3.4797, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.4643351548746925e-05, + "loss": 3.4758, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.4634981980040137e-05, + "loss": 3.4828, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4626596032529617e-05, + "loss": 3.4752, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4618210085019094e-05, + "loss": 3.4762, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4609824137508574e-05, + "loss": 3.4702, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4601454568801786e-05, + "loss": 3.4509, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459306862129127e-05, + "loss": 3.4977, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4584682673780746e-05, + "loss": 3.4845, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4576296726270226e-05, + "loss": 3.4838, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456792715756344e-05, + "loss": 3.4753, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4559541210052915e-05, + "loss": 3.477, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551155262542395e-05, + "loss": 3.465, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.454276931503188e-05, + "loss": 3.4819, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.453439974632509e-05, + "loss": 3.475, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4526013798814568e-05, + "loss": 3.4779, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4517627851304048e-05, + "loss": 3.4938, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4509241903793528e-05, + "loss": 3.4729, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.450087233508674e-05, + "loss": 3.4689, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.449248638757622e-05, + "loss": 3.4903, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.44841004400657e-05, + "loss": 3.4592, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4475730871358912e-05, + "loss": 3.4726, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.446734492384839e-05, + "loss": 3.4841, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.445895897633787e-05, + "loss": 3.4805, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.445057302882735e-05, + "loss": 3.4692, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442203460120565e-05, + "loss": 3.471, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.443381751261004e-05, + "loss": 3.46, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.442543156509952e-05, + "loss": 3.47, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4417045617589e-05, + "loss": 3.4797, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4408676048882214e-05, + "loss": 3.4676, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4400290101371694e-05, + "loss": 3.4825, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4391904153861174e-05, + "loss": 3.4789, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4383518206350654e-05, + "loss": 3.4889, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375132258840134e-05, + "loss": 3.4714, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4366746311329614e-05, + "loss": 3.4711, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4358360363819093e-05, + "loss": 3.4806, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4349990795112303e-05, + "loss": 3.4683, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4341604847601786e-05, + "loss": 3.4846, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333218900091266e-05, + "loss": 3.4765, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4324832952580746e-05, + "loss": 3.4748, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4316463383873955e-05, + "loss": 3.477, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4308093815167164e-05, + "loss": 3.4641, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4299707867656647e-05, + "loss": 3.4698, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4291321920146127e-05, + "loss": 3.4732, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4282935972635607e-05, + "loss": 3.4802, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4274550025125087e-05, + "loss": 3.4671, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4266164077614567e-05, + "loss": 3.4745, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4257778130104044e-05, + "loss": 3.4667, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4249392182593524e-05, + "loss": 3.47, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.424102261388674e-05, + "loss": 3.463, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.423263666637622e-05, + "loss": 3.4771, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4224250718865696e-05, + "loss": 3.4808, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.421588115015891e-05, + "loss": 3.4823, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.420749520264839e-05, + "loss": 3.4811, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4199109255137865e-05, + "loss": 3.4639, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.419072330762735e-05, + "loss": 3.4715, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.418235373892056e-05, + "loss": 3.4737, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.417396779141004e-05, + "loss": 3.481, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4165581843899517e-05, + "loss": 3.479, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4157195896388997e-05, + "loss": 3.474, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.414882632768221e-05, + "loss": 3.4707, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4140440380171693e-05, + "loss": 3.4876, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.413205443266117e-05, + "loss": 3.4613, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.412366848515065e-05, + "loss": 3.4766, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.4115298916443862e-05, + "loss": 3.4641, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.410691296893334e-05, + "loss": 3.4781, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.409852702142282e-05, + "loss": 3.4636, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4090141073912302e-05, + "loss": 3.4768, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4081771505205515e-05, + "loss": 3.4676, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.407338555769499e-05, + "loss": 3.4712, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.406499961018447e-05, + "loss": 3.4741, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.405661366267395e-05, + "loss": 3.4717, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4048244093967164e-05, + "loss": 3.4828, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4039858146456644e-05, + "loss": 3.486, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4031472198946123e-05, + "loss": 3.4758, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023086251435603e-05, + "loss": 3.4763, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4014716682728813e-05, + "loss": 3.4713, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4006330735218292e-05, + "loss": 3.4708, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3997944787707772e-05, + "loss": 3.4683, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3989558840197256e-05, + "loss": 3.4802, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3981189271490465e-05, + "loss": 3.457, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3972803323979945e-05, + "loss": 3.4757, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3964417376469425e-05, + "loss": 3.4717, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3956031428958905e-05, + "loss": 3.4797, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3947661860252117e-05, + "loss": 3.4708, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3939275912741597e-05, + "loss": 3.4694, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3930889965231077e-05, + "loss": 3.4705, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3922504017720557e-05, + "loss": 3.4824, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3914134449013766e-05, + "loss": 3.4794, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3905748501503246e-05, + "loss": 3.4831, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3897362553992726e-05, + "loss": 3.4636, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.388897660648221e-05, + "loss": 3.4765, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.388060703777542e-05, + "loss": 3.4756, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.38722210902649e-05, + "loss": 3.4699, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386383514275438e-05, + "loss": 3.4722, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385544919524386e-05, + "loss": 3.4849, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384707962653707e-05, + "loss": 3.4742, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.383869367902655e-05, + "loss": 3.4962, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.383030773151603e-05, + "loss": 3.4703, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.382192178400551e-05, + "loss": 3.4773, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.381355221529872e-05, + "loss": 3.467, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.38051662677882e-05, + "loss": 3.4711, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.379678032027768e-05, + "loss": 3.4773, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3788394372767163e-05, + "loss": 3.4722, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780024804060372e-05, + "loss": 3.4748, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3771638856549852e-05, + "loss": 3.4571, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3763252909039332e-05, + "loss": 3.4748, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.858839988708496, + "eval_runtime": 310.4692, + "eval_samples_per_second": 1229.078, + "eval_steps_per_second": 38.41, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3754866961528812e-05, + "loss": 3.4729, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3746481014018292e-05, + "loss": 3.4699, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738095066507772e-05, + "loss": 3.4809, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3729709118997252e-05, + "loss": 3.4775, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721339550290464e-05, + "loss": 3.4872, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.371295360277994e-05, + "loss": 3.4713, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3704584034073153e-05, + "loss": 3.4727, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696198086562633e-05, + "loss": 3.4618, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3687812139052117e-05, + "loss": 3.4755, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679426191541593e-05, + "loss": 3.4732, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671040244031073e-05, + "loss": 3.4747, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3662654296520553e-05, + "loss": 3.4657, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654284727813762e-05, + "loss": 3.4727, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3645898780303242e-05, + "loss": 3.4658, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3637512832792726e-05, + "loss": 3.4627, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629126885282206e-05, + "loss": 3.4596, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3620740937771686e-05, + "loss": 3.4617, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612354990261166e-05, + "loss": 3.4712, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3603969042750645e-05, + "loss": 3.465, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3595583095240122e-05, + "loss": 3.4843, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587213526533335e-05, + "loss": 3.4748, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3578827579022818e-05, + "loss": 3.4799, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570441631512298e-05, + "loss": 3.466, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562055684001774e-05, + "loss": 3.4707, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3553686115294987e-05, + "loss": 3.4694, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545300167784467e-05, + "loss": 3.4806, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3536914220273947e-05, + "loss": 3.4678, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528528272763427e-05, + "loss": 3.4649, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.352015870405664e-05, + "loss": 3.4613, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351177275654612e-05, + "loss": 3.4694, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3503386809035596e-05, + "loss": 3.4745, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495000861525076e-05, + "loss": 3.474, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486631292818288e-05, + "loss": 3.4771, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.347824534530777e-05, + "loss": 3.4742, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3469859397797248e-05, + "loss": 3.4702, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3461473450286728e-05, + "loss": 3.475, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345310388157994e-05, + "loss": 3.4735, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3444717934069417e-05, + "loss": 3.4605, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436331986558897e-05, + "loss": 3.4596, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.342794603904838e-05, + "loss": 3.4601, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419576470341593e-05, + "loss": 3.4614, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.341119052283107e-05, + "loss": 3.4764, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340280457532055e-05, + "loss": 3.4711, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339441862781003e-05, + "loss": 3.4609, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386049059103242e-05, + "loss": 3.4706, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3377663111592722e-05, + "loss": 3.4648, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369277164082202e-05, + "loss": 3.4668, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3360891216571682e-05, + "loss": 3.4575, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335252164786489e-05, + "loss": 3.4395, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334413570035437e-05, + "loss": 3.4882, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333574975284385e-05, + "loss": 3.4694, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327363805333334e-05, + "loss": 3.475, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3318994236626543e-05, + "loss": 3.4595, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3310608289116023e-05, + "loss": 3.4689, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302222341605503e-05, + "loss": 3.4543, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3293852772898716e-05, + "loss": 3.4672, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285466825388196e-05, + "loss": 3.467, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277080877877675e-05, + "loss": 3.4653, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3268694930367155e-05, + "loss": 3.4833, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260325361660365e-05, + "loss": 3.4606, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3251939414149844e-05, + "loss": 3.4542, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243553466639324e-05, + "loss": 3.4804, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235167519128804e-05, + "loss": 3.4474, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3226797950422017e-05, + "loss": 3.4566, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3218412002911497e-05, + "loss": 3.4732, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3210026055400977e-05, + "loss": 3.4733, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3201640107890457e-05, + "loss": 3.4559, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193270539183666e-05, + "loss": 3.4644, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318488459167315e-05, + "loss": 3.4482, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317649864416263e-05, + "loss": 3.4613, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316811269665211e-05, + "loss": 3.4666, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3159743127945318e-05, + "loss": 3.455, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3151357180434798e-05, + "loss": 3.4715, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3142971232924278e-05, + "loss": 3.4655, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134585285413758e-05, + "loss": 3.4787, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.312621571670697e-05, + "loss": 3.4577, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.311782976919645e-05, + "loss": 3.4645, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.310944382168593e-05, + "loss": 3.4675, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.310105787417541e-05, + "loss": 3.4569, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309268830546862e-05, + "loss": 3.4715, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084302357958103e-05, + "loss": 3.4653, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3075916410447583e-05, + "loss": 3.4634, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067530462937063e-05, + "loss": 3.4663, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059160894230272e-05, + "loss": 3.4548, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3050774946719752e-05, + "loss": 3.455, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3042388999209232e-05, + "loss": 3.4625, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034003051698712e-05, + "loss": 3.4681, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025633482991924e-05, + "loss": 3.4597, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017247535481404e-05, + "loss": 3.4637, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3008861587970884e-05, + "loss": 3.4499, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000475640460364e-05, + "loss": 3.4616, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992106071753573e-05, + "loss": 3.4537, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2983720124243057e-05, + "loss": 3.4634, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975334176732536e-05, + "loss": 3.4754, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2966948229222016e-05, + "loss": 3.4672, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958578660515226e-05, + "loss": 3.4695, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950192713004705e-05, + "loss": 3.4518, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2941806765494185e-05, + "loss": 3.4618, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933420817983665e-05, + "loss": 3.4601, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925051249276878e-05, + "loss": 3.4709, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2916665301766358e-05, + "loss": 3.4644, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908279354255838e-05, + "loss": 3.4683, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2899893406745314e-05, + "loss": 3.4586, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891523838038527e-05, + "loss": 3.4731, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288313789052801e-05, + "loss": 3.4541, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287475194301749e-05, + "loss": 3.4649, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866365995506967e-05, + "loss": 3.4512, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285799642680018e-05, + "loss": 3.4688, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284961047928966e-05, + "loss": 3.4545, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.284122453177914e-05, + "loss": 3.4634, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.283283858426862e-05, + "loss": 3.4582, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282446901556183e-05, + "loss": 3.461, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281608306805131e-05, + "loss": 3.4605, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2807697120540788e-05, + "loss": 3.4593, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799311173030268e-05, + "loss": 3.4695, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279094160432348e-05, + "loss": 3.4726, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2782555656812964e-05, + "loss": 3.4666, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277416970930244e-05, + "loss": 3.4676, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276578376179192e-05, + "loss": 3.4574, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757414193085133e-05, + "loss": 3.4597, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749028245574613e-05, + "loss": 3.4608, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274064229806409e-05, + "loss": 3.4671, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732256350553573e-05, + "loss": 3.4457, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2723886781846785e-05, + "loss": 3.4644, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715500834336262e-05, + "loss": 3.4623, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707114886825742e-05, + "loss": 3.4644, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2698728939315222e-05, + "loss": 3.4593, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690359370608434e-05, + "loss": 3.4594, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2681973423097914e-05, + "loss": 3.4597, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2673587475587394e-05, + "loss": 3.471, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665201528076874e-05, + "loss": 3.468, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2656831959370087e-05, + "loss": 3.4733, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648446011859563e-05, + "loss": 3.452, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640060064349043e-05, + "loss": 3.4669, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2631674116838526e-05, + "loss": 3.4666, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623304548131736e-05, + "loss": 3.4592, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2614918600621215e-05, + "loss": 3.4643, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606532653110695e-05, + "loss": 3.4715, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598146705600175e-05, + "loss": 3.4645, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2589777136893388e-05, + "loss": 3.4808, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581391189382868e-05, + "loss": 3.4614, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573005241872348e-05, + "loss": 3.4619, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2564619294361828e-05, + "loss": 3.4593, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556249725655037e-05, + "loss": 3.4595, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2547863778144517e-05, + "loss": 3.46, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539477830633997e-05, + "loss": 3.4599, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.253110826192721e-05, + "loss": 3.4659, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.252272231441669e-05, + "loss": 3.4452, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251433636690617e-05, + "loss": 3.4668, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8602488040924072, + "eval_runtime": 303.1037, + "eval_samples_per_second": 1258.946, + "eval_steps_per_second": 39.343, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.250595041939565e-05, + "loss": 3.4656, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2497580850688858e-05, + "loss": 3.4578, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.248919490317834e-05, + "loss": 3.4662, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.248080895566782e-05, + "loss": 3.4683, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.24724230081573e-05, + "loss": 3.4783, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.246405343945051e-05, + "loss": 3.46, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2455683870743723e-05, + "loss": 3.4648, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2447297923233203e-05, + "loss": 3.4502, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2438911975722683e-05, + "loss": 3.4647, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430526028212163e-05, + "loss": 3.4625, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422140080701643e-05, + "loss": 3.4621, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2413754133191123e-05, + "loss": 3.4553, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405384564484332e-05, + "loss": 3.4588, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2396998616973812e-05, + "loss": 3.4534, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2388612669463295e-05, + "loss": 3.4565, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2380226721952775e-05, + "loss": 3.4486, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2371840774442255e-05, + "loss": 3.4486, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2363454826931735e-05, + "loss": 3.4585, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.235506887942121e-05, + "loss": 3.4548, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.234668293191069e-05, + "loss": 3.4704, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338313363203904e-05, + "loss": 3.4656, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2329927415693387e-05, + "loss": 3.4693, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2321541468182864e-05, + "loss": 3.4499, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313155520672344e-05, + "loss": 3.46, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2304785951965556e-05, + "loss": 3.4589, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296400004455036e-05, + "loss": 3.4683, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288014056944513e-05, + "loss": 3.4549, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2279628109433996e-05, + "loss": 3.4585, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.227125854072721e-05, + "loss": 3.4525, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2262872593216685e-05, + "loss": 3.4551, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2254486645706165e-05, + "loss": 3.4609, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246100698195645e-05, + "loss": 3.4668, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2237731129488858e-05, + "loss": 3.4675, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229345181978338e-05, + "loss": 3.4639, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2220959234467818e-05, + "loss": 3.4578, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2212573286957298e-05, + "loss": 3.4612, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220420371825051e-05, + "loss": 3.4627, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2195817770739987e-05, + "loss": 3.4507, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187431823229467e-05, + "loss": 3.4463, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.217904587571895e-05, + "loss": 3.4459, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.217067630701216e-05, + "loss": 3.4528, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216229035950164e-05, + "loss": 3.4605, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215390441199112e-05, + "loss": 3.4629, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.21455184644806e-05, + "loss": 3.4529, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213714889577381e-05, + "loss": 3.4559, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.212876294826329e-05, + "loss": 3.4555, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.212037700075277e-05, + "loss": 3.4563, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.211199105324225e-05, + "loss": 3.4465, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210362148453546e-05, + "loss": 3.4284, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209523553702494e-05, + "loss": 3.4729, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208684958951442e-05, + "loss": 3.4579, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2078463642003904e-05, + "loss": 3.4651, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070094073297113e-05, + "loss": 3.4528, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2061708125786593e-05, + "loss": 3.4541, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053322178276073e-05, + "loss": 3.4427, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2044936230765553e-05, + "loss": 3.4533, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2036566662058765e-05, + "loss": 3.4586, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028180714548245e-05, + "loss": 3.4512, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2019794767037725e-05, + "loss": 3.475, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011408819527205e-05, + "loss": 3.452, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003039250820414e-05, + "loss": 3.444, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1994653303309894e-05, + "loss": 3.4673, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986267355799374e-05, + "loss": 3.4392, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1977897787092586e-05, + "loss": 3.4404, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1969511839582066e-05, + "loss": 3.4671, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961125892071546e-05, + "loss": 3.4612, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1952739944561026e-05, + "loss": 3.443, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944353997050506e-05, + "loss": 3.4535, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193598442834372e-05, + "loss": 3.4388, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.19275984808332e-05, + "loss": 3.4485, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.191921253332268e-05, + "loss": 3.4527, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1910842964615888e-05, + "loss": 3.4462, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902457017105368e-05, + "loss": 3.4586, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894071069594848e-05, + "loss": 3.4543, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885685122084328e-05, + "loss": 3.4652, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.187729917457381e-05, + "loss": 3.4478, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1868913227063288e-05, + "loss": 3.4522, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1860527279552767e-05, + "loss": 3.4553, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852141332042247e-05, + "loss": 3.4475, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.184377176333546e-05, + "loss": 3.4578, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835385815824936e-05, + "loss": 3.4567, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.182699986831442e-05, + "loss": 3.4508, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.18186139208039e-05, + "loss": 3.4621, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810244352097112e-05, + "loss": 3.4403, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180185840458659e-05, + "loss": 3.4428, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179347245707607e-05, + "loss": 3.4531, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.178508650956555e-05, + "loss": 3.4571, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.177671694085876e-05, + "loss": 3.4478, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.176833099334824e-05, + "loss": 3.4537, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.175994504583772e-05, + "loss": 3.4373, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1751575477130934e-05, + "loss": 3.4501, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174318952962041e-05, + "loss": 3.4416, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173480358210989e-05, + "loss": 3.4544, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1726417634599373e-05, + "loss": 3.4625, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1718048065892583e-05, + "loss": 3.4547, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1709662118382063e-05, + "loss": 3.4585, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701276170871543e-05, + "loss": 3.4426, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1692890223361022e-05, + "loss": 3.4491, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1684520654654235e-05, + "loss": 3.4463, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1676134707143715e-05, + "loss": 3.4634, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1667748759633195e-05, + "loss": 3.453, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659362812122675e-05, + "loss": 3.4595, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1650993243415884e-05, + "loss": 3.445, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1642607295905364e-05, + "loss": 3.4561, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1634221348394844e-05, + "loss": 3.4471, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1625835400884327e-05, + "loss": 3.4533, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1617465832177536e-05, + "loss": 3.4406, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1609079884667016e-05, + "loss": 3.4565, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1600693937156496e-05, + "loss": 3.4412, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592307989645976e-05, + "loss": 3.4518, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.158393842093919e-05, + "loss": 3.4432, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.157555247342867e-05, + "loss": 3.4547, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.156716652591815e-05, + "loss": 3.4476, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155878057840763e-05, + "loss": 3.4472, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550411009700838e-05, + "loss": 3.4607, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542025062190318e-05, + "loss": 3.461, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1533639114679797e-05, + "loss": 3.4593, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152525316716928e-05, + "loss": 3.4515, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151688359846249e-05, + "loss": 3.4502, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.150849765095197e-05, + "loss": 3.4491, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.150011170344145e-05, + "loss": 3.4502, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.149172575593093e-05, + "loss": 3.4512, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483356187224142e-05, + "loss": 3.4392, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1474970239713622e-05, + "loss": 3.4539, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1466584292203102e-05, + "loss": 3.4534, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458198344692582e-05, + "loss": 3.4536, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.144982877598579e-05, + "loss": 3.4515, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.144144282847527e-05, + "loss": 3.4451, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143305688096475e-05, + "loss": 3.4474, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1424670933454234e-05, + "loss": 3.4636, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416301364747444e-05, + "loss": 3.4601, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1407915417236924e-05, + "loss": 3.458, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1399529469726404e-05, + "loss": 3.4422, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391143522215883e-05, + "loss": 3.457, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1382773953509096e-05, + "loss": 3.4521, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1374388005998576e-05, + "loss": 3.4468, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1366002058488056e-05, + "loss": 3.453, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1357616110977536e-05, + "loss": 3.4546, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349246542270745e-05, + "loss": 3.4542, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1340860594760225e-05, + "loss": 3.4712, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1332474647249705e-05, + "loss": 3.4481, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324088699739185e-05, + "loss": 3.4543, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1315719131032397e-05, + "loss": 3.4519, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1307333183521877e-05, + "loss": 3.45, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1298947236011357e-05, + "loss": 3.4477, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1290561288500834e-05, + "loss": 3.4467, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282191719794046e-05, + "loss": 3.4517, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127380577228353e-05, + "loss": 3.4372, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126541982477301e-05, + "loss": 3.4557, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.8607735633850098, + "eval_runtime": 302.8237, + "eval_samples_per_second": 1260.109, + "eval_steps_per_second": 39.379, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257033877262486e-05, + "loss": 3.4538, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248647929751966e-05, + "loss": 3.4461, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240261982241446e-05, + "loss": 3.4539, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1231876034730926e-05, + "loss": 3.4574, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.122350646602414e-05, + "loss": 3.4657, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.121512051851362e-05, + "loss": 3.4486, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120675094980683e-05, + "loss": 3.4579, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198365002296307e-05, + "loss": 3.442, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1189979054785787e-05, + "loss": 3.4465, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181593107275267e-05, + "loss": 3.4566, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.117320715976475e-05, + "loss": 3.4499, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.116482121225423e-05, + "loss": 3.4419, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.115645164354744e-05, + "loss": 3.456, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114806569603692e-05, + "loss": 3.4439, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.11396797485264e-05, + "loss": 3.4389, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.113129380101588e-05, + "loss": 3.4392, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.112290785350536e-05, + "loss": 3.4381, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111452190599484e-05, + "loss": 3.4492, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110613595848432e-05, + "loss": 3.4377, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.10977500109738e-05, + "loss": 3.4615, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089380442267012e-05, + "loss": 3.4523, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108099449475649e-05, + "loss": 3.4603, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107260854724597e-05, + "loss": 3.4426, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064222599735452e-05, + "loss": 3.4451, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.105585303102866e-05, + "loss": 3.452, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.104746708351814e-05, + "loss": 3.4539, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103908113600762e-05, + "loss": 3.4443, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.10306951884971e-05, + "loss": 3.4475, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022325619790313e-05, + "loss": 3.4389, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1013939672279793e-05, + "loss": 3.4454, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1005553724769273e-05, + "loss": 3.4472, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997167777258753e-05, + "loss": 3.4551, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0988798208551962e-05, + "loss": 3.4527, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980412261041442e-05, + "loss": 3.4533, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972026313530922e-05, + "loss": 3.4495, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963640366020405e-05, + "loss": 3.4491, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955270797313615e-05, + "loss": 3.4509, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0946884849803095e-05, + "loss": 3.4407, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938498902292574e-05, + "loss": 3.4368, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930112954782054e-05, + "loss": 3.4343, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0921743386075267e-05, + "loss": 3.4422, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913357438564747e-05, + "loss": 3.444, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0904971491054227e-05, + "loss": 3.453, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896585543543707e-05, + "loss": 3.4443, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888215974836916e-05, + "loss": 3.4442, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0879830027326396e-05, + "loss": 3.4473, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871444079815876e-05, + "loss": 3.4469, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.086305813230536e-05, + "loss": 3.4341, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854688563598568e-05, + "loss": 3.4191, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846302616088048e-05, + "loss": 3.456, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0837916668577528e-05, + "loss": 3.4499, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829530721067008e-05, + "loss": 3.4559, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.082116115236022e-05, + "loss": 3.4387, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.08127752048497e-05, + "loss": 3.4451, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.080438925733918e-05, + "loss": 3.4347, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079601968863239e-05, + "loss": 3.4419, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.078763374112187e-05, + "loss": 3.4524, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.077924779361135e-05, + "loss": 3.4347, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.077086184610083e-05, + "loss": 3.4645, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762492277394042e-05, + "loss": 3.4457, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754106329883522e-05, + "loss": 3.4281, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0745720382373002e-05, + "loss": 3.4579, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737334434862482e-05, + "loss": 3.4304, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072896486615569e-05, + "loss": 3.4287, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720578918645174e-05, + "loss": 3.4549, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712192971134654e-05, + "loss": 3.4478, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0703807023624134e-05, + "loss": 3.434, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695437454917343e-05, + "loss": 3.4404, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687051507406823e-05, + "loss": 3.432, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0678665559896303e-05, + "loss": 3.4359, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670279612385783e-05, + "loss": 3.4449, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0661910043678996e-05, + "loss": 3.4351, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653524096168476e-05, + "loss": 3.4498, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645138148657956e-05, + "loss": 3.4418, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0636752201147435e-05, + "loss": 3.4529, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628382632440645e-05, + "loss": 3.4384, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0619996684930128e-05, + "loss": 3.4458, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611610737419608e-05, + "loss": 3.4429, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603224789909088e-05, + "loss": 3.4369, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0594855221202297e-05, + "loss": 3.4507, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586469273691777e-05, + "loss": 3.4472, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578083326181257e-05, + "loss": 3.4358, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569697378670737e-05, + "loss": 3.4528, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.056132780996395e-05, + "loss": 3.4295, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.055294186245343e-05, + "loss": 3.4307, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.054455591494291e-05, + "loss": 3.4452, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536169967432386e-05, + "loss": 3.4453, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0527800398725598e-05, + "loss": 3.4399, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519414451215078e-05, + "loss": 3.4469, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.051102850370456e-05, + "loss": 3.4288, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502642556194038e-05, + "loss": 3.4365, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049427298748725e-05, + "loss": 3.4346, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.048588703997673e-05, + "loss": 3.4408, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477501092466207e-05, + "loss": 3.4525, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046911514495569e-05, + "loss": 3.444, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0460745576248903e-05, + "loss": 3.4495, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452359628738383e-05, + "loss": 3.4324, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.044397368122786e-05, + "loss": 3.4385, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043558773371734e-05, + "loss": 3.4351, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427218165010552e-05, + "loss": 3.448, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0418832217500032e-05, + "loss": 3.4425, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410446269989512e-05, + "loss": 3.4498, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402060322478992e-05, + "loss": 3.4395, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393690753772204e-05, + "loss": 3.4428, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038530480626168e-05, + "loss": 3.4409, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037691885875116e-05, + "loss": 3.4397, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0368532911240644e-05, + "loss": 3.429, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360163342533857e-05, + "loss": 3.4496, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0351777395023333e-05, + "loss": 3.4307, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343391447512813e-05, + "loss": 3.4394, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335005500002293e-05, + "loss": 3.4317, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0326635931295506e-05, + "loss": 3.4416, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318249983784986e-05, + "loss": 3.4401, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0309864036274465e-05, + "loss": 3.4354, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301478088763945e-05, + "loss": 3.4483, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293108520057155e-05, + "loss": 3.4527, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0284722572546634e-05, + "loss": 3.4503, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276336625036114e-05, + "loss": 3.4401, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0267950677525598e-05, + "loss": 3.4417, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0259581108818807e-05, + "loss": 3.4373, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0251195161308287e-05, + "loss": 3.4397, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0242809213797767e-05, + "loss": 3.4386, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234423266287247e-05, + "loss": 3.4283, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.022605369758046e-05, + "loss": 3.4435, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.021766775006994e-05, + "loss": 3.4449, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020928180255942e-05, + "loss": 3.4372, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.02008958550489e-05, + "loss": 3.4401, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192526286342108e-05, + "loss": 3.4386, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184140338831588e-05, + "loss": 3.4361, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0175754391321068e-05, + "loss": 3.4503, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016736844381055e-05, + "loss": 3.4457, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015899887510376e-05, + "loss": 3.4494, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.015061292759324e-05, + "loss": 3.4317, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.014222698008272e-05, + "loss": 3.4437, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013385741137593e-05, + "loss": 3.4416, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125471463865413e-05, + "loss": 3.4399, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117085516354893e-05, + "loss": 3.4426, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108699568844373e-05, + "loss": 3.4423, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100330000137582e-05, + "loss": 3.4466, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0091944052627062e-05, + "loss": 3.4635, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083558105116542e-05, + "loss": 3.4342, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075172157606022e-05, + "loss": 3.4465, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0066802588899234e-05, + "loss": 3.4399, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058416641388714e-05, + "loss": 3.4411, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050030693878194e-05, + "loss": 3.4376, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041644746367674e-05, + "loss": 3.4357, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033275177660883e-05, + "loss": 3.4428, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0024889230150367e-05, + "loss": 3.4269, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0016503282639847e-05, + "loss": 3.4437, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.863162040710449, + "eval_runtime": 304.4739, + "eval_samples_per_second": 1253.28, + "eval_steps_per_second": 39.166, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008117335129326e-05, + "loss": 3.4391, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9999747766422536e-05, + "loss": 3.4361, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991361818912016e-05, + "loss": 3.4411, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9982975871401495e-05, + "loss": 3.4447, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9974589923890975e-05, + "loss": 3.4551, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9966220355184188e-05, + "loss": 3.4397, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9957850786477397e-05, + "loss": 3.4496, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9949464838966877e-05, + "loss": 3.4333, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941078891456357e-05, + "loss": 3.436, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9932692943945837e-05, + "loss": 3.4477, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924306996435317e-05, + "loss": 3.4403, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.99159210489248e-05, + "loss": 3.4319, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990755148021801e-05, + "loss": 3.4468, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989916553270749e-05, + "loss": 3.4285, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989077958519697e-05, + "loss": 3.4308, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988239363768645e-05, + "loss": 3.4234, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.987400769017593e-05, + "loss": 3.4314, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986562174266541e-05, + "loss": 3.4403, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985723579515489e-05, + "loss": 3.4289, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984884984764437e-05, + "loss": 3.4488, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9840480278937578e-05, + "loss": 3.4454, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832094331427058e-05, + "loss": 3.4464, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9823708383916538e-05, + "loss": 3.4355, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981532243640602e-05, + "loss": 3.436, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.980695286769923e-05, + "loss": 3.4416, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.979856692018871e-05, + "loss": 3.4423, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.979018097267819e-05, + "loss": 3.4326, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.978179502516767e-05, + "loss": 3.4391, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9773425456460883e-05, + "loss": 3.4286, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765039508950363e-05, + "loss": 3.4348, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9756653561439843e-05, + "loss": 3.4381, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748267613929323e-05, + "loss": 3.4408, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9739898045222532e-05, + "loss": 3.4452, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9731512097712012e-05, + "loss": 3.4459, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.972312615020149e-05, + "loss": 3.4349, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9714740202690975e-05, + "loss": 3.4403, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9706370633984184e-05, + "loss": 3.4418, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9697984686473664e-05, + "loss": 3.4294, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9689598738963144e-05, + "loss": 3.4303, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681212791452624e-05, + "loss": 3.4249, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9672843222745836e-05, + "loss": 3.4289, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9664457275235316e-05, + "loss": 3.4348, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656071327724796e-05, + "loss": 3.4438, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9647685380214276e-05, + "loss": 3.434, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639315811507485e-05, + "loss": 3.4321, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9630929863996965e-05, + "loss": 3.4321, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9622543916486445e-05, + "loss": 3.4386, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614157968975925e-05, + "loss": 3.4224, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9605788400269138e-05, + "loss": 3.4124, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9597402452758618e-05, + "loss": 3.4433, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9589016505248098e-05, + "loss": 3.4372, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9580630557737578e-05, + "loss": 3.4444, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572260989030787e-05, + "loss": 3.4288, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.956387504152027e-05, + "loss": 3.4329, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.955548909400975e-05, + "loss": 3.4251, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954710314649923e-05, + "loss": 3.4308, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953873357779244e-05, + "loss": 3.4429, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953034763028192e-05, + "loss": 3.4235, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.95219616827714e-05, + "loss": 3.4566, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.951359211406461e-05, + "loss": 3.4314, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.950520616655409e-05, + "loss": 3.4162, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949682021904357e-05, + "loss": 3.4461, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948843427153305e-05, + "loss": 3.4261, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.948006470282626e-05, + "loss": 3.4168, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.947167875531574e-05, + "loss": 3.4409, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463292807805224e-05, + "loss": 3.4391, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9454906860294704e-05, + "loss": 3.4256, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9446537291587913e-05, + "loss": 3.4274, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438151344077393e-05, + "loss": 3.4206, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9429765396566873e-05, + "loss": 3.4239, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9421379449056353e-05, + "loss": 3.4366, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413009880349565e-05, + "loss": 3.4253, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9404623932839045e-05, + "loss": 3.433, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396237985328525e-05, + "loss": 3.4295, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9387852037818e-05, + "loss": 3.4432, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379482469111214e-05, + "loss": 3.4287, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371096521600694e-05, + "loss": 3.4362, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9362710574090177e-05, + "loss": 3.4298, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9354324626579654e-05, + "loss": 3.4275, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9345955057872866e-05, + "loss": 3.4391, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337569110362346e-05, + "loss": 3.4358, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329183162851826e-05, + "loss": 3.4276, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9320797215341306e-05, + "loss": 3.4375, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.931242764663452e-05, + "loss": 3.4177, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304041699124e-05, + "loss": 3.4218, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9295655751613475e-05, + "loss": 3.4325, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287269804102955e-05, + "loss": 3.4353, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9278883856592435e-05, + "loss": 3.4217, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9270497909081915e-05, + "loss": 3.4372, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.92621119615714e-05, + "loss": 3.4228, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.925372601406088e-05, + "loss": 3.4247, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9245356445354088e-05, + "loss": 3.4219, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9236970497843568e-05, + "loss": 3.4298, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9228584550333048e-05, + "loss": 3.441, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9220198602822527e-05, + "loss": 3.4328, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.921182903411574e-05, + "loss": 3.4381, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.920344308660522e-05, + "loss": 3.4238, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.91950571390947e-05, + "loss": 3.4287, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.918667119158418e-05, + "loss": 3.4251, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.917830162287739e-05, + "loss": 3.4369, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.916991567536687e-05, + "loss": 3.4322, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.916152972785635e-05, + "loss": 3.4362, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153143780345832e-05, + "loss": 3.4328, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.914477421163904e-05, + "loss": 3.431, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913638826412852e-05, + "loss": 3.4324, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9128002316618e-05, + "loss": 3.4293, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9119616369107478e-05, + "loss": 3.4195, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111246800400694e-05, + "loss": 3.4354, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9102860852890174e-05, + "loss": 3.424, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094474905379654e-05, + "loss": 3.4271, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086105336672863e-05, + "loss": 3.4283, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9077719389162343e-05, + "loss": 3.4276, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9069333441651823e-05, + "loss": 3.4299, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9060947494141302e-05, + "loss": 3.4245, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052577925434515e-05, + "loss": 3.4403, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044191977923995e-05, + "loss": 3.4405, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9035806030413475e-05, + "loss": 3.4391, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.902742008290295e-05, + "loss": 3.4273, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019050514196164e-05, + "loss": 3.4349, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9010664566685647e-05, + "loss": 3.4249, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9002278619175127e-05, + "loss": 3.4302, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8993892671664604e-05, + "loss": 3.431, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985523102957816e-05, + "loss": 3.4172, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977137155447296e-05, + "loss": 3.4314, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8968751207936776e-05, + "loss": 3.4326, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8960365260426256e-05, + "loss": 3.4322, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895199569171947e-05, + "loss": 3.4271, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894360974420895e-05, + "loss": 3.4255, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935223796698425e-05, + "loss": 3.4265, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8926837849187905e-05, + "loss": 3.4412, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918468280481118e-05, + "loss": 3.4345, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.89100823329706e-05, + "loss": 3.445, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8901696385460078e-05, + "loss": 3.4213, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8893310437949557e-05, + "loss": 3.4298, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.888494086924277e-05, + "loss": 3.4347, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.887655492173225e-05, + "loss": 3.429, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886816897422173e-05, + "loss": 3.4307, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.885978302671121e-05, + "loss": 3.4334, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8851413458004422e-05, + "loss": 3.4334, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.88430275104939e-05, + "loss": 3.4501, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.883464156298338e-05, + "loss": 3.4276, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882625561547286e-05, + "loss": 3.4343, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.881788604676607e-05, + "loss": 3.4348, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.880950009925555e-05, + "loss": 3.4254, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.880111415174503e-05, + "loss": 3.4274, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.879272820423451e-05, + "loss": 3.424, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784358635527724e-05, + "loss": 3.4311, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.87759726880172e-05, + "loss": 3.4215, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8767586740506684e-05, + "loss": 3.4302, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.8628933429718018, + "eval_runtime": 304.8396, + "eval_samples_per_second": 1251.776, + "eval_steps_per_second": 39.119, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759200792996163e-05, + "loss": 3.4321, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8750814845485643e-05, + "loss": 3.4233, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742428897975123e-05, + "loss": 3.429, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734042950464603e-05, + "loss": 3.4366, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8725673381757812e-05, + "loss": 3.4472, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717287434247292e-05, + "loss": 3.43, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8708917865540505e-05, + "loss": 3.4345, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700531918029985e-05, + "loss": 3.424, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692145970519465e-05, + "loss": 3.4246, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8683760023008945e-05, + "loss": 3.4326, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675374075498425e-05, + "loss": 3.4294, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8666988127987905e-05, + "loss": 3.4206, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8658618559281117e-05, + "loss": 3.4366, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8650232611770597e-05, + "loss": 3.4173, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8641846664260077e-05, + "loss": 3.419, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633460716749554e-05, + "loss": 3.4107, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625074769239034e-05, + "loss": 3.4247, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8616688821728514e-05, + "loss": 3.4271, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8608302874217994e-05, + "loss": 3.4182, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8599916926707477e-05, + "loss": 3.4353, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591547358000686e-05, + "loss": 3.434, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8583161410490166e-05, + "loss": 3.4378, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8574775462979646e-05, + "loss": 3.4249, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566389515469126e-05, + "loss": 3.4272, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558019946762338e-05, + "loss": 3.4301, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8549633999251818e-05, + "loss": 3.4347, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541248051741298e-05, + "loss": 3.4193, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8532862104230778e-05, + "loss": 3.4313, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8524492535523987e-05, + "loss": 3.4143, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516106588013467e-05, + "loss": 3.4234, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8507720640502947e-05, + "loss": 3.4299, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849933469299243e-05, + "loss": 3.433, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.849096512428564e-05, + "loss": 3.4275, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.848257917677512e-05, + "loss": 3.4383, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.84741932292646e-05, + "loss": 3.4239, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846580728175408e-05, + "loss": 3.4296, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457437713047292e-05, + "loss": 3.4319, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449051765536772e-05, + "loss": 3.4151, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8440665818026252e-05, + "loss": 3.4194, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432279870515732e-05, + "loss": 3.419, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.842391030180894e-05, + "loss": 3.4173, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.841552435429842e-05, + "loss": 3.4214, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.84071384067879e-05, + "loss": 3.4374, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.839875245927738e-05, + "loss": 3.4214, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390382890570593e-05, + "loss": 3.4226, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8381996943060073e-05, + "loss": 3.4219, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8373610995549553e-05, + "loss": 3.427, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.836522504803903e-05, + "loss": 3.4115, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8356855479332242e-05, + "loss": 3.4034, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348469531821726e-05, + "loss": 3.434, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340083584311206e-05, + "loss": 3.4263, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8331697636800682e-05, + "loss": 3.4368, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323328068093895e-05, + "loss": 3.4183, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8314942120583375e-05, + "loss": 3.4212, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8306556173072855e-05, + "loss": 3.4142, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8298170225562334e-05, + "loss": 3.4193, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8289800656855547e-05, + "loss": 3.4363, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281414709345027e-05, + "loss": 3.4092, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273028761834503e-05, + "loss": 3.4471, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8264659193127716e-05, + "loss": 3.4252, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256273245617196e-05, + "loss": 3.4036, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824788729810668e-05, + "loss": 3.4328, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8239501350596156e-05, + "loss": 3.4195, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231131781889368e-05, + "loss": 3.4056, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8222745834378848e-05, + "loss": 3.429, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214359886868328e-05, + "loss": 3.4336, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8205973939357808e-05, + "loss": 3.4135, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819760437065102e-05, + "loss": 3.4203, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.81892184231405e-05, + "loss": 3.4076, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8180832475629977e-05, + "loss": 3.4172, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8172446528119457e-05, + "loss": 3.4236, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164060580608937e-05, + "loss": 3.4144, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815569101190215e-05, + "loss": 3.4269, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.814730506439163e-05, + "loss": 3.4178, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.813891911688111e-05, + "loss": 3.4362, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.813053316937059e-05, + "loss": 3.418, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122163600663802e-05, + "loss": 3.4266, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.811377765315328e-05, + "loss": 3.4197, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105391705642762e-05, + "loss": 3.4165, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097022136935974e-05, + "loss": 3.4266, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.808863618942545e-05, + "loss": 3.4219, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.808025024191493e-05, + "loss": 3.4234, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.807186429440441e-05, + "loss": 3.4254, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063494725697623e-05, + "loss": 3.4165, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055108778187103e-05, + "loss": 3.4052, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8046722830676583e-05, + "loss": 3.4193, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038336883166063e-05, + "loss": 3.4273, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8029967314459276e-05, + "loss": 3.4142, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8021581366948752e-05, + "loss": 3.424, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013195419438232e-05, + "loss": 3.4106, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8004809471927716e-05, + "loss": 3.4148, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996439903220925e-05, + "loss": 3.4128, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988053955710405e-05, + "loss": 3.4193, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7979668008199885e-05, + "loss": 3.4272, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971282060689364e-05, + "loss": 3.4244, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7962912491982577e-05, + "loss": 3.4272, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7954526544472057e-05, + "loss": 3.4141, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946140596961537e-05, + "loss": 3.4158, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7937754649451017e-05, + "loss": 3.4158, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7929385080744226e-05, + "loss": 3.4248, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7920999133233706e-05, + "loss": 3.4218, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7912613185723186e-05, + "loss": 3.429, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904227238212666e-05, + "loss": 3.4211, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7895857669505878e-05, + "loss": 3.4181, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887471721995358e-05, + "loss": 3.4259, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879085774484838e-05, + "loss": 3.4165, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7870699826974318e-05, + "loss": 3.4108, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.786233025826753e-05, + "loss": 3.4238, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785394431075701e-05, + "loss": 3.4156, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.784555836324649e-05, + "loss": 3.4143, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.783717241573597e-05, + "loss": 3.4153, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782880284702918e-05, + "loss": 3.4145, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.782041689951866e-05, + "loss": 3.4228, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.781203095200814e-05, + "loss": 3.4138, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780364500449762e-05, + "loss": 3.4279, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795275435790832e-05, + "loss": 3.4294, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7786889488280312e-05, + "loss": 3.4318, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7778503540769792e-05, + "loss": 3.4193, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770117593259272e-05, + "loss": 3.4231, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.776174802455248e-05, + "loss": 3.414, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7753362077041964e-05, + "loss": 3.4253, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7744976129531444e-05, + "loss": 3.4183, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736590182020924e-05, + "loss": 3.4068, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728220613314133e-05, + "loss": 3.4201, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7719834665803613e-05, + "loss": 3.4206, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7711448718293093e-05, + "loss": 3.424, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703062770782573e-05, + "loss": 3.4151, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7694693202075786e-05, + "loss": 3.414, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686307254565266e-05, + "loss": 3.4151, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7677921307054746e-05, + "loss": 3.4315, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669535359544225e-05, + "loss": 3.4221, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661165790837435e-05, + "loss": 3.43, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7652779843326918e-05, + "loss": 3.4095, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644393895816398e-05, + "loss": 3.4203, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636007948305874e-05, + "loss": 3.4246, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7627638379599087e-05, + "loss": 3.4158, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619252432088567e-05, + "loss": 3.4213, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7610866484578047e-05, + "loss": 3.4206, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7602480537067527e-05, + "loss": 3.4274, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759411096836074e-05, + "loss": 3.4333, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758572502085022e-05, + "loss": 3.4218, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.75773390733397e-05, + "loss": 3.4213, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7568953125829176e-05, + "loss": 3.4227, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7560583557122388e-05, + "loss": 3.4135, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.755219760961187e-05, + "loss": 3.4188, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7543811662101348e-05, + "loss": 3.4157, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7535425714590828e-05, + "loss": 3.4188, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.752705614588404e-05, + "loss": 3.4105, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.751867019837352e-05, + "loss": 3.4168, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.865187883377075, + "eval_runtime": 303.3679, + "eval_samples_per_second": 1257.849, + "eval_steps_per_second": 39.309, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510284250863e-05, + "loss": 3.4205, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7501914682156213e-05, + "loss": 3.4136, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493528734645693e-05, + "loss": 3.4187, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485142787135173e-05, + "loss": 3.4248, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.747675683962465e-05, + "loss": 3.4384, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7468387270917862e-05, + "loss": 3.4194, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460017702211074e-05, + "loss": 3.4275, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451631754700554e-05, + "loss": 3.414, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443245807190034e-05, + "loss": 3.4127, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7434859859679514e-05, + "loss": 3.4182, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426473912168994e-05, + "loss": 3.4243, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741808796465847e-05, + "loss": 3.4152, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7409718395951687e-05, + "loss": 3.4234, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7401332448441167e-05, + "loss": 3.4069, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7392946500930647e-05, + "loss": 3.41, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384560553420123e-05, + "loss": 3.3977, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376174605909603e-05, + "loss": 3.4174, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7367788658399083e-05, + "loss": 3.4165, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7359402710888563e-05, + "loss": 3.4077, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351016763378043e-05, + "loss": 3.4253, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7342647194671255e-05, + "loss": 3.4261, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334261247160735e-05, + "loss": 3.4263, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7325875299650215e-05, + "loss": 3.415, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317489352139695e-05, + "loss": 3.4146, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309119783432904e-05, + "loss": 3.4248, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7300733835922388e-05, + "loss": 3.4246, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7292347888411868e-05, + "loss": 3.4084, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7283961940901348e-05, + "loss": 3.4189, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7275592372194557e-05, + "loss": 3.4087, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267206424684037e-05, + "loss": 3.4095, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7258820477173517e-05, + "loss": 3.4197, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250434529662997e-05, + "loss": 3.4219, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.724206496095621e-05, + "loss": 3.4198, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.723367901344569e-05, + "loss": 3.4271, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.722529306593517e-05, + "loss": 3.4149, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.721690711842465e-05, + "loss": 3.4213, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7208537549717858e-05, + "loss": 3.4236, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.720015160220734e-05, + "loss": 3.4047, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.719176565469682e-05, + "loss": 3.4075, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7183379707186298e-05, + "loss": 3.4099, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717501013847951e-05, + "loss": 3.4026, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716662419096899e-05, + "loss": 3.414, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.715823824345847e-05, + "loss": 3.4275, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.714985229594795e-05, + "loss": 3.4112, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141482727241163e-05, + "loss": 3.4131, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133096779730643e-05, + "loss": 3.4161, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7124710832220123e-05, + "loss": 3.4167, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.71163248847096e-05, + "loss": 3.3995, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7107955316002812e-05, + "loss": 3.3945, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099569368492295e-05, + "loss": 3.42, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709118342098177e-05, + "loss": 3.4203, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7082813852274984e-05, + "loss": 3.4282, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7074427904764464e-05, + "loss": 3.4085, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066041957253944e-05, + "loss": 3.4098, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7057656009743424e-05, + "loss": 3.407, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7049270062232904e-05, + "loss": 3.4088, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7040884114722384e-05, + "loss": 3.4237, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7032498167211864e-05, + "loss": 3.3951, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7024112219701344e-05, + "loss": 3.438, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7015742650994553e-05, + "loss": 3.4161, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7007356703484033e-05, + "loss": 3.3959, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6998970755973513e-05, + "loss": 3.4213, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6990584808462996e-05, + "loss": 3.4074, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982215239756205e-05, + "loss": 3.3968, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6973829292245685e-05, + "loss": 3.4197, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965443344735165e-05, + "loss": 3.421, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957057397224645e-05, + "loss": 3.401, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6948687828517858e-05, + "loss": 3.4132, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6940301881007338e-05, + "loss": 3.3958, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6931915933496818e-05, + "loss": 3.4095, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6923529985986298e-05, + "loss": 3.4081, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691517679608324e-05, + "loss": 3.4084, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.690679084857272e-05, + "loss": 3.4122, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.68984049010622e-05, + "loss": 3.4075, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.689001895355168e-05, + "loss": 3.4275, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.688163300604116e-05, + "loss": 3.4082, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687324705853064e-05, + "loss": 3.4178, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686486111102012e-05, + "loss": 3.4051, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.68564751635096e-05, + "loss": 3.4069, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.684810559480281e-05, + "loss": 3.4187, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.683971964729229e-05, + "loss": 3.41, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.683133369978177e-05, + "loss": 3.4111, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.682294775227125e-05, + "loss": 3.4185, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.681457818356446e-05, + "loss": 3.404, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.680619223605394e-05, + "loss": 3.3959, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.679780628854342e-05, + "loss": 3.4093, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.67894203410329e-05, + "loss": 3.4176, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781050772326113e-05, + "loss": 3.4027, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6772664824815593e-05, + "loss": 3.4146, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764278877305073e-05, + "loss": 3.4053, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.675589292979455e-05, + "loss": 3.3994, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6747523361087765e-05, + "loss": 3.4028, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739137413577245e-05, + "loss": 3.4097, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6730751466066725e-05, + "loss": 3.422, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.67223655185562e-05, + "loss": 3.4137, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6713995949849414e-05, + "loss": 3.415, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6705610002338894e-05, + "loss": 3.4048, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6697224054828374e-05, + "loss": 3.4066, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6688854486121586e-05, + "loss": 3.4049, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680468538611066e-05, + "loss": 3.4141, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672082591100546e-05, + "loss": 3.414, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6663696643590023e-05, + "loss": 3.416, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6655327074883235e-05, + "loss": 3.4126, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.664694112737272e-05, + "loss": 3.4039, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.66385551798622e-05, + "loss": 3.4166, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630169232351675e-05, + "loss": 3.407, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6621799663644888e-05, + "loss": 3.4004, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613413716134368e-05, + "loss": 3.4094, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605027768623848e-05, + "loss": 3.4077, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6596641821113328e-05, + "loss": 3.4039, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.658827225240654e-05, + "loss": 3.404, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.657988630489602e-05, + "loss": 3.4035, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6571500357385497e-05, + "loss": 3.4122, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563114409874976e-05, + "loss": 3.4095, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.655474484116819e-05, + "loss": 3.4101, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654635889365767e-05, + "loss": 3.417, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653797294614715e-05, + "loss": 3.423, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652958699863663e-05, + "loss": 3.4069, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.652121742992984e-05, + "loss": 3.4144, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6512831482419318e-05, + "loss": 3.404, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6504445534908798e-05, + "loss": 3.4118, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.649605958739828e-05, + "loss": 3.4081, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6487690018691494e-05, + "loss": 3.4022, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.647930407118097e-05, + "loss": 3.405, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.647091812367045e-05, + "loss": 3.4141, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.646253217615993e-05, + "loss": 3.4133, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454162607453143e-05, + "loss": 3.4028, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6445776659942623e-05, + "loss": 3.4036, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437390712432103e-05, + "loss": 3.4084, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429004764921583e-05, + "loss": 3.4162, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.642063519621479e-05, + "loss": 3.4146, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641224924870427e-05, + "loss": 3.4222, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640386330119375e-05, + "loss": 3.4004, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6395477353683235e-05, + "loss": 3.411, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6387107784976444e-05, + "loss": 3.4146, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6378721837465924e-05, + "loss": 3.4028, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370335889955404e-05, + "loss": 3.4087, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6361949942444884e-05, + "loss": 3.4135, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6353580373738096e-05, + "loss": 3.419, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6345194426227576e-05, + "loss": 3.4221, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6336808478717056e-05, + "loss": 3.4096, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6328422531206536e-05, + "loss": 3.4124, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320052962499745e-05, + "loss": 3.412, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6311667014989225e-05, + "loss": 3.405, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6303281067478705e-05, + "loss": 3.4075, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.629489511996819e-05, + "loss": 3.409, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6286525551261398e-05, + "loss": 3.4031, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6278139603750878e-05, + "loss": 3.4065, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6269753656240358e-05, + "loss": 3.4053, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.866305351257324, + "eval_runtime": 303.9758, + "eval_samples_per_second": 1255.333, + "eval_steps_per_second": 39.23, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261367708729838e-05, + "loss": 3.4048, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6252981761219317e-05, + "loss": 3.4036, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244595813708797e-05, + "loss": 3.4123, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236209866198277e-05, + "loss": 3.4135, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.622784029749149e-05, + "loss": 3.4232, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.621945434998097e-05, + "loss": 3.4109, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.621108478127418e-05, + "loss": 3.42, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.620269883376366e-05, + "loss": 3.4055, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194312886253142e-05, + "loss": 3.4016, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6185926938742622e-05, + "loss": 3.4057, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.61775409912321e-05, + "loss": 3.4198, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616915504372158e-05, + "loss": 3.4019, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.616078547501479e-05, + "loss": 3.4177, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615239952750427e-05, + "loss": 3.3934, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614401357999375e-05, + "loss": 3.3986, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613562763248323e-05, + "loss": 3.3903, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612724168497271e-05, + "loss": 3.4097, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.611885573746219e-05, + "loss": 3.4042, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.611046978995167e-05, + "loss": 3.4036, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.610208384244115e-05, + "loss": 3.4043, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609371427373436e-05, + "loss": 3.421, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085328326223843e-05, + "loss": 3.4137, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6076942378713323e-05, + "loss": 3.4073, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068556431202803e-05, + "loss": 3.4023, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060186862496012e-05, + "loss": 3.4189, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6051800914985492e-05, + "loss": 3.409, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6043414967474972e-05, + "loss": 3.4025, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035029019964452e-05, + "loss": 3.4074, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6026659451257665e-05, + "loss": 3.3986, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018273503747145e-05, + "loss": 3.3971, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6009887556236625e-05, + "loss": 3.412, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.60015016087261e-05, + "loss": 3.407, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993132040019314e-05, + "loss": 3.4141, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5984746092508797e-05, + "loss": 3.4166, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5976360144998277e-05, + "loss": 3.4035, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5967974197487753e-05, + "loss": 3.4123, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959604628780966e-05, + "loss": 3.4115, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951218681270446e-05, + "loss": 3.3986, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5942832733759926e-05, + "loss": 3.4034, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5934446786249406e-05, + "loss": 3.3938, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592607721754262e-05, + "loss": 3.397, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5917691270032098e-05, + "loss": 3.4014, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909305322521575e-05, + "loss": 3.4175, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5900919375011055e-05, + "loss": 3.4016, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892549806304267e-05, + "loss": 3.3992, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884163858793747e-05, + "loss": 3.4074, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5875777911283227e-05, + "loss": 3.4057, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5867391963772707e-05, + "loss": 3.3931, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585902239506592e-05, + "loss": 3.3852, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850636447555396e-05, + "loss": 3.4083, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.584225050004488e-05, + "loss": 3.4144, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.583386455253436e-05, + "loss": 3.4139, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825494983827572e-05, + "loss": 3.3988, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581710903631705e-05, + "loss": 3.4008, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580872308880653e-05, + "loss": 3.3943, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.580033714129601e-05, + "loss": 3.3962, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.579196757258922e-05, + "loss": 3.4152, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.57835816250787e-05, + "loss": 3.39, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577519567756818e-05, + "loss": 3.4256, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.576680973005766e-05, + "loss": 3.4035, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.575844016135087e-05, + "loss": 3.3895, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575005421384035e-05, + "loss": 3.4089, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.574166826632983e-05, + "loss": 3.397, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733298697623046e-05, + "loss": 3.3878, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5724912750112522e-05, + "loss": 3.4047, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716526802602002e-05, + "loss": 3.4123, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708140855091482e-05, + "loss": 3.393, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.569977128638469e-05, + "loss": 3.4017, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5691385338874175e-05, + "loss": 3.3863, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5682999391363655e-05, + "loss": 3.4, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5674613443853135e-05, + "loss": 3.398, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666243875146344e-05, + "loss": 3.3998, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5657857927635824e-05, + "loss": 3.3979, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5649471980125304e-05, + "loss": 3.402, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641086032614783e-05, + "loss": 3.4149, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5632716463907996e-05, + "loss": 3.4018, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5624330516397476e-05, + "loss": 3.4057, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5615944568886956e-05, + "loss": 3.3973, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5607558621376436e-05, + "loss": 3.3969, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599189052669645e-05, + "loss": 3.4096, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5590803105159128e-05, + "loss": 3.3999, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5582417157648608e-05, + "loss": 3.3986, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574031210138088e-05, + "loss": 3.4052, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5565661641431297e-05, + "loss": 3.3989, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557275693920777e-05, + "loss": 3.3813, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5548889746410257e-05, + "loss": 3.4003, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5540503798899737e-05, + "loss": 3.4031, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.553213423019295e-05, + "loss": 3.3955, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.552374828268243e-05, + "loss": 3.4031, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.551536233517191e-05, + "loss": 3.3972, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550697638766139e-05, + "loss": 3.3912, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.54986068189546e-05, + "loss": 3.3958, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490220871444082e-05, + "loss": 3.3971, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5481834923933562e-05, + "loss": 3.4059, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473448976423042e-05, + "loss": 3.4059, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.546507940771625e-05, + "loss": 3.4099, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545669346020573e-05, + "loss": 3.3892, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544830751269521e-05, + "loss": 3.3975, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.543992156518469e-05, + "loss": 3.3986, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431551996477903e-05, + "loss": 3.4053, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423166048967383e-05, + "loss": 3.4043, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5414780101456863e-05, + "loss": 3.4054, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406394153946343e-05, + "loss": 3.4002, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398024585239552e-05, + "loss": 3.3928, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389638637729036e-05, + "loss": 3.4067, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381252690218516e-05, + "loss": 3.3968, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5372866742707996e-05, + "loss": 3.3967, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364497174001205e-05, + "loss": 3.397, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356111226490685e-05, + "loss": 3.3966, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5347725278980165e-05, + "loss": 3.3967, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5339339331469644e-05, + "loss": 3.3926, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5330969762762857e-05, + "loss": 3.3906, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322583815252337e-05, + "loss": 3.4047, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314197867741817e-05, + "loss": 3.4012, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5305811920231293e-05, + "loss": 3.398, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297442351524506e-05, + "loss": 3.4078, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.528905640401399e-05, + "loss": 3.4147, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.528067045650347e-05, + "loss": 3.3934, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5272284508992946e-05, + "loss": 3.4014, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5263914940286158e-05, + "loss": 3.3968, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255528992775638e-05, + "loss": 3.4007, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247143045265117e-05, + "loss": 3.3963, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5238757097754596e-05, + "loss": 3.3941, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.523038752904781e-05, + "loss": 3.3962, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.522200158153729e-05, + "loss": 3.4045, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213615634026767e-05, + "loss": 3.3979, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205229686516249e-05, + "loss": 3.3975, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5196860117809461e-05, + "loss": 3.3982, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188474170298941e-05, + "loss": 3.3989, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.518008822278842e-05, + "loss": 3.4043, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.51717022752779e-05, + "loss": 3.4055, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163332706571112e-05, + "loss": 3.409, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.515494675906059e-05, + "loss": 3.3925, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.514656081155007e-05, + "loss": 3.4014, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.513817486403955e-05, + "loss": 3.4032, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5129805295332764e-05, + "loss": 3.395, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121419347822241e-05, + "loss": 3.3939, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.511303340031172e-05, + "loss": 3.403, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.51046474528012e-05, + "loss": 3.4116, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096277884094415e-05, + "loss": 3.4116, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5087891936583892e-05, + "loss": 3.4011, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079505989073373e-05, + "loss": 3.4008, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071136420366586e-05, + "loss": 3.4031, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5062750472856064e-05, + "loss": 3.3998, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054364525345544e-05, + "loss": 3.3944, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5045978577835024e-05, + "loss": 3.4025, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037609009128236e-05, + "loss": 3.3914, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029223061617715e-05, + "loss": 3.3981, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5020837114107195e-05, + "loss": 3.3953, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.866746425628662, + "eval_runtime": 307.3086, + "eval_samples_per_second": 1241.719, + "eval_steps_per_second": 38.805, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012451166596675e-05, + "loss": 3.4028, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004081597889889e-05, + "loss": 3.3893, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995695650379365e-05, + "loss": 3.4005, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987309702868845e-05, + "loss": 3.4073, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4978923755358327e-05, + "loss": 3.409, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970554186651536e-05, + "loss": 3.406, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.496218461794475e-05, + "loss": 3.4082, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.495379867043423e-05, + "loss": 3.3928, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.494541272292371e-05, + "loss": 3.3907, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937026775413188e-05, + "loss": 3.4007, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4928640827902668e-05, + "loss": 3.3999, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920254880392148e-05, + "loss": 3.3977, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.491188531168536e-05, + "loss": 3.4072, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903499364174839e-05, + "loss": 3.385, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895113416664319e-05, + "loss": 3.3906, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4886727469153799e-05, + "loss": 3.3769, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.487834152164328e-05, + "loss": 3.4027, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.486995557413276e-05, + "loss": 3.3896, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.486156962662224e-05, + "loss": 3.3951, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853183679111719e-05, + "loss": 3.3967, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4844814110404931e-05, + "loss": 3.4062, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836428162894411e-05, + "loss": 3.4051, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828042215383891e-05, + "loss": 3.3953, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.481965626787337e-05, + "loss": 3.3921, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811286699166582e-05, + "loss": 3.4095, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4802900751656062e-05, + "loss": 3.3984, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794514804145543e-05, + "loss": 3.3914, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.478612885663502e-05, + "loss": 3.4002, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4777759287928234e-05, + "loss": 3.3848, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769373340417714e-05, + "loss": 3.3919, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.476098739290719e-05, + "loss": 3.4025, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752601445396672e-05, + "loss": 3.3947, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744231876689885e-05, + "loss": 3.3989, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4735845929179365e-05, + "loss": 3.4066, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727459981668843e-05, + "loss": 3.3936, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719074034158323e-05, + "loss": 3.4003, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4710704465451536e-05, + "loss": 3.4034, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702318517941015e-05, + "loss": 3.3852, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4693932570430494e-05, + "loss": 3.3922, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685546622919974e-05, + "loss": 3.3851, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677177054213186e-05, + "loss": 3.3865, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4668791106702664e-05, + "loss": 3.3916, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660405159192144e-05, + "loss": 3.4061, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652019211681624e-05, + "loss": 3.3914, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643649642974839e-05, + "loss": 3.3918, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635263695464315e-05, + "loss": 3.3972, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4626877747953797e-05, + "loss": 3.3974, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618491800443277e-05, + "loss": 3.3825, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610122231736487e-05, + "loss": 3.3744, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4601736284225967e-05, + "loss": 3.3943, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593350336715447e-05, + "loss": 3.4078, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4584964389204927e-05, + "loss": 3.4038, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576594820498138e-05, + "loss": 3.3864, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568208872987618e-05, + "loss": 3.3913, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4559822925477098e-05, + "loss": 3.3883, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551436977966578e-05, + "loss": 3.3812, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543067409259789e-05, + "loss": 3.4117, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4534681461749269e-05, + "loss": 3.3789, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.452629551423875e-05, + "loss": 3.4127, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.451790956672823e-05, + "loss": 3.3947, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.450953999802144e-05, + "loss": 3.3809, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501154050510921e-05, + "loss": 3.3973, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4492768103000401e-05, + "loss": 3.3883, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484382155489881e-05, + "loss": 3.379, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476012586783092e-05, + "loss": 3.3948, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467626639272572e-05, + "loss": 3.402, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459240691762052e-05, + "loss": 3.3843, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4450854744251532e-05, + "loss": 3.3929, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442485175544742e-05, + "loss": 3.3761, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434099228034222e-05, + "loss": 3.3902, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4425713280523704e-05, + "loss": 3.3862, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417327333013184e-05, + "loss": 3.3919, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4408957764306393e-05, + "loss": 3.3884, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400571816795875e-05, + "loss": 3.3904, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392185869285355e-05, + "loss": 3.4062, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4383799921774835e-05, + "loss": 3.3904, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375430353068045e-05, + "loss": 3.3965, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367044405557525e-05, + "loss": 3.39, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4358658458047005e-05, + "loss": 3.3872, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350272510536485e-05, + "loss": 3.3985, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4341902941829696e-05, + "loss": 3.3883, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333516994319176e-05, + "loss": 3.3946, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325131046808658e-05, + "loss": 3.3943, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4316745099298138e-05, + "loss": 3.3913, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308375530591347e-05, + "loss": 3.3711, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4299989583080828e-05, + "loss": 3.3939, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291603635570308e-05, + "loss": 3.3918, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283217688059788e-05, + "loss": 3.3862, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4274848119352999e-05, + "loss": 3.3926, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266462171842479e-05, + "loss": 3.3884, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258076224331959e-05, + "loss": 3.3818, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.424970665562517e-05, + "loss": 3.3828, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.424132070811465e-05, + "loss": 3.3888, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.423293476060413e-05, + "loss": 3.3923, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.422454881309361e-05, + "loss": 3.3962, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.421617924438682e-05, + "loss": 3.3971, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.42077932968763e-05, + "loss": 3.3834, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199407349365782e-05, + "loss": 3.3854, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191037780658991e-05, + "loss": 3.3896, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4182651833148473e-05, + "loss": 3.3955, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174265885637953e-05, + "loss": 3.3933, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4165879938127433e-05, + "loss": 3.3957, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157493990616913e-05, + "loss": 3.3924, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149108043106391e-05, + "loss": 3.3842, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4140722095595871e-05, + "loss": 3.3946, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132336148085351e-05, + "loss": 3.3868, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4123966579378562e-05, + "loss": 3.3846, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115580631868042e-05, + "loss": 3.3867, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107194684357522e-05, + "loss": 3.3873, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4098808736847002e-05, + "loss": 3.3855, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090439168140212e-05, + "loss": 3.3873, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082053220629692e-05, + "loss": 3.3775, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4073667273119174e-05, + "loss": 3.3911, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065281325608654e-05, + "loss": 3.3966, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4056911756901863e-05, + "loss": 3.3849, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048525809391345e-05, + "loss": 3.3975, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040139861880825e-05, + "loss": 3.4047, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4031753914370305e-05, + "loss": 3.3854, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4023384345663515e-05, + "loss": 3.3909, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4014998398152995e-05, + "loss": 3.39, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4006612450642475e-05, + "loss": 3.3898, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3998226503131955e-05, + "loss": 3.3874, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3989856934425166e-05, + "loss": 3.3839, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981470986914646e-05, + "loss": 3.3888, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973085039404128e-05, + "loss": 3.3927, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3964699091893608e-05, + "loss": 3.3871, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956329523186817e-05, + "loss": 3.3923, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3947943575676298e-05, + "loss": 3.3855, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3939557628165778e-05, + "loss": 3.3858, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931171680655258e-05, + "loss": 3.3883, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3922802111948469e-05, + "loss": 3.4, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914416164437949e-05, + "loss": 3.3973, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906030216927429e-05, + "loss": 3.386, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897644269416909e-05, + "loss": 3.3855, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.388927470071012e-05, + "loss": 3.3951, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.38808887531996e-05, + "loss": 3.381, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872502805689081e-05, + "loss": 3.3902, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.386413323698229e-05, + "loss": 3.3934, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.385574728947177e-05, + "loss": 3.403, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847361341961252e-05, + "loss": 3.3983, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3838975394450732e-05, + "loss": 3.396, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830605825743943e-05, + "loss": 3.3886, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822219878233423e-05, + "loss": 3.3977, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3813833930722903e-05, + "loss": 3.3854, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805447983212383e-05, + "loss": 3.3843, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797078414505593e-05, + "loss": 3.3922, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3788692466995073e-05, + "loss": 3.38, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780306519484553e-05, + "loss": 3.3914, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3771920571974033e-05, + "loss": 3.3831, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8682382106781006, + "eval_runtime": 307.0196, + "eval_samples_per_second": 1242.888, + "eval_steps_per_second": 38.841, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763551003267244e-05, + "loss": 3.3927, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755165055756724e-05, + "loss": 3.3835, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3746779108246206e-05, + "loss": 3.389, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738393160735686e-05, + "loss": 3.3986, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730023592028895e-05, + "loss": 3.3979, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721637644518376e-05, + "loss": 3.4013, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713268075811585e-05, + "loss": 3.3912, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3704882128301067e-05, + "loss": 3.3863, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696496180790547e-05, + "loss": 3.3763, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688110233280027e-05, + "loss": 3.394, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3679724285769507e-05, + "loss": 3.3889, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671338338258985e-05, + "loss": 3.3869, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3662968769552198e-05, + "loss": 3.4012, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654582822041678e-05, + "loss": 3.3721, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.364619687453116e-05, + "loss": 3.3797, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3637810927020636e-05, + "loss": 3.3757, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629424979510116e-05, + "loss": 3.3879, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621039031999597e-05, + "loss": 3.3832, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612653084489077e-05, + "loss": 3.3834, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604267136978557e-05, + "loss": 3.3883, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3595897568271768e-05, + "loss": 3.3954, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587511620761248e-05, + "loss": 3.3943, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579125673250728e-05, + "loss": 3.3885, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3570739725740208e-05, + "loss": 3.3819, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562370157033419e-05, + "loss": 3.4011, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3553984209522899e-05, + "loss": 3.3846, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545598262012379e-05, + "loss": 3.3836, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.353721231450186e-05, + "loss": 3.3887, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.352884274579507e-05, + "loss": 3.3759, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520456798284551e-05, + "loss": 3.3817, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512070850774031e-05, + "loss": 3.3888, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503684903263511e-05, + "loss": 3.3866, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495315334556722e-05, + "loss": 3.3931, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3486929387046202e-05, + "loss": 3.3964, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478543439535682e-05, + "loss": 3.3847, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470157492025162e-05, + "loss": 3.3924, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3461787923318373e-05, + "loss": 3.3964, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453401975807852e-05, + "loss": 3.3764, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445016028297332e-05, + "loss": 3.3834, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436630080786814e-05, + "loss": 3.3717, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428260512080023e-05, + "loss": 3.3824, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3419874564569505e-05, + "loss": 3.3781, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411488617058985e-05, + "loss": 3.4036, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403102669548465e-05, + "loss": 3.3806, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3394733100841676e-05, + "loss": 3.381, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386347153331155e-05, + "loss": 3.3835, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3377961205820635e-05, + "loss": 3.3859, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3369575258310114e-05, + "loss": 3.3776, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361205689603326e-05, + "loss": 3.3656, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3352819742092806e-05, + "loss": 3.3873, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344433794582286e-05, + "loss": 3.3945, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336047847071764e-05, + "loss": 3.3905, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3327678278364977e-05, + "loss": 3.3807, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319292330854457e-05, + "loss": 3.3764, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3310906383343935e-05, + "loss": 3.3813, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302520435833415e-05, + "loss": 3.369, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.329415086712663e-05, + "loss": 3.4004, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3285764919616109e-05, + "loss": 3.3709, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277378972105586e-05, + "loss": 3.4011, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3268993024595067e-05, + "loss": 3.3886, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.326062345588828e-05, + "loss": 3.3695, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.325223750837776e-05, + "loss": 3.3858, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3243851560867238e-05, + "loss": 3.3839, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235465613356718e-05, + "loss": 3.3721, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.322709604464993e-05, + "loss": 3.3766, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3218710097139409e-05, + "loss": 3.3963, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210324149628889e-05, + "loss": 3.3766, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3201938202118369e-05, + "loss": 3.378, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193568633411583e-05, + "loss": 3.371, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.318518268590106e-05, + "loss": 3.3818, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.317679673839054e-05, + "loss": 3.3746, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168410790880021e-05, + "loss": 3.3814, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160041222173234e-05, + "loss": 3.3778, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.315165527466271e-05, + "loss": 3.3822, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143269327152192e-05, + "loss": 3.3915, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3134883379641672e-05, + "loss": 3.3802, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126513810934882e-05, + "loss": 3.385, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118127863424362e-05, + "loss": 3.3819, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3109741915913842e-05, + "loss": 3.3807, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101355968403322e-05, + "loss": 3.3853, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3092986399696533e-05, + "loss": 3.3792, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084600452186013e-05, + "loss": 3.3826, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076214504675493e-05, + "loss": 3.386, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3067828557164975e-05, + "loss": 3.382, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059458988458184e-05, + "loss": 3.3652, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051073040947664e-05, + "loss": 3.3819, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042687093437145e-05, + "loss": 3.3765, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034301145926625e-05, + "loss": 3.3803, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3025931577219836e-05, + "loss": 3.3784, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017545629709316e-05, + "loss": 3.383, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009159682198796e-05, + "loss": 3.368, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3000790113492007e-05, + "loss": 3.3739, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992404165981487e-05, + "loss": 3.3782, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984018218470967e-05, + "loss": 3.3876, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975632270960447e-05, + "loss": 3.381, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967262702253658e-05, + "loss": 3.3922, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2958876754743137e-05, + "loss": 3.3705, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950490807232617e-05, + "loss": 3.378, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942104859722099e-05, + "loss": 3.3787, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2933735291015308e-05, + "loss": 3.3843, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.292534934350479e-05, + "loss": 3.3817, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.291696339599427e-05, + "loss": 3.3878, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.290857744848375e-05, + "loss": 3.3794, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.290020787977696e-05, + "loss": 3.3776, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.289182193226644e-05, + "loss": 3.3895, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.288343598475592e-05, + "loss": 3.3733, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.28750500372454e-05, + "loss": 3.3747, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866680468538611e-05, + "loss": 3.378, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858294521028091e-05, + "loss": 3.3756, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2849908573517571e-05, + "loss": 3.3759, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841522626007053e-05, + "loss": 3.3814, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833153057300262e-05, + "loss": 3.3685, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824767109789742e-05, + "loss": 3.3818, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816381162279223e-05, + "loss": 3.3841, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2807995214768703e-05, + "loss": 3.374, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799625646061914e-05, + "loss": 3.3909, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791239698551394e-05, + "loss": 3.3932, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2782853751040874e-05, + "loss": 3.3766, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774467803530354e-05, + "loss": 3.3818, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766098234823565e-05, + "loss": 3.3802, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2757712287313045e-05, + "loss": 3.3793, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749326339802525e-05, + "loss": 3.3738, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2740940392292006e-05, + "loss": 3.3749, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732570823585215e-05, + "loss": 3.3774, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724184876074695e-05, + "loss": 3.3858, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2715798928564177e-05, + "loss": 3.379, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707412981053657e-05, + "loss": 3.377, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699043412346868e-05, + "loss": 3.3776, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690657464836348e-05, + "loss": 3.3761, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682271517325828e-05, + "loss": 3.3761, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2673885569815306e-05, + "loss": 3.3918, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665516001108519e-05, + "loss": 3.3899, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657130053597998e-05, + "loss": 3.3801, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2648744106087478e-05, + "loss": 3.3762, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640358158576957e-05, + "loss": 3.3847, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.263198858987017e-05, + "loss": 3.3759, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623602642359649e-05, + "loss": 3.3774, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.261521669484913e-05, + "loss": 3.3824, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2606830747338607e-05, + "loss": 3.4002, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598461178631822e-05, + "loss": 3.3805, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590075231121301e-05, + "loss": 3.388, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581689283610778e-05, + "loss": 3.3805, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573319714903992e-05, + "loss": 3.3869, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2564933767393472e-05, + "loss": 3.3755, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556547819882952e-05, + "loss": 3.3739, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.254816187237243e-05, + "loss": 3.3837, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2539792303665643e-05, + "loss": 3.3696, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531406356155123e-05, + "loss": 3.3833, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523020408644603e-05, + "loss": 3.371, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8690528869628906, + "eval_runtime": 304.3894, + "eval_samples_per_second": 1253.628, + "eval_steps_per_second": 39.177, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514634461134081e-05, + "loss": 3.3823, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506264892427294e-05, + "loss": 3.376, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2497878944916773e-05, + "loss": 3.3778, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489492997406253e-05, + "loss": 3.3896, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481107049895733e-05, + "loss": 3.3857, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2472737481188944e-05, + "loss": 3.3922, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464367912482155e-05, + "loss": 3.3791, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2455981964971637e-05, + "loss": 3.3772, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2447596017461117e-05, + "loss": 3.3726, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2439210069950595e-05, + "loss": 3.3815, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2430824122440075e-05, + "loss": 3.3781, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422438174929556e-05, + "loss": 3.3788, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2414068606222767e-05, + "loss": 3.3918, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2405682658712246e-05, + "loss": 3.3646, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397296711201727e-05, + "loss": 3.3657, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388910763691207e-05, + "loss": 3.3665, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2380524816180685e-05, + "loss": 3.3742, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372138868670165e-05, + "loss": 3.3761, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2363752921159647e-05, + "loss": 3.3761, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355366973649125e-05, + "loss": 3.376, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2346997404942338e-05, + "loss": 3.3871, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2338611457431818e-05, + "loss": 3.3811, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330225509921298e-05, + "loss": 3.3811, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2321839562410776e-05, + "loss": 3.3732, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313469993703988e-05, + "loss": 3.391, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305084046193468e-05, + "loss": 3.375, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2296698098682948e-05, + "loss": 3.3765, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288312151172428e-05, + "loss": 3.3736, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2279942582465639e-05, + "loss": 3.3693, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2271556634955119e-05, + "loss": 3.3729, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263170687444599e-05, + "loss": 3.3762, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2254784739934079e-05, + "loss": 3.3773, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2246415171227291e-05, + "loss": 3.3839, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238029223716771e-05, + "loss": 3.3885, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.222964327620625e-05, + "loss": 3.376, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.222125732869573e-05, + "loss": 3.3833, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2212887759988942e-05, + "loss": 3.3827, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204501812478422e-05, + "loss": 3.3673, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.21961158649679e-05, + "loss": 3.3726, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2187729917457382e-05, + "loss": 3.3601, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179360348750593e-05, + "loss": 3.3733, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2170974401240073e-05, + "loss": 3.37, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162588453729553e-05, + "loss": 3.3895, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154202506219033e-05, + "loss": 3.3694, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2145832937512245e-05, + "loss": 3.3711, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137446990001723e-05, + "loss": 3.3783, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129061042491203e-05, + "loss": 3.3758, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2120675094980683e-05, + "loss": 3.3722, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112305526273896e-05, + "loss": 3.3513, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2103919578763374e-05, + "loss": 3.3747, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2095533631252854e-05, + "loss": 3.3835, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2087147683742336e-05, + "loss": 3.3839, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2078778115035545e-05, + "loss": 3.3709, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070392167525026e-05, + "loss": 3.3665, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062006220014506e-05, + "loss": 3.3743, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2053620272503986e-05, + "loss": 3.363, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045250703797197e-05, + "loss": 3.3876, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2036864756286677e-05, + "loss": 3.3594, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028478808776157e-05, + "loss": 3.3923, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020109240069368e-05, + "loss": 3.3786, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2011723292558848e-05, + "loss": 3.3594, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2003337345048328e-05, + "loss": 3.3732, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1994951397537808e-05, + "loss": 3.3801, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986565450027288e-05, + "loss": 3.3593, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978179502516768e-05, + "loss": 3.3644, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1969793555006247e-05, + "loss": 3.3871, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961407607495727e-05, + "loss": 3.3701, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953038038788938e-05, + "loss": 3.3688, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1944652091278418e-05, + "loss": 3.3574, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.19362661437679e-05, + "loss": 3.3722, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1927880196257378e-05, + "loss": 3.364, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919510627550589e-05, + "loss": 3.375, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.191112468004007e-05, + "loss": 3.3654, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1902738732529549e-05, + "loss": 3.3751, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1894352785019029e-05, + "loss": 3.3814, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1885983216312241e-05, + "loss": 3.3737, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1877597268801721e-05, + "loss": 3.3712, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.18692113212912e-05, + "loss": 3.3689, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1860825373780681e-05, + "loss": 3.3759, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852455805073892e-05, + "loss": 3.3772, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844069857563372e-05, + "loss": 3.3698, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1835683910052852e-05, + "loss": 3.3727, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827297962542332e-05, + "loss": 3.3727, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1818928393835543e-05, + "loss": 3.3726, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810542446325022e-05, + "loss": 3.3545, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802156498814502e-05, + "loss": 3.372, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1793770551303982e-05, + "loss": 3.367, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785400982597195e-05, + "loss": 3.3736, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777015035086673e-05, + "loss": 3.3729, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768629087576153e-05, + "loss": 3.3744, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760243140065635e-05, + "loss": 3.3617, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1751873571358846e-05, + "loss": 3.3612, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743487623848324e-05, + "loss": 3.366, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1735101676337805e-05, + "loss": 3.3777, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1726715728827285e-05, + "loss": 3.3715, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718346160120496e-05, + "loss": 3.379, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1709960212609976e-05, + "loss": 3.3649, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1701574265099456e-05, + "loss": 3.3691, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693188317588936e-05, + "loss": 3.3642, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1684818748882147e-05, + "loss": 3.3781, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1676432801371627e-05, + "loss": 3.3695, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668046853861107e-05, + "loss": 3.3803, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1659660906350587e-05, + "loss": 3.3699, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1651291337643798e-05, + "loss": 3.3661, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1642905390133277e-05, + "loss": 3.3834, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1634519442622759e-05, + "loss": 3.3601, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626133495112237e-05, + "loss": 3.3636, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.161776392640545e-05, + "loss": 3.3728, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.160937797889493e-05, + "loss": 3.3638, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.160099203138441e-05, + "loss": 3.365, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1592606083873888e-05, + "loss": 3.3717, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.15842365151671e-05, + "loss": 3.3595, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.157585056765658e-05, + "loss": 3.3753, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567464620146059e-05, + "loss": 3.3698, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.155907867263554e-05, + "loss": 3.3702, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1550709103928751e-05, + "loss": 3.3792, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542323156418231e-05, + "loss": 3.3854, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1533937208907711e-05, + "loss": 3.371, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525567640200922e-05, + "loss": 3.3715, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1517181692690404e-05, + "loss": 3.3695, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1508795745179883e-05, + "loss": 3.3675, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1500409797669362e-05, + "loss": 3.3648, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492040228962574e-05, + "loss": 3.3696, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483654281452054e-05, + "loss": 3.3621, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475268333941532e-05, + "loss": 3.3775, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1466882386431012e-05, + "loss": 3.3686, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458512817724225e-05, + "loss": 3.371, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450126870213705e-05, + "loss": 3.3699, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1441740922703185e-05, + "loss": 3.3654, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433354975192665e-05, + "loss": 3.3677, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1424985406485876e-05, + "loss": 3.3826, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1416599458975357e-05, + "loss": 3.3783, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408213511464835e-05, + "loss": 3.374, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1399827563954315e-05, + "loss": 3.3619, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391457995247528e-05, + "loss": 3.372, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383072047737006e-05, + "loss": 3.3681, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1374686100226486e-05, + "loss": 3.368, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1366300152715966e-05, + "loss": 3.374, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1357930584009179e-05, + "loss": 3.3864, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1349544636498657e-05, + "loss": 3.3716, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341158688988138e-05, + "loss": 3.3794, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1332772741477618e-05, + "loss": 3.3713, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1324403172770828e-05, + "loss": 3.3764, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.131601722526031e-05, + "loss": 3.3626, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1307631277749789e-05, + "loss": 3.3667, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1299245330239269e-05, + "loss": 3.3765, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.129087576153248e-05, + "loss": 3.3583, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.128248981402196e-05, + "loss": 3.3731, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.127410386651144e-05, + "loss": 3.3647, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.86952543258667, + "eval_runtime": 303.7559, + "eval_samples_per_second": 1256.242, + "eval_steps_per_second": 39.258, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.126571791900092e-05, + "loss": 3.3695, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.12573319714904e-05, + "loss": 3.3677, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.124894602397988e-05, + "loss": 3.3666, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.124056007646936e-05, + "loss": 3.3794, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.123219050776257e-05, + "loss": 3.3785, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.122380456025205e-05, + "loss": 3.3836, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.121541861274153e-05, + "loss": 3.3684, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207049044034743e-05, + "loss": 3.3714, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1198663096524221e-05, + "loss": 3.3605, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190277149013701e-05, + "loss": 3.375, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1181891201503183e-05, + "loss": 3.3693, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1173505253992661e-05, + "loss": 3.3699, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165119306482141e-05, + "loss": 3.372, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1156749737775353e-05, + "loss": 3.3633, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1148363790264833e-05, + "loss": 3.3612, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1139977842754312e-05, + "loss": 3.3588, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1131591895243793e-05, + "loss": 3.3574, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123205947733273e-05, + "loss": 3.3642, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1114820000222751e-05, + "loss": 3.3681, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106434052712231e-05, + "loss": 3.3637, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098064484005444e-05, + "loss": 3.3801, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1089678536494924e-05, + "loss": 3.3721, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081292588984404e-05, + "loss": 3.3681, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1072906641473884e-05, + "loss": 3.3667, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064537072767095e-05, + "loss": 3.3819, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1056151125256575e-05, + "loss": 3.3622, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1047765177746054e-05, + "loss": 3.3695, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039379230235534e-05, + "loss": 3.3616, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031009661528747e-05, + "loss": 3.3662, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1022623714018225e-05, + "loss": 3.3638, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1014237766507705e-05, + "loss": 3.3634, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1005851818997185e-05, + "loss": 3.3728, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0997482250290398e-05, + "loss": 3.3749, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989096302779876e-05, + "loss": 3.3716, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0980710355269356e-05, + "loss": 3.3691, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0972324407758837e-05, + "loss": 3.3717, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0963954839052047e-05, + "loss": 3.3741, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0955568891541528e-05, + "loss": 3.3566, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0947182944031008e-05, + "loss": 3.366, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0938796996520488e-05, + "loss": 3.3506, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0930427427813699e-05, + "loss": 3.3654, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922041480303179e-05, + "loss": 3.3549, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0913655532792659e-05, + "loss": 3.3836, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905269585282139e-05, + "loss": 3.3643, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.089690001657535e-05, + "loss": 3.3589, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.088851406906483e-05, + "loss": 3.3661, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.088012812155431e-05, + "loss": 3.3702, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.087174217404379e-05, + "loss": 3.3605, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0863372605337e-05, + "loss": 3.3441, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0854986657826482e-05, + "loss": 3.3625, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0846600710315962e-05, + "loss": 3.3756, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.083821476280544e-05, + "loss": 3.3711, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0829845194098653e-05, + "loss": 3.3659, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0821459246588132e-05, + "loss": 3.3556, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.081307329907761e-05, + "loss": 3.3661, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.080468735156709e-05, + "loss": 3.3499, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0796317782860303e-05, + "loss": 3.3793, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0787931835349783e-05, + "loss": 3.3507, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0779545887839263e-05, + "loss": 3.3789, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771159940328743e-05, + "loss": 3.3731, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0762790371621954e-05, + "loss": 3.348, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754404424111434e-05, + "loss": 3.3657, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746018476600914e-05, + "loss": 3.3701, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0737632529090394e-05, + "loss": 3.3465, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729262960383606e-05, + "loss": 3.3554, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0720877012873084e-05, + "loss": 3.3762, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712491065362564e-05, + "loss": 3.3612, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704105117852044e-05, + "loss": 3.3557, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0695735549145257e-05, + "loss": 3.3514, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687349601634735e-05, + "loss": 3.3626, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0678963654124217e-05, + "loss": 3.3511, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0670577706613697e-05, + "loss": 3.3674, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0662208137906906e-05, + "loss": 3.3551, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0653822190396387e-05, + "loss": 3.3657, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0645436242885867e-05, + "loss": 3.37, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0637050295375347e-05, + "loss": 3.3644, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0628680726668558e-05, + "loss": 3.3619, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0620294779158038e-05, + "loss": 3.3606, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0611908831647518e-05, + "loss": 3.3686, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0603522884136998e-05, + "loss": 3.3653, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595153315430209e-05, + "loss": 3.3631, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0586767367919689e-05, + "loss": 3.3622, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.057838142040917e-05, + "loss": 3.363, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0569995472898649e-05, + "loss": 3.3622, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.056162590419186e-05, + "loss": 3.3466, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0553239956681341e-05, + "loss": 3.3606, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0544854009170821e-05, + "loss": 3.3594, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.05364680616603e-05, + "loss": 3.3625, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0528098492953512e-05, + "loss": 3.3625, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0519712545442992e-05, + "loss": 3.3613, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.051132659793247e-05, + "loss": 3.3545, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0502957029225683e-05, + "loss": 3.349, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0494571081715163e-05, + "loss": 3.3563, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486185134204642e-05, + "loss": 3.3682, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0477799186694122e-05, + "loss": 3.3632, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469429617987333e-05, + "loss": 3.3704, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461043670476813e-05, + "loss": 3.3583, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0452657722966295e-05, + "loss": 3.358, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444271775455773e-05, + "loss": 3.3564, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0435902206748986e-05, + "loss": 3.3699, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427516259238466e-05, + "loss": 3.3609, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419130311727944e-05, + "loss": 3.3715, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0410744364217424e-05, + "loss": 3.3572, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0402374795510636e-05, + "loss": 3.3562, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0393988848000116e-05, + "loss": 3.3739, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0385602900489594e-05, + "loss": 3.3543, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377216952979076e-05, + "loss": 3.3546, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0368847384272287e-05, + "loss": 3.3622, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0360461436761767e-05, + "loss": 3.3602, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352075489251247e-05, + "loss": 3.352, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0343689541740727e-05, + "loss": 3.3596, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.033531997303394e-05, + "loss": 3.3514, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0326934025523417e-05, + "loss": 3.3599, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0318548078012897e-05, + "loss": 3.3609, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0310162130502377e-05, + "loss": 3.3603, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.030179256179559e-05, + "loss": 3.3647, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0293406614285068e-05, + "loss": 3.3801, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285020666774548e-05, + "loss": 3.361, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.027663471926403e-05, + "loss": 3.3629, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.026826515055724e-05, + "loss": 3.3585, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.025987920304672e-05, + "loss": 3.3577, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.02514932555362e-05, + "loss": 3.3544, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.024310730802568e-05, + "loss": 3.36, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0234737739318891e-05, + "loss": 3.3567, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0226351791808371e-05, + "loss": 3.3676, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0217965844297851e-05, + "loss": 3.3599, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0209579896787331e-05, + "loss": 3.3633, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0201210328080542e-05, + "loss": 3.3598, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0192824380570022e-05, + "loss": 3.3551, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0184438433059502e-05, + "loss": 3.3554, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0176052485548982e-05, + "loss": 3.3712, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0167682916842193e-05, + "loss": 3.3743, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159296969331674e-05, + "loss": 3.3657, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0150911021821154e-05, + "loss": 3.3526, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0142525074310632e-05, + "loss": 3.3582, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0134155505603845e-05, + "loss": 3.3632, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0125769558093325e-05, + "loss": 3.3597, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117383610582805e-05, + "loss": 3.3635, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0108997663072283e-05, + "loss": 3.3763, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0100628094365496e-05, + "loss": 3.3595, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092242146854975e-05, + "loss": 3.3731, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0083856199344455e-05, + "loss": 3.3604, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075470251833935e-05, + "loss": 3.3669, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067100683127146e-05, + "loss": 3.3589, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0058714735616626e-05, + "loss": 3.3533, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0050328788106106e-05, + "loss": 3.3663, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0041959219399317e-05, + "loss": 3.3528, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0033573271888799e-05, + "loss": 3.3606, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025187324378277e-05, + "loss": 3.3566, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0016801376867757e-05, + "loss": 3.3613, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.869974136352539, + "eval_runtime": 304.5387, + "eval_samples_per_second": 1253.013, + "eval_steps_per_second": 39.158, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0008415429357237e-05, + "loss": 3.3561, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 1.0000029481846718e-05, + "loss": 3.3617, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.991643534336197e-06, + "loss": 3.3685, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.983273965629409e-06, + "loss": 3.3694, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.974888018118889e-06, + "loss": 3.3768, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.966502070608367e-06, + "loss": 3.3591, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.95813250190158e-06, + "loss": 3.3561, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.94974655439106e-06, + "loss": 3.3555, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.94136060688054e-06, + "loss": 3.3641, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.932974659370018e-06, + "loss": 3.3593, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.9245887118595e-06, + "loss": 3.3606, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.91620276434898e-06, + "loss": 3.3596, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.90783319564219e-06, + "loss": 3.3561, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.89944724813167e-06, + "loss": 3.3564, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.89106130062115e-06, + "loss": 3.3514, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.88267535311063e-06, + "loss": 3.3467, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.87428940560011e-06, + "loss": 3.3537, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.86590345808959e-06, + "loss": 3.3591, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.85751751057907e-06, + "loss": 3.3546, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.849147941872283e-06, + "loss": 3.3726, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.840761994361761e-06, + "loss": 3.3597, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.83237604685124e-06, + "loss": 3.3631, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.82399009934072e-06, + "loss": 3.3547, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.815620530633932e-06, + "loss": 3.3697, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.807234583123412e-06, + "loss": 3.3545, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.798848635612891e-06, + "loss": 3.3605, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.790462688102373e-06, + "loss": 3.3503, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.782093119395582e-06, + "loss": 3.3588, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.773707171885064e-06, + "loss": 3.3486, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.765321224374544e-06, + "loss": 3.3576, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.756935276864022e-06, + "loss": 3.3646, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.748565708157235e-06, + "loss": 3.3592, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.740179760646715e-06, + "loss": 3.364, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.731793813136194e-06, + "loss": 3.3624, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.723407865625673e-06, + "loss": 3.3562, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.715038296918885e-06, + "loss": 3.3692, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.706652349408365e-06, + "loss": 3.3501, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.698266401897845e-06, + "loss": 3.3555, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.689880454387325e-06, + "loss": 3.3423, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.681510885680536e-06, + "loss": 3.3517, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.673124938170018e-06, + "loss": 3.3473, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.664738990659496e-06, + "loss": 3.3699, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.656353043148976e-06, + "loss": 3.3559, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.647983474442188e-06, + "loss": 3.3519, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.639597526931668e-06, + "loss": 3.3607, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.631211579421146e-06, + "loss": 3.3583, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.622825631910626e-06, + "loss": 3.3499, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.614456063203839e-06, + "loss": 3.3395, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.606070115693319e-06, + "loss": 3.347, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.597684168182799e-06, + "loss": 3.3685, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.589298220672279e-06, + "loss": 3.3654, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.58092865196549e-06, + "loss": 3.352, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.57254270445497e-06, + "loss": 3.3476, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.56415675694445e-06, + "loss": 3.3582, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.55577080943393e-06, + "loss": 3.3413, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.547401240727142e-06, + "loss": 3.362, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.53901529321662e-06, + "loss": 3.3437, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.5306293457061e-06, + "loss": 3.3699, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.52224339819558e-06, + "loss": 3.3625, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.513873829488793e-06, + "loss": 3.3464, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.50548788197827e-06, + "loss": 3.3507, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.497101934467752e-06, + "loss": 3.3637, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.488715986957232e-06, + "loss": 3.3383, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.480346418250442e-06, + "loss": 3.3455, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.471960470739923e-06, + "loss": 3.364, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.463574523229403e-06, + "loss": 3.3553, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.455188575718881e-06, + "loss": 3.3487, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.446819007012094e-06, + "loss": 3.3444, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.438433059501574e-06, + "loss": 3.35, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.430047111991054e-06, + "loss": 3.3423, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.421661164480534e-06, + "loss": 3.3603, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.413291595773745e-06, + "loss": 3.3449, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.404905648263224e-06, + "loss": 3.3578, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.396519700752706e-06, + "loss": 3.3576, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.388133753242184e-06, + "loss": 3.3605, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.379764184535395e-06, + "loss": 3.3506, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.371378237024877e-06, + "loss": 3.3533, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.362992289514355e-06, + "loss": 3.3566, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.354622720807568e-06, + "loss": 3.3563, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.346236773297048e-06, + "loss": 3.3526, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.337850825786527e-06, + "loss": 3.3525, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.329464878276006e-06, + "loss": 3.3539, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.321095309569218e-06, + "loss": 3.3506, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.312709362058698e-06, + "loss": 3.3445, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.304323414548178e-06, + "loss": 3.3469, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.295937467037658e-06, + "loss": 3.3521, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.287567898330869e-06, + "loss": 3.3584, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.279181950820349e-06, + "loss": 3.3521, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.270796003309829e-06, + "loss": 3.3518, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.262410055799309e-06, + "loss": 3.3439, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.254040487092521e-06, + "loss": 3.3405, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.245654539582001e-06, + "loss": 3.3461, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.23726859207148e-06, + "loss": 3.3551, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.22888264456096e-06, + "loss": 3.3541, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.220513075854172e-06, + "loss": 3.3614, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.212127128343652e-06, + "loss": 3.3565, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.20374118083313e-06, + "loss": 3.3426, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.195355233322612e-06, + "loss": 3.3481, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.186985664615823e-06, + "loss": 3.355, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.178599717105303e-06, + "loss": 3.3567, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.170213769594782e-06, + "loss": 3.3606, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.161827822084262e-06, + "loss": 3.3516, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.153458253377473e-06, + "loss": 3.3457, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.145072305866953e-06, + "loss": 3.3664, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.136686358356433e-06, + "loss": 3.3428, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.128300410845913e-06, + "loss": 3.3465, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.119930842139126e-06, + "loss": 3.3504, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.111544894628604e-06, + "loss": 3.3545, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.103158947118084e-06, + "loss": 3.339, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.094772999607565e-06, + "loss": 3.354, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.086403430900775e-06, + "loss": 3.3448, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.078017483390256e-06, + "loss": 3.3531, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.069631535879736e-06, + "loss": 3.3512, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.061245588369216e-06, + "loss": 3.3476, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.052876019662427e-06, + "loss": 3.3597, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.044490072151907e-06, + "loss": 3.3672, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.036104124641387e-06, + "loss": 3.3549, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.027718177130865e-06, + "loss": 3.3483, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.019348608424078e-06, + "loss": 3.3514, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.010962660913558e-06, + "loss": 3.3472, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 9.002576713403037e-06, + "loss": 3.3514, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.994190765892517e-06, + "loss": 3.3496, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.985821197185728e-06, + "loss": 3.3473, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.977435249675208e-06, + "loss": 3.3544, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.96904930216469e-06, + "loss": 3.3513, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.960663354654168e-06, + "loss": 3.351, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.95229378594738e-06, + "loss": 3.3496, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.94390783843686e-06, + "loss": 3.3457, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.935521890926339e-06, + "loss": 3.3504, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.927135943415819e-06, + "loss": 3.3611, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.918766374709031e-06, + "loss": 3.3634, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.910380427198511e-06, + "loss": 3.3582, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.901994479687991e-06, + "loss": 3.3404, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.893624910981202e-06, + "loss": 3.3535, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.885238963470682e-06, + "loss": 3.3518, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.876853015960162e-06, + "loss": 3.3509, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.868467068449642e-06, + "loss": 3.3496, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.860097499742853e-06, + "loss": 3.3678, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.851711552232334e-06, + "loss": 3.3489, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.843325604721812e-06, + "loss": 3.3661, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.834939657211292e-06, + "loss": 3.3504, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.826570088504505e-06, + "loss": 3.3594, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.818184140993985e-06, + "loss": 3.3468, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.809798193483463e-06, + "loss": 3.3467, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.801412245972945e-06, + "loss": 3.3553, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.793042677266156e-06, + "loss": 3.3458, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.784656729755634e-06, + "loss": 3.3511, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.776270782245115e-06, + "loss": 3.3467, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.767884834734595e-06, + "loss": 3.3501, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.8708646297454834, + "eval_runtime": 309.1914, + "eval_samples_per_second": 1234.158, + "eval_steps_per_second": 38.568, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.759515266027806e-06, + "loss": 3.3485, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.751129318517286e-06, + "loss": 3.3525, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.742743371006766e-06, + "loss": 3.3596, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.734357423496246e-06, + "loss": 3.3565, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.725987854789459e-06, + "loss": 3.3682, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.717601907278937e-06, + "loss": 3.3493, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.70923233857215e-06, + "loss": 3.3505, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.70084639106163e-06, + "loss": 3.3453, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.692460443551108e-06, + "loss": 3.3559, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.684074496040588e-06, + "loss": 3.3499, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.67568854853007e-06, + "loss": 3.3496, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.667302601019549e-06, + "loss": 3.3529, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.658933032312758e-06, + "loss": 3.343, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.65054708480224e-06, + "loss": 3.3491, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.64216113729172e-06, + "loss": 3.3402, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.633775189781198e-06, + "loss": 3.342, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.62538924227068e-06, + "loss": 3.3429, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.61700329476016e-06, + "loss": 3.3465, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.60861734724964e-06, + "loss": 3.3445, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.60024777854285e-06, + "loss": 3.3693, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.59186183103233e-06, + "loss": 3.3487, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.58347588352181e-06, + "loss": 3.3503, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.575089936011289e-06, + "loss": 3.3495, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.566720367304501e-06, + "loss": 3.3557, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.558334419793981e-06, + "loss": 3.3492, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.549948472283461e-06, + "loss": 3.3549, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.541562524772941e-06, + "loss": 3.3396, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.533192956066152e-06, + "loss": 3.3499, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.524807008555632e-06, + "loss": 3.3368, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.516421061045113e-06, + "loss": 3.3534, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.508035113534592e-06, + "loss": 3.3514, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.499665544827804e-06, + "loss": 3.3514, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.491279597317284e-06, + "loss": 3.3564, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.482893649806762e-06, + "loss": 3.3511, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.474507702296242e-06, + "loss": 3.3512, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.466138133589455e-06, + "loss": 3.3571, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.457752186078935e-06, + "loss": 3.3447, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.449366238568415e-06, + "loss": 3.3445, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.440980291057895e-06, + "loss": 3.3346, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.432610722351105e-06, + "loss": 3.344, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.424224774840585e-06, + "loss": 3.3409, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.415838827330065e-06, + "loss": 3.3589, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.407452879819545e-06, + "loss": 3.3455, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.399083311112758e-06, + "loss": 3.344, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.390697363602236e-06, + "loss": 3.3525, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.382311416091716e-06, + "loss": 3.3453, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.373925468581196e-06, + "loss": 3.3438, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.365555899874408e-06, + "loss": 3.3345, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.357169952363887e-06, + "loss": 3.3346, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.348784004853367e-06, + "loss": 3.3576, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.340398057342848e-06, + "loss": 3.3543, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.332028488636059e-06, + "loss": 3.3413, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.323642541125539e-06, + "loss": 3.3432, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.315256593615019e-06, + "loss": 3.3481, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.306870646104499e-06, + "loss": 3.3339, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.29850107739771e-06, + "loss": 3.3554, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.29011512988719e-06, + "loss": 3.3341, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.28172918237667e-06, + "loss": 3.3581, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.27334323486615e-06, + "loss": 3.3551, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.26497366615936e-06, + "loss": 3.338, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.25658771864884e-06, + "loss": 3.3421, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.24820177113832e-06, + "loss": 3.3531, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.2398158236278e-06, + "loss": 3.3265, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.231446254921011e-06, + "loss": 3.3399, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.223060307410493e-06, + "loss": 3.3531, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.214674359899973e-06, + "loss": 3.3496, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.206288412389451e-06, + "loss": 3.3367, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.197918843682663e-06, + "loss": 3.3349, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.189532896172143e-06, + "loss": 3.3409, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.181146948661623e-06, + "loss": 3.3362, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.172761001151103e-06, + "loss": 3.3469, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.164391432444314e-06, + "loss": 3.3359, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.156005484933794e-06, + "loss": 3.3509, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.147619537423274e-06, + "loss": 3.3508, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.139233589912754e-06, + "loss": 3.3498, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.130864021205965e-06, + "loss": 3.338, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.122478073695446e-06, + "loss": 3.3458, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.114092126184925e-06, + "loss": 3.3474, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.105706178674405e-06, + "loss": 3.3463, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.097336609967617e-06, + "loss": 3.3462, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.088950662457095e-06, + "loss": 3.3445, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.080564714946575e-06, + "loss": 3.3476, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.072195146239788e-06, + "loss": 3.3411, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.063809198729268e-06, + "loss": 3.332, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.055423251218746e-06, + "loss": 3.337, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.047037303708228e-06, + "loss": 3.3415, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.038667735001438e-06, + "loss": 3.3494, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.030281787490918e-06, + "loss": 3.3441, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.021895839980398e-06, + "loss": 3.3411, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.013509892469878e-06, + "loss": 3.3346, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.005140323763089e-06, + "loss": 3.3336, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.996754376252569e-06, + "loss": 3.3357, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.988368428742049e-06, + "loss": 3.3458, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.979982481231529e-06, + "loss": 3.3448, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.971612912524741e-06, + "loss": 3.3529, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.96322696501422e-06, + "loss": 3.3446, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.9548410175037e-06, + "loss": 3.3364, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.946455069993181e-06, + "loss": 3.339, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.938085501286392e-06, + "loss": 3.3433, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.92969955377587e-06, + "loss": 3.351, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.921313606265352e-06, + "loss": 3.3508, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.912927658754832e-06, + "loss": 3.3415, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.904558090048043e-06, + "loss": 3.3378, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.896172142537523e-06, + "loss": 3.3555, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.887786195027003e-06, + "loss": 3.334, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.879400247516483e-06, + "loss": 3.3421, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.871030678809693e-06, + "loss": 3.342, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.862644731299173e-06, + "loss": 3.3436, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.854258783788653e-06, + "loss": 3.3318, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.845872836278133e-06, + "loss": 3.3452, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.837503267571344e-06, + "loss": 3.3329, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.829117320060824e-06, + "loss": 3.3434, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.820731372550306e-06, + "loss": 3.3437, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.812345425039784e-06, + "loss": 3.3363, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.803975856332996e-06, + "loss": 3.3554, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.795589908822476e-06, + "loss": 3.3555, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.787203961311956e-06, + "loss": 3.3448, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.778818013801435e-06, + "loss": 3.341, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.770448445094647e-06, + "loss": 3.3409, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.762062497584127e-06, + "loss": 3.3426, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.753676550073605e-06, + "loss": 3.336, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.745290602563087e-06, + "loss": 3.3458, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.736921033856298e-06, + "loss": 3.3341, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.728535086345778e-06, + "loss": 3.3443, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.720149138835258e-06, + "loss": 3.345, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.711763191324738e-06, + "loss": 3.3476, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.70339362261795e-06, + "loss": 3.3364, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.69500767510743e-06, + "loss": 3.3351, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.686621727596908e-06, + "loss": 3.3472, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.678235780086388e-06, + "loss": 3.3473, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.6698662113796e-06, + "loss": 3.3532, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.661480263869079e-06, + "loss": 3.3496, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.653094316358559e-06, + "loss": 3.3343, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.64470836884804e-06, + "loss": 3.3446, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.636338800141251e-06, + "loss": 3.3451, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.6279528526307305e-06, + "loss": 3.3398, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.619566905120211e-06, + "loss": 3.3421, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.611180957609691e-06, + "loss": 3.3544, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.602811388902903e-06, + "loss": 3.3411, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.594425441392382e-06, + "loss": 3.3605, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.586039493881862e-06, + "loss": 3.3402, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.577669925175074e-06, + "loss": 3.3474, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.569283977664553e-06, + "loss": 3.3416, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.560898030154033e-06, + "loss": 3.3379, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.5525120826435135e-06, + "loss": 3.3451, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.544142513936725e-06, + "loss": 3.3393, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.535756566426204e-06, + "loss": 3.3407, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.527370618915684e-06, + "loss": 3.3339, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.518984671405164e-06, + "loss": 3.3403, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.8718197345733643, + "eval_runtime": 308.4832, + "eval_samples_per_second": 1236.991, + "eval_steps_per_second": 38.657, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.510598723894643e-06, + "loss": 3.3388, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.502212776384124e-06, + "loss": 3.3422, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.493826828873604e-06, + "loss": 3.3509, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.485440881363083e-06, + "loss": 3.3449, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.477071312656295e-06, + "loss": 3.3631, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.468685365145775e-06, + "loss": 3.3389, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.460315796438986e-06, + "loss": 3.3435, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.4519298489284655e-06, + "loss": 3.3322, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.443543901417946e-06, + "loss": 3.3463, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.435157953907426e-06, + "loss": 3.3406, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.426772006396906e-06, + "loss": 3.3376, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.418386058886385e-06, + "loss": 3.3503, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.410016490179597e-06, + "loss": 3.3335, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.401630542669078e-06, + "loss": 3.3424, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.393244595158556e-06, + "loss": 3.3293, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.384858647648037e-06, + "loss": 3.3345, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.376472700137517e-06, + "loss": 3.3285, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.3680867526269975e-06, + "loss": 3.3418, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.359700805116476e-06, + "loss": 3.3366, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.351314857605957e-06, + "loss": 3.3565, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.342945288899168e-06, + "loss": 3.3412, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.334559341388647e-06, + "loss": 3.3422, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.326173393878127e-06, + "loss": 3.3386, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.317803825171339e-06, + "loss": 3.3493, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.30941787766082e-06, + "loss": 3.3396, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.301031930150298e-06, + "loss": 3.3463, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.292645982639779e-06, + "loss": 3.3331, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.2842764139329904e-06, + "loss": 3.3376, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.27589046642247e-06, + "loss": 3.3249, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.2675045189119495e-06, + "loss": 3.3458, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.2591185714014295e-06, + "loss": 3.3452, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.250749002694641e-06, + "loss": 3.3413, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.24236305518412e-06, + "loss": 3.3512, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.233977107673601e-06, + "loss": 3.3412, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.225591160163081e-06, + "loss": 3.3365, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.217221591456293e-06, + "loss": 3.3489, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.208835643945772e-06, + "loss": 3.3366, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.200449696435252e-06, + "loss": 3.3326, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.1920637489247325e-06, + "loss": 3.327, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.183694180217944e-06, + "loss": 3.334, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.175308232707423e-06, + "loss": 3.333, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.166922285196903e-06, + "loss": 3.3474, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.158536337686383e-06, + "loss": 3.3413, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.150166768979594e-06, + "loss": 3.3301, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.141780821469074e-06, + "loss": 3.3462, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.133394873958555e-06, + "loss": 3.3366, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.125008926448035e-06, + "loss": 3.3302, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.116639357741245e-06, + "loss": 3.3278, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.108253410230725e-06, + "loss": 3.3222, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.099867462720205e-06, + "loss": 3.3483, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.0914815152096844e-06, + "loss": 3.3462, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.083111946502896e-06, + "loss": 3.334, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.074725998992376e-06, + "loss": 3.3318, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.066340051481857e-06, + "loss": 3.3391, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.057954103971336e-06, + "loss": 3.3224, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.049584535264548e-06, + "loss": 3.3455, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.0411985877540275e-06, + "loss": 3.3271, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.032812640243508e-06, + "loss": 3.3442, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.024426692732987e-06, + "loss": 3.3511, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.016057124026198e-06, + "loss": 3.3326, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.007671176515679e-06, + "loss": 3.3271, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.999285229005158e-06, + "loss": 3.3446, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.990899281494638e-06, + "loss": 3.3192, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.98252971278785e-06, + "loss": 3.3318, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.97414376527733e-06, + "loss": 3.3427, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.965757817766809e-06, + "loss": 3.344, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.95737187025629e-06, + "loss": 3.3305, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.949002301549501e-06, + "loss": 3.3246, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.940616354038981e-06, + "loss": 3.3284, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.93223040652846e-06, + "loss": 3.3249, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.92384445901794e-06, + "loss": 3.3383, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.915474890311152e-06, + "loss": 3.3261, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.907088942800631e-06, + "loss": 3.3416, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.898702995290111e-06, + "loss": 3.3406, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.890317047779592e-06, + "loss": 3.3414, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.881947479072803e-06, + "loss": 3.3275, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.8735615315622825e-06, + "loss": 3.3347, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.8651755840517625e-06, + "loss": 3.3411, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.856789636541243e-06, + "loss": 3.3327, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.848420067834455e-06, + "loss": 3.3396, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.840034120323933e-06, + "loss": 3.3348, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.831648172813414e-06, + "loss": 3.3339, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.823262225302894e-06, + "loss": 3.336, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.814892656596105e-06, + "loss": 3.3215, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.806506709085585e-06, + "loss": 3.3316, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.798120761575065e-06, + "loss": 3.3312, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.789734814064544e-06, + "loss": 3.3425, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.781365245357755e-06, + "loss": 3.334, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.772979297847236e-06, + "loss": 3.333, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.764593350336716e-06, + "loss": 3.3257, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.756207402826195e-06, + "loss": 3.3255, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.747837834119407e-06, + "loss": 3.3223, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.739451886608887e-06, + "loss": 3.334, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.731065939098368e-06, + "loss": 3.3453, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.722696370391578e-06, + "loss": 3.3405, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.714310422881058e-06, + "loss": 3.3362, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.705924475370538e-06, + "loss": 3.3265, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.6975385278600175e-06, + "loss": 3.3346, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.689168959153229e-06, + "loss": 3.3307, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.680783011642709e-06, + "loss": 3.3419, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.67239706413219e-06, + "loss": 3.3397, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.664011116621668e-06, + "loss": 3.3354, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.65564154791488e-06, + "loss": 3.3269, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.6472556004043606e-06, + "loss": 3.349, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.6388696528938405e-06, + "loss": 3.3226, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.63048370538332e-06, + "loss": 3.3354, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.622114136676531e-06, + "loss": 3.3253, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.613728189166011e-06, + "loss": 3.3367, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.60534224165549e-06, + "loss": 3.3244, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.596956294144971e-06, + "loss": 3.338, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.588586725438183e-06, + "loss": 3.3285, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.580200777927663e-06, + "loss": 3.3297, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.571814830417142e-06, + "loss": 3.34, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.563428882906622e-06, + "loss": 3.3254, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.5550593141998334e-06, + "loss": 3.3473, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.546673366689314e-06, + "loss": 3.3458, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.538287419178793e-06, + "loss": 3.338, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.529901471668273e-06, + "loss": 3.3315, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.521531902961485e-06, + "loss": 3.3348, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.513145955450964e-06, + "loss": 3.3307, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.504760007940444e-06, + "loss": 3.3282, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.496374060429925e-06, + "loss": 3.337, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.4880044917231364e-06, + "loss": 3.3263, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.479618544212615e-06, + "loss": 3.3352, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.4712325967020955e-06, + "loss": 3.3372, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.4628466491915755e-06, + "loss": 3.3356, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.454477080484787e-06, + "loss": 3.3291, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.446091132974266e-06, + "loss": 3.3265, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.437705185463746e-06, + "loss": 3.3381, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.429319237953227e-06, + "loss": 3.3356, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.420949669246437e-06, + "loss": 3.3398, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.412563721735918e-06, + "loss": 3.3452, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.404177774225398e-06, + "loss": 3.3234, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.3957918267148785e-06, + "loss": 3.3354, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.387422258008088e-06, + "loss": 3.3357, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.379036310497568e-06, + "loss": 3.332, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.370650362987049e-06, + "loss": 3.3342, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.362264415476528e-06, + "loss": 3.3472, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.35389484676974e-06, + "loss": 3.3325, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.34550889925922e-06, + "loss": 3.3496, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.3371229517487e-06, + "loss": 3.3328, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.328737004238179e-06, + "loss": 3.3343, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.3203674355313906e-06, + "loss": 3.3341, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.311981488020871e-06, + "loss": 3.3289, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.303595540510351e-06, + "loss": 3.3347, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.2952095929998304e-06, + "loss": 3.3338, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.286840024293042e-06, + "loss": 3.329, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.278454076782522e-06, + "loss": 3.3269, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.270068129272001e-06, + "loss": 3.3309, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.8717753887176514, + "eval_runtime": 305.9575, + "eval_samples_per_second": 1247.203, + "eval_steps_per_second": 38.976, + "step": 2671200 + }, + { + "epoch": 1.0, + "learning_rate": 6.261682181761482e-06, + "loss": 3.3355, + "step": 2671616 + }, + { + "epoch": 1.0, + "learning_rate": 6.253312613054694e-06, + "loss": 3.3319, + "step": 2672128 + }, + { + "epoch": 1.0, + "learning_rate": 6.244926665544173e-06, + "loss": 3.3404, + "step": 2672640 + }, + { + "epoch": 1.0, + "learning_rate": 6.2365407180336535e-06, + "loss": 3.3361, + "step": 2673152 + }, + { + "epoch": 1.0, + "learning_rate": 6.228154770523133e-06, + "loss": 3.3554, + "step": 2673664 + }, + { + "epoch": 1.0, + "learning_rate": 6.219785201816344e-06, + "loss": 3.3317, + "step": 2674176 + }, + { + "epoch": 1.0, + "learning_rate": 6.211415633109555e-06, + "loss": 3.3351, + "step": 2674688 + }, + { + "epoch": 1.0, + "learning_rate": 6.203029685599036e-06, + "loss": 3.3224, + "step": 2675200 + }, + { + "epoch": 1.0, + "learning_rate": 6.194643738088515e-06, + "loss": 3.3376, + "step": 2675712 + }, + { + "epoch": 1.0, + "learning_rate": 6.186257790577995e-06, + "loss": 3.333, + "step": 2676224 + }, + { + "epoch": 1.0, + "learning_rate": 6.177871843067475e-06, + "loss": 3.3268, + "step": 2676736 + }, + { + "epoch": 1.0, + "learning_rate": 6.169485895556955e-06, + "loss": 3.3357, + "step": 2677248 + }, + { + "epoch": 1.0, + "learning_rate": 6.1611163268501664e-06, + "loss": 3.3276, + "step": 2677760 + }, + { + "epoch": 1.0, + "learning_rate": 6.152730379339646e-06, + "loss": 3.3336, + "step": 2678272 + }, + { + "epoch": 1.0, + "learning_rate": 6.144344431829126e-06, + "loss": 3.3215, + "step": 2678784 + }, + { + "epoch": 1.0, + "learning_rate": 6.135958484318606e-06, + "loss": 3.3258, + "step": 2679296 + }, + { + "epoch": 1.0, + "learning_rate": 6.1275725368080854e-06, + "loss": 3.3218, + "step": 2679808 + }, + { + "epoch": 1.0, + "learning_rate": 6.119186589297566e-06, + "loss": 3.3306, + "step": 2680320 + }, + { + "epoch": 1.0, + "learning_rate": 6.110800641787045e-06, + "loss": 3.3276, + "step": 2680832 + }, + { + "epoch": 1.0, + "learning_rate": 6.102414694276526e-06, + "loss": 3.3467, + "step": 2681344 + }, + { + "epoch": 1.0, + "learning_rate": 6.094045125569737e-06, + "loss": 3.3327, + "step": 2681856 + }, + { + "epoch": 1.0, + "learning_rate": 6.085659178059217e-06, + "loss": 3.3383, + "step": 2682368 + }, + { + "epoch": 1.0, + "learning_rate": 6.077273230548697e-06, + "loss": 3.326, + "step": 2682880 + }, + { + "epoch": 1.0, + "learning_rate": 6.068887283038177e-06, + "loss": 3.3374, + "step": 2683392 + }, + { + "epoch": 1.0, + "learning_rate": 6.0605177143313884e-06, + "loss": 3.3301, + "step": 2683904 + }, + { + "epoch": 1.0, + "learning_rate": 6.0521317668208675e-06, + "loss": 3.338, + "step": 2684416 + }, + { + "epoch": 1.0, + "learning_rate": 6.043745819310348e-06, + "loss": 3.3268, + "step": 2684928 + }, + { + "epoch": 1.0, + "learning_rate": 6.035376250603559e-06, + "loss": 3.3257, + "step": 2685440 + }, + { + "epoch": 1.0, + "learning_rate": 6.026990303093039e-06, + "loss": 3.3208, + "step": 2685952 + }, + { + "epoch": 1.01, + "learning_rate": 6.018604355582519e-06, + "loss": 3.3319, + "step": 2686464 + }, + { + "epoch": 1.01, + "learning_rate": 6.010218408071999e-06, + "loss": 3.3382, + "step": 2686976 + }, + { + "epoch": 1.01, + "learning_rate": 6.00184883936521e-06, + "loss": 3.3319, + "step": 2687488 + }, + { + "epoch": 1.01, + "learning_rate": 5.993462891854691e-06, + "loss": 3.3447, + "step": 2688000 + }, + { + "epoch": 1.01, + "learning_rate": 5.98507694434417e-06, + "loss": 3.335, + "step": 2688512 + }, + { + "epoch": 1.01, + "learning_rate": 5.97669099683365e-06, + "loss": 3.3284, + "step": 2689024 + }, + { + "epoch": 1.01, + "learning_rate": 5.968321428126861e-06, + "loss": 3.3382, + "step": 2689536 + }, + { + "epoch": 1.01, + "learning_rate": 5.959935480616341e-06, + "loss": 3.3326, + "step": 2690048 + }, + { + "epoch": 1.01, + "learning_rate": 5.951549533105821e-06, + "loss": 3.3204, + "step": 2690560 + }, + { + "epoch": 1.01, + "learning_rate": 5.943163585595301e-06, + "loss": 3.3182, + "step": 2691072 + }, + { + "epoch": 1.01, + "learning_rate": 5.934794016888513e-06, + "loss": 3.3253, + "step": 2691584 + }, + { + "epoch": 1.01, + "learning_rate": 5.926408069377992e-06, + "loss": 3.3292, + "step": 2692096 + }, + { + "epoch": 1.01, + "learning_rate": 5.918022121867473e-06, + "loss": 3.3352, + "step": 2692608 + }, + { + "epoch": 1.01, + "learning_rate": 5.909636174356952e-06, + "loss": 3.333, + "step": 2693120 + }, + { + "epoch": 1.01, + "learning_rate": 5.9012666056501635e-06, + "loss": 3.322, + "step": 2693632 + }, + { + "epoch": 1.01, + "learning_rate": 5.892880658139643e-06, + "loss": 3.3342, + "step": 2694144 + }, + { + "epoch": 1.01, + "learning_rate": 5.884494710629123e-06, + "loss": 3.3305, + "step": 2694656 + }, + { + "epoch": 1.01, + "learning_rate": 5.876108763118603e-06, + "loss": 3.3242, + "step": 2695168 + }, + { + "epoch": 1.01, + "learning_rate": 5.867739194411814e-06, + "loss": 3.3171, + "step": 2695680 + }, + { + "epoch": 1.01, + "learning_rate": 5.859353246901295e-06, + "loss": 3.3084, + "step": 2696192 + }, + { + "epoch": 1.01, + "learning_rate": 5.850967299390774e-06, + "loss": 3.3485, + "step": 2696704 + }, + { + "epoch": 1.01, + "learning_rate": 5.842581351880254e-06, + "loss": 3.3341, + "step": 2697216 + }, + { + "epoch": 1.01, + "learning_rate": 5.834211783173466e-06, + "loss": 3.3281, + "step": 2697728 + }, + { + "epoch": 1.01, + "learning_rate": 5.825825835662945e-06, + "loss": 3.3271, + "step": 2698240 + }, + { + "epoch": 1.01, + "learning_rate": 5.8174398881524255e-06, + "loss": 3.3261, + "step": 2698752 + }, + { + "epoch": 1.01, + "learning_rate": 5.809053940641905e-06, + "loss": 3.3163, + "step": 2699264 + }, + { + "epoch": 1.01, + "learning_rate": 5.800684371935117e-06, + "loss": 3.3327, + "step": 2699776 + }, + { + "epoch": 1.01, + "learning_rate": 5.792298424424596e-06, + "loss": 3.322, + "step": 2700288 + }, + { + "epoch": 1.01, + "learning_rate": 5.783912476914077e-06, + "loss": 3.3307, + "step": 2700800 + }, + { + "epoch": 1.01, + "learning_rate": 5.775526529403556e-06, + "loss": 3.3447, + "step": 2701312 + }, + { + "epoch": 1.01, + "learning_rate": 5.767156960696768e-06, + "loss": 3.3238, + "step": 2701824 + }, + { + "epoch": 1.01, + "learning_rate": 5.758771013186248e-06, + "loss": 3.3152, + "step": 2702336 + }, + { + "epoch": 1.01, + "learning_rate": 5.750385065675727e-06, + "loss": 3.3413, + "step": 2702848 + }, + { + "epoch": 1.01, + "learning_rate": 5.741999118165208e-06, + "loss": 3.3097, + "step": 2703360 + }, + { + "epoch": 1.01, + "learning_rate": 5.7336295494584184e-06, + "loss": 3.3172, + "step": 2703872 + }, + { + "epoch": 1.01, + "learning_rate": 5.725243601947898e-06, + "loss": 3.3381, + "step": 2704384 + }, + { + "epoch": 1.01, + "learning_rate": 5.716857654437378e-06, + "loss": 3.3348, + "step": 2704896 + }, + { + "epoch": 1.01, + "learning_rate": 5.708471706926858e-06, + "loss": 3.32, + "step": 2705408 + }, + { + "epoch": 1.01, + "learning_rate": 5.70010213822007e-06, + "loss": 3.3199, + "step": 2705920 + }, + { + "epoch": 1.01, + "learning_rate": 5.69171619070955e-06, + "loss": 3.3159, + "step": 2706432 + }, + { + "epoch": 1.01, + "learning_rate": 5.68333024319903e-06, + "loss": 3.3173, + "step": 2706944 + }, + { + "epoch": 1.01, + "learning_rate": 5.674944295688509e-06, + "loss": 3.3331, + "step": 2707456 + }, + { + "epoch": 1.01, + "learning_rate": 5.666574726981721e-06, + "loss": 3.3146, + "step": 2707968 + }, + { + "epoch": 1.01, + "learning_rate": 5.6581887794712006e-06, + "loss": 3.3353, + "step": 2708480 + }, + { + "epoch": 1.01, + "learning_rate": 5.6498028319606805e-06, + "loss": 3.3272, + "step": 2708992 + }, + { + "epoch": 1.01, + "learning_rate": 5.6414168844501605e-06, + "loss": 3.3376, + "step": 2709504 + }, + { + "epoch": 1.01, + "learning_rate": 5.633047315743372e-06, + "loss": 3.3237, + "step": 2710016 + }, + { + "epoch": 1.01, + "learning_rate": 5.624661368232852e-06, + "loss": 3.321, + "step": 2710528 + }, + { + "epoch": 1.01, + "learning_rate": 5.616275420722332e-06, + "loss": 3.3322, + "step": 2711040 + }, + { + "epoch": 1.01, + "learning_rate": 5.607889473211812e-06, + "loss": 3.3207, + "step": 2711552 + }, + { + "epoch": 1.01, + "learning_rate": 5.599519904505024e-06, + "loss": 3.3361, + "step": 2712064 + }, + { + "epoch": 1.01, + "learning_rate": 5.591133956994503e-06, + "loss": 3.3261, + "step": 2712576 + }, + { + "epoch": 1.01, + "learning_rate": 5.582748009483983e-06, + "loss": 3.3236, + "step": 2713088 + }, + { + "epoch": 1.01, + "learning_rate": 5.574362061973463e-06, + "loss": 3.3245, + "step": 2713600 + }, + { + "epoch": 1.01, + "learning_rate": 5.5659924932666734e-06, + "loss": 3.3157, + "step": 2714112 + }, + { + "epoch": 1.01, + "learning_rate": 5.557606545756154e-06, + "loss": 3.3213, + "step": 2714624 + }, + { + "epoch": 1.01, + "learning_rate": 5.549220598245633e-06, + "loss": 3.3252, + "step": 2715136 + }, + { + "epoch": 1.01, + "learning_rate": 5.540834650735114e-06, + "loss": 3.3298, + "step": 2715648 + }, + { + "epoch": 1.01, + "learning_rate": 5.532465082028325e-06, + "loss": 3.325, + "step": 2716160 + }, + { + "epoch": 1.01, + "learning_rate": 5.524079134517805e-06, + "loss": 3.3243, + "step": 2716672 + }, + { + "epoch": 1.02, + "learning_rate": 5.515693187007285e-06, + "loss": 3.3196, + "step": 2717184 + }, + { + "epoch": 1.02, + "learning_rate": 5.5073236183004965e-06, + "loss": 3.3162, + "step": 2717696 + }, + { + "epoch": 1.02, + "learning_rate": 5.4989376707899764e-06, + "loss": 3.3165, + "step": 2718208 + }, + { + "epoch": 1.02, + "learning_rate": 5.4905517232794555e-06, + "loss": 3.3243, + "step": 2718720 + }, + { + "epoch": 1.02, + "learning_rate": 5.482165775768936e-06, + "loss": 3.3341, + "step": 2719232 + }, + { + "epoch": 1.02, + "learning_rate": 5.473796207062147e-06, + "loss": 3.3381, + "step": 2719744 + }, + { + "epoch": 1.02, + "learning_rate": 5.465410259551627e-06, + "loss": 3.3256, + "step": 2720256 + }, + { + "epoch": 1.02, + "learning_rate": 5.457024312041107e-06, + "loss": 3.3152, + "step": 2720768 + }, + { + "epoch": 1.02, + "learning_rate": 5.448638364530587e-06, + "loss": 3.3225, + "step": 2721280 + }, + { + "epoch": 1.02, + "learning_rate": 5.440268795823799e-06, + "loss": 3.3256, + "step": 2721792 + }, + { + "epoch": 1.02, + "learning_rate": 5.431882848313279e-06, + "loss": 3.3308, + "step": 2722304 + }, + { + "epoch": 1.02, + "learning_rate": 5.4234969008027586e-06, + "loss": 3.3288, + "step": 2722816 + }, + { + "epoch": 1.02, + "learning_rate": 5.415110953292238e-06, + "loss": 3.3255, + "step": 2723328 + }, + { + "epoch": 1.02, + "learning_rate": 5.406741384585449e-06, + "loss": 3.3181, + "step": 2723840 + }, + { + "epoch": 1.02, + "learning_rate": 5.398355437074929e-06, + "loss": 3.3409, + "step": 2724352 + }, + { + "epoch": 1.02, + "learning_rate": 5.389969489564409e-06, + "loss": 3.3118, + "step": 2724864 + }, + { + "epoch": 1.02, + "learning_rate": 5.381583542053889e-06, + "loss": 3.3296, + "step": 2725376 + }, + { + "epoch": 1.02, + "learning_rate": 5.373213973347101e-06, + "loss": 3.3152, + "step": 2725888 + }, + { + "epoch": 1.02, + "learning_rate": 5.36482802583658e-06, + "loss": 3.3266, + "step": 2726400 + }, + { + "epoch": 1.02, + "learning_rate": 5.356442078326061e-06, + "loss": 3.3159, + "step": 2726912 + }, + { + "epoch": 1.02, + "learning_rate": 5.34805613081554e-06, + "loss": 3.3277, + "step": 2727424 + }, + { + "epoch": 1.02, + "learning_rate": 5.339686562108752e-06, + "loss": 3.3201, + "step": 2727936 + }, + { + "epoch": 1.02, + "learning_rate": 5.331300614598231e-06, + "loss": 3.3214, + "step": 2728448 + }, + { + "epoch": 1.02, + "learning_rate": 5.322914667087711e-06, + "loss": 3.3243, + "step": 2728960 + }, + { + "epoch": 1.02, + "learning_rate": 5.314528719577191e-06, + "loss": 3.318, + "step": 2729472 + }, + { + "epoch": 1.02, + "learning_rate": 5.306159150870402e-06, + "loss": 3.3353, + "step": 2729984 + }, + { + "epoch": 1.02, + "learning_rate": 5.297773203359883e-06, + "loss": 3.3382, + "step": 2730496 + }, + { + "epoch": 1.02, + "learning_rate": 5.289387255849362e-06, + "loss": 3.329, + "step": 2731008 + }, + { + "epoch": 1.02, + "learning_rate": 5.281001308338843e-06, + "loss": 3.3231, + "step": 2731520 + }, + { + "epoch": 1.02, + "learning_rate": 5.272631739632054e-06, + "loss": 3.3283, + "step": 2732032 + }, + { + "epoch": 1.02, + "learning_rate": 5.264245792121534e-06, + "loss": 3.3211, + "step": 2732544 + }, + { + "epoch": 1.02, + "learning_rate": 5.2558598446110135e-06, + "loss": 3.3192, + "step": 2733056 + }, + { + "epoch": 1.02, + "learning_rate": 5.2474738971004935e-06, + "loss": 3.3279, + "step": 2733568 + }, + { + "epoch": 1.02, + "learning_rate": 5.239104328393705e-06, + "loss": 3.3116, + "step": 2734080 + }, + { + "epoch": 1.02, + "learning_rate": 5.230718380883184e-06, + "loss": 3.33, + "step": 2734592 + }, + { + "epoch": 1.02, + "learning_rate": 5.222332433372665e-06, + "loss": 3.3253, + "step": 2735104 + }, + { + "epoch": 1.02, + "learning_rate": 5.213946485862144e-06, + "loss": 3.3295, + "step": 2735616 + }, + { + "epoch": 1.02, + "learning_rate": 5.205576917155356e-06, + "loss": 3.3218, + "step": 2736128 + }, + { + "epoch": 1.02, + "learning_rate": 5.197190969644836e-06, + "loss": 3.3175, + "step": 2736640 + }, + { + "epoch": 1.02, + "learning_rate": 5.188805022134315e-06, + "loss": 3.3233, + "step": 2737152 + }, + { + "epoch": 1.02, + "learning_rate": 5.180419074623796e-06, + "loss": 3.3348, + "step": 2737664 + }, + { + "epoch": 1.02, + "learning_rate": 5.1720495059170064e-06, + "loss": 3.3274, + "step": 2738176 + }, + { + "epoch": 1.02, + "learning_rate": 5.163663558406487e-06, + "loss": 3.3376, + "step": 2738688 + }, + { + "epoch": 1.02, + "learning_rate": 5.155277610895966e-06, + "loss": 3.3152, + "step": 2739200 + }, + { + "epoch": 1.02, + "learning_rate": 5.146891663385447e-06, + "loss": 3.327, + "step": 2739712 + }, + { + "epoch": 1.02, + "learning_rate": 5.138522094678658e-06, + "loss": 3.3275, + "step": 2740224 + }, + { + "epoch": 1.02, + "learning_rate": 5.130136147168138e-06, + "loss": 3.3194, + "step": 2740736 + }, + { + "epoch": 1.02, + "learning_rate": 5.121750199657618e-06, + "loss": 3.3233, + "step": 2741248 + }, + { + "epoch": 1.02, + "learning_rate": 5.113364252147097e-06, + "loss": 3.3407, + "step": 2741760 + }, + { + "epoch": 1.02, + "learning_rate": 5.104994683440309e-06, + "loss": 3.3243, + "step": 2742272 + }, + { + "epoch": 1.02, + "learning_rate": 5.0966087359297886e-06, + "loss": 3.3434, + "step": 2742784 + }, + { + "epoch": 1.02, + "learning_rate": 5.0882227884192685e-06, + "loss": 3.322, + "step": 2743296 + }, + { + "epoch": 1.02, + "learning_rate": 5.0798368409087485e-06, + "loss": 3.3294, + "step": 2743808 + }, + { + "epoch": 1.02, + "learning_rate": 5.07146727220196e-06, + "loss": 3.3207, + "step": 2744320 + }, + { + "epoch": 1.02, + "learning_rate": 5.06308132469144e-06, + "loss": 3.3233, + "step": 2744832 + }, + { + "epoch": 1.02, + "learning_rate": 5.05469537718092e-06, + "loss": 3.3262, + "step": 2745344 + }, + { + "epoch": 1.02, + "learning_rate": 5.046325808474131e-06, + "loss": 3.3244, + "step": 2745856 + }, + { + "epoch": 1.02, + "learning_rate": 5.037939860963612e-06, + "loss": 3.3229, + "step": 2746368 + }, + { + "epoch": 1.02, + "learning_rate": 5.029553913453091e-06, + "loss": 3.3133, + "step": 2746880 + }, + { + "epoch": 1.02, + "learning_rate": 5.021167965942571e-06, + "loss": 3.3237, + "step": 2747392 + }, + { + "epoch": 1.03, + "eval_loss": 3.8717565536499023, + "eval_runtime": 302.7812, + "eval_samples_per_second": 1260.286, + "eval_steps_per_second": 39.385, + "step": 2747520 + }, + { + "epoch": 0.0, + "learning_rate": 5.012782018432051e-06, + "loss": 3.3247, + "step": 2747904 + }, + { + "epoch": 0.0, + "learning_rate": 5.004396070921531e-06, + "loss": 3.3238, + "step": 2748416 + }, + { + "epoch": 0.0, + "learning_rate": 4.9960101234110105e-06, + "loss": 3.3324, + "step": 2748928 + }, + { + "epoch": 0.0, + "learning_rate": 4.9876241759004905e-06, + "loss": 3.3284, + "step": 2749440 + }, + { + "epoch": 0.0, + "learning_rate": 4.979254607193702e-06, + "loss": 3.3438, + "step": 2749952 + }, + { + "epoch": 0.0, + "learning_rate": 4.970868659683182e-06, + "loss": 3.3279, + "step": 2750464 + }, + { + "epoch": 0.0, + "learning_rate": 4.962499090976394e-06, + "loss": 3.3256, + "step": 2750976 + }, + { + "epoch": 0.0, + "learning_rate": 4.954113143465873e-06, + "loss": 3.3136, + "step": 2751488 + }, + { + "epoch": 0.0, + "learning_rate": 4.945727195955353e-06, + "loss": 3.3267, + "step": 2752000 + }, + { + "epoch": 0.0, + "learning_rate": 4.937341248444833e-06, + "loss": 3.3227, + "step": 2752512 + }, + { + "epoch": 0.0, + "learning_rate": 4.928955300934313e-06, + "loss": 3.3244, + "step": 2753024 + }, + { + "epoch": 0.0, + "learning_rate": 4.920569353423793e-06, + "loss": 3.3265, + "step": 2753536 + }, + { + "epoch": 0.0, + "learning_rate": 4.9121997847170035e-06, + "loss": 3.3182, + "step": 2754048 + }, + { + "epoch": 0.0, + "learning_rate": 4.903813837206484e-06, + "loss": 3.3259, + "step": 2754560 + }, + { + "epoch": 0.0, + "learning_rate": 4.895427889695963e-06, + "loss": 3.3126, + "step": 2755072 + }, + { + "epoch": 0.0, + "learning_rate": 4.887041942185443e-06, + "loss": 3.3137, + "step": 2755584 + }, + { + "epoch": 0.0, + "learning_rate": 4.878655994674924e-06, + "loss": 3.3121, + "step": 2756096 + }, + { + "epoch": 0.0, + "learning_rate": 4.870270047164403e-06, + "loss": 3.3242, + "step": 2756608 + }, + { + "epoch": 0.0, + "learning_rate": 4.861884099653884e-06, + "loss": 3.3183, + "step": 2757120 + }, + { + "epoch": 0.0, + "learning_rate": 4.853498152143363e-06, + "loss": 3.3378, + "step": 2757632 + }, + { + "epoch": 0.0, + "learning_rate": 4.845128583436575e-06, + "loss": 3.3255, + "step": 2758144 + }, + { + "epoch": 0.0, + "learning_rate": 4.836742635926055e-06, + "loss": 3.3295, + "step": 2758656 + }, + { + "epoch": 0.0, + "learning_rate": 4.828356688415534e-06, + "loss": 3.3203, + "step": 2759168 + }, + { + "epoch": 0.0, + "learning_rate": 4.819970740905015e-06, + "loss": 3.325, + "step": 2759680 + }, + { + "epoch": 0.0, + "learning_rate": 4.8116011721982254e-06, + "loss": 3.323, + "step": 2760192 + }, + { + "epoch": 0.0, + "learning_rate": 4.803215224687705e-06, + "loss": 3.3306, + "step": 2760704 + }, + { + "epoch": 0.0, + "learning_rate": 4.794829277177185e-06, + "loss": 3.3194, + "step": 2761216 + }, + { + "epoch": 0.0, + "learning_rate": 4.786443329666665e-06, + "loss": 3.3188, + "step": 2761728 + }, + { + "epoch": 0.0, + "learning_rate": 4.778073760959877e-06, + "loss": 3.3128, + "step": 2762240 + }, + { + "epoch": 0.0, + "learning_rate": 4.769687813449357e-06, + "loss": 3.3219, + "step": 2762752 + }, + { + "epoch": 0.01, + "learning_rate": 4.761301865938837e-06, + "loss": 3.3306, + "step": 2763264 + }, + { + "epoch": 0.01, + "learning_rate": 4.7529322972320485e-06, + "loss": 3.3235, + "step": 2763776 + }, + { + "epoch": 0.01, + "learning_rate": 4.744546349721528e-06, + "loss": 3.3326, + "step": 2764288 + }, + { + "epoch": 0.01, + "learning_rate": 4.7361604022110076e-06, + "loss": 3.3214, + "step": 2764800 + }, + { + "epoch": 0.01, + "learning_rate": 4.7277744547004875e-06, + "loss": 3.3208, + "step": 2765312 + }, + { + "epoch": 0.01, + "learning_rate": 4.719404885993699e-06, + "loss": 3.3293, + "step": 2765824 + }, + { + "epoch": 0.01, + "learning_rate": 4.711018938483179e-06, + "loss": 3.326, + "step": 2766336 + }, + { + "epoch": 0.01, + "learning_rate": 4.702632990972659e-06, + "loss": 3.3087, + "step": 2766848 + }, + { + "epoch": 0.01, + "learning_rate": 4.694247043462139e-06, + "loss": 3.3152, + "step": 2767360 + }, + { + "epoch": 0.01, + "learning_rate": 4.68587747475535e-06, + "loss": 3.314, + "step": 2767872 + }, + { + "epoch": 0.01, + "learning_rate": 4.677491527244831e-06, + "loss": 3.317, + "step": 2768384 + }, + { + "epoch": 0.01, + "learning_rate": 4.66910557973431e-06, + "loss": 3.3294, + "step": 2768896 + }, + { + "epoch": 0.01, + "learning_rate": 4.66071963222379e-06, + "loss": 3.3223, + "step": 2769408 + }, + { + "epoch": 0.01, + "learning_rate": 4.652350063517001e-06, + "loss": 3.3176, + "step": 2769920 + }, + { + "epoch": 0.01, + "learning_rate": 4.64396411600648e-06, + "loss": 3.3249, + "step": 2770432 + }, + { + "epoch": 0.01, + "learning_rate": 4.635578168495961e-06, + "loss": 3.3158, + "step": 2770944 + }, + { + "epoch": 0.01, + "learning_rate": 4.62719222098544e-06, + "loss": 3.3181, + "step": 2771456 + }, + { + "epoch": 0.01, + "learning_rate": 4.618822652278652e-06, + "loss": 3.3117, + "step": 2771968 + }, + { + "epoch": 0.01, + "learning_rate": 4.610436704768132e-06, + "loss": 3.2969, + "step": 2772480 + }, + { + "epoch": 0.01, + "learning_rate": 4.602050757257612e-06, + "loss": 3.337, + "step": 2772992 + }, + { + "epoch": 0.01, + "learning_rate": 4.593664809747092e-06, + "loss": 3.3253, + "step": 2773504 + }, + { + "epoch": 0.01, + "learning_rate": 4.5852952410403035e-06, + "loss": 3.326, + "step": 2774016 + }, + { + "epoch": 0.01, + "learning_rate": 4.5769092935297834e-06, + "loss": 3.3147, + "step": 2774528 + }, + { + "epoch": 0.01, + "learning_rate": 4.5685233460192625e-06, + "loss": 3.3178, + "step": 2775040 + }, + { + "epoch": 0.01, + "learning_rate": 4.560137398508743e-06, + "loss": 3.3089, + "step": 2775552 + }, + { + "epoch": 0.01, + "learning_rate": 4.551767829801954e-06, + "loss": 3.3229, + "step": 2776064 + }, + { + "epoch": 0.01, + "learning_rate": 4.543381882291434e-06, + "loss": 3.3176, + "step": 2776576 + }, + { + "epoch": 0.01, + "learning_rate": 4.534995934780914e-06, + "loss": 3.3198, + "step": 2777088 + }, + { + "epoch": 0.01, + "learning_rate": 4.526609987270394e-06, + "loss": 3.3371, + "step": 2777600 + }, + { + "epoch": 0.01, + "learning_rate": 4.518240418563606e-06, + "loss": 3.3135, + "step": 2778112 + }, + { + "epoch": 0.01, + "learning_rate": 4.509854471053085e-06, + "loss": 3.3115, + "step": 2778624 + }, + { + "epoch": 0.01, + "learning_rate": 4.5014685235425655e-06, + "loss": 3.3317, + "step": 2779136 + }, + { + "epoch": 0.01, + "learning_rate": 4.493082576032045e-06, + "loss": 3.3014, + "step": 2779648 + }, + { + "epoch": 0.01, + "learning_rate": 4.484713007325256e-06, + "loss": 3.3124, + "step": 2780160 + }, + { + "epoch": 0.01, + "learning_rate": 4.476327059814736e-06, + "loss": 3.3264, + "step": 2780672 + }, + { + "epoch": 0.01, + "learning_rate": 4.467941112304216e-06, + "loss": 3.3225, + "step": 2781184 + }, + { + "epoch": 0.01, + "learning_rate": 4.459555164793696e-06, + "loss": 3.3133, + "step": 2781696 + }, + { + "epoch": 0.01, + "learning_rate": 4.451185596086908e-06, + "loss": 3.3143, + "step": 2782208 + }, + { + "epoch": 0.01, + "learning_rate": 4.442799648576387e-06, + "loss": 3.3039, + "step": 2782720 + }, + { + "epoch": 0.01, + "learning_rate": 4.434413701065867e-06, + "loss": 3.311, + "step": 2783232 + }, + { + "epoch": 0.01, + "learning_rate": 4.426027753555347e-06, + "loss": 3.3206, + "step": 2783744 + }, + { + "epoch": 0.01, + "learning_rate": 4.4176581848485585e-06, + "loss": 3.3113, + "step": 2784256 + }, + { + "epoch": 0.01, + "learning_rate": 4.409272237338038e-06, + "loss": 3.3253, + "step": 2784768 + }, + { + "epoch": 0.01, + "learning_rate": 4.400886289827518e-06, + "loss": 3.3212, + "step": 2785280 + }, + { + "epoch": 0.01, + "learning_rate": 4.392500342316998e-06, + "loss": 3.331, + "step": 2785792 + }, + { + "epoch": 0.01, + "learning_rate": 4.384130773610209e-06, + "loss": 3.3153, + "step": 2786304 + }, + { + "epoch": 0.01, + "learning_rate": 4.37574482609969e-06, + "loss": 3.3141, + "step": 2786816 + }, + { + "epoch": 0.01, + "learning_rate": 4.367358878589169e-06, + "loss": 3.3216, + "step": 2787328 + }, + { + "epoch": 0.01, + "learning_rate": 4.358972931078649e-06, + "loss": 3.3111, + "step": 2787840 + }, + { + "epoch": 0.01, + "learning_rate": 4.350603362371861e-06, + "loss": 3.3295, + "step": 2788352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3422174148613406e-06, + "loss": 3.3179, + "step": 2788864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3338314673508205e-06, + "loss": 3.3149, + "step": 2789376 + }, + { + "epoch": 0.01, + "learning_rate": 4.325461898644031e-06, + "loss": 3.3193, + "step": 2789888 + }, + { + "epoch": 0.01, + "learning_rate": 4.317075951133512e-06, + "loss": 3.3071, + "step": 2790400 + }, + { + "epoch": 0.01, + "learning_rate": 4.308690003622991e-06, + "loss": 3.3099, + "step": 2790912 + }, + { + "epoch": 0.01, + "learning_rate": 4.300304056112472e-06, + "loss": 3.315, + "step": 2791424 + }, + { + "epoch": 0.01, + "learning_rate": 4.291934487405683e-06, + "loss": 3.3222, + "step": 2791936 + }, + { + "epoch": 0.01, + "learning_rate": 4.283548539895163e-06, + "loss": 3.3138, + "step": 2792448 + }, + { + "epoch": 0.01, + "learning_rate": 4.275162592384643e-06, + "loss": 3.3164, + "step": 2792960 + }, + { + "epoch": 0.02, + "learning_rate": 4.266776644874122e-06, + "loss": 3.3084, + "step": 2793472 + }, + { + "epoch": 0.02, + "learning_rate": 4.258407076167334e-06, + "loss": 3.3126, + "step": 2793984 + }, + { + "epoch": 0.02, + "learning_rate": 4.2500211286568134e-06, + "loss": 3.3045, + "step": 2794496 + }, + { + "epoch": 0.02, + "learning_rate": 4.241635181146294e-06, + "loss": 3.3177, + "step": 2795008 + }, + { + "epoch": 0.02, + "learning_rate": 4.233249233635773e-06, + "loss": 3.3249, + "step": 2795520 + }, + { + "epoch": 0.02, + "learning_rate": 4.224879664928985e-06, + "loss": 3.3256, + "step": 2796032 + }, + { + "epoch": 0.02, + "learning_rate": 4.216493717418465e-06, + "loss": 3.3231, + "step": 2796544 + }, + { + "epoch": 0.02, + "learning_rate": 4.208107769907945e-06, + "loss": 3.3065, + "step": 2797056 + }, + { + "epoch": 0.02, + "learning_rate": 4.199721822397425e-06, + "loss": 3.315, + "step": 2797568 + }, + { + "epoch": 0.02, + "learning_rate": 4.1913522536906365e-06, + "loss": 3.3155, + "step": 2798080 + }, + { + "epoch": 0.02, + "learning_rate": 4.182966306180116e-06, + "loss": 3.3235, + "step": 2798592 + }, + { + "epoch": 0.02, + "learning_rate": 4.1745803586695956e-06, + "loss": 3.3216, + "step": 2799104 + }, + { + "epoch": 0.02, + "learning_rate": 4.1661944111590755e-06, + "loss": 3.3172, + "step": 2799616 + }, + { + "epoch": 0.02, + "learning_rate": 4.157824842452287e-06, + "loss": 3.3147, + "step": 2800128 + }, + { + "epoch": 0.02, + "learning_rate": 4.149438894941767e-06, + "loss": 3.3288, + "step": 2800640 + }, + { + "epoch": 0.02, + "learning_rate": 4.141052947431247e-06, + "loss": 3.3062, + "step": 2801152 + }, + { + "epoch": 0.02, + "learning_rate": 4.132666999920727e-06, + "loss": 3.3186, + "step": 2801664 + }, + { + "epoch": 0.02, + "learning_rate": 4.124297431213938e-06, + "loss": 3.3087, + "step": 2802176 + }, + { + "epoch": 0.02, + "learning_rate": 4.115911483703419e-06, + "loss": 3.319, + "step": 2802688 + }, + { + "epoch": 0.02, + "learning_rate": 4.107525536192898e-06, + "loss": 3.3045, + "step": 2803200 + }, + { + "epoch": 0.02, + "learning_rate": 4.099139588682378e-06, + "loss": 3.3204, + "step": 2803712 + }, + { + "epoch": 0.02, + "learning_rate": 4.090770019975589e-06, + "loss": 3.3103, + "step": 2804224 + }, + { + "epoch": 0.02, + "learning_rate": 4.082384072465069e-06, + "loss": 3.3148, + "step": 2804736 + }, + { + "epoch": 0.02, + "learning_rate": 4.073998124954549e-06, + "loss": 3.3178, + "step": 2805248 + }, + { + "epoch": 0.02, + "learning_rate": 4.065612177444029e-06, + "loss": 3.3099, + "step": 2805760 + }, + { + "epoch": 0.02, + "learning_rate": 4.057242608737241e-06, + "loss": 3.3249, + "step": 2806272 + }, + { + "epoch": 0.02, + "learning_rate": 4.04885666122672e-06, + "loss": 3.3302, + "step": 2806784 + }, + { + "epoch": 0.02, + "learning_rate": 4.040470713716201e-06, + "loss": 3.3194, + "step": 2807296 + }, + { + "epoch": 0.02, + "learning_rate": 4.03208476620568e-06, + "loss": 3.317, + "step": 2807808 + }, + { + "epoch": 0.02, + "learning_rate": 4.0237151974988915e-06, + "loss": 3.3159, + "step": 2808320 + }, + { + "epoch": 0.02, + "learning_rate": 4.0153292499883714e-06, + "loss": 3.3133, + "step": 2808832 + }, + { + "epoch": 0.02, + "learning_rate": 4.0069433024778505e-06, + "loss": 3.3096, + "step": 2809344 + }, + { + "epoch": 0.02, + "learning_rate": 3.998557354967331e-06, + "loss": 3.3246, + "step": 2809856 + }, + { + "epoch": 0.02, + "learning_rate": 3.990187786260542e-06, + "loss": 3.302, + "step": 2810368 + }, + { + "epoch": 0.02, + "learning_rate": 3.981801838750022e-06, + "loss": 3.3182, + "step": 2810880 + }, + { + "epoch": 0.02, + "learning_rate": 3.973415891239502e-06, + "loss": 3.3155, + "step": 2811392 + }, + { + "epoch": 0.02, + "learning_rate": 3.965029943728983e-06, + "loss": 3.3222, + "step": 2811904 + }, + { + "epoch": 0.02, + "learning_rate": 3.956660375022194e-06, + "loss": 3.3148, + "step": 2812416 + }, + { + "epoch": 0.02, + "learning_rate": 3.948274427511674e-06, + "loss": 3.312, + "step": 2812928 + }, + { + "epoch": 0.02, + "learning_rate": 3.9398884800011535e-06, + "loss": 3.3135, + "step": 2813440 + }, + { + "epoch": 0.02, + "learning_rate": 3.931502532490633e-06, + "loss": 3.324, + "step": 2813952 + }, + { + "epoch": 0.02, + "learning_rate": 3.923132963783844e-06, + "loss": 3.3224, + "step": 2814464 + }, + { + "epoch": 0.02, + "learning_rate": 3.914747016273324e-06, + "loss": 3.3274, + "step": 2814976 + }, + { + "epoch": 0.02, + "learning_rate": 3.906361068762804e-06, + "loss": 3.3067, + "step": 2815488 + }, + { + "epoch": 0.02, + "learning_rate": 3.897975121252284e-06, + "loss": 3.3197, + "step": 2816000 + }, + { + "epoch": 0.02, + "learning_rate": 3.889605552545496e-06, + "loss": 3.3192, + "step": 2816512 + }, + { + "epoch": 0.02, + "learning_rate": 3.881219605034976e-06, + "loss": 3.3113, + "step": 2817024 + }, + { + "epoch": 0.02, + "learning_rate": 3.872833657524455e-06, + "loss": 3.3166, + "step": 2817536 + }, + { + "epoch": 0.02, + "learning_rate": 3.864447710013936e-06, + "loss": 3.3313, + "step": 2818048 + }, + { + "epoch": 0.02, + "learning_rate": 3.8560781413071465e-06, + "loss": 3.3151, + "step": 2818560 + }, + { + "epoch": 0.02, + "learning_rate": 3.847692193796626e-06, + "loss": 3.3384, + "step": 2819072 + }, + { + "epoch": 0.02, + "learning_rate": 3.839306246286106e-06, + "loss": 3.3137, + "step": 2819584 + }, + { + "epoch": 0.02, + "learning_rate": 3.830920298775586e-06, + "loss": 3.3204, + "step": 2820096 + }, + { + "epoch": 0.02, + "learning_rate": 3.822550730068797e-06, + "loss": 3.3105, + "step": 2820608 + }, + { + "epoch": 0.02, + "learning_rate": 3.814164782558278e-06, + "loss": 3.3137, + "step": 2821120 + }, + { + "epoch": 0.02, + "learning_rate": 3.8057788350477575e-06, + "loss": 3.3203, + "step": 2821632 + }, + { + "epoch": 0.02, + "learning_rate": 3.797392887537237e-06, + "loss": 3.315, + "step": 2822144 + }, + { + "epoch": 0.02, + "learning_rate": 3.7890233188304486e-06, + "loss": 3.3197, + "step": 2822656 + }, + { + "epoch": 0.02, + "learning_rate": 3.780637371319928e-06, + "loss": 3.2992, + "step": 2823168 + }, + { + "epoch": 0.02, + "learning_rate": 3.7722514238094085e-06, + "loss": 3.3183, + "step": 2823680 + }, + { + "epoch": 0.03, + "eval_loss": 3.871791124343872, + "eval_runtime": 304.117, + "eval_samples_per_second": 1254.751, + "eval_steps_per_second": 39.212, + "step": 2823840 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.9283357378034248e+18, + "trial_name": null, + "trial_params": null +}