diff --git "a/checkpoint-1679040/trainer_state.json" "b/checkpoint-1679040/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1679040/trainer_state.json" @@ -0,0 +1,19875 @@ +{ + "best_metric": 3.842865228652954, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-c-command/transformer/4/checkpoints/checkpoint-992160", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1679040, + "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": 10.971, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8154, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1847, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9857, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8193, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7079, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6091, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5446, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4504, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4209, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.36, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3199, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2787, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2129, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1939, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1454, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1243, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.096, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0567, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0328, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0169, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9887, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9587, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9377, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9283, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9015, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8741, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8642, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8442, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8307, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8157, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.8021, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7877, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7701, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.766, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7659, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7421, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7039, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.709, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6884, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6933, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.679, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6728, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6509, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.66, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6436, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6429, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6296, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6088, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.6106, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6125, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.59, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5812, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5749, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.571, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5556, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5736, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5415, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5508, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5421, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5168, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5256, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.515, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.5005, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4936, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.5088, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4867, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4814, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4686, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4814, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4871, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4712, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4646, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4687, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4669, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.458, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4395, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4467, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.435, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4315, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4216, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4283, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4326, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4228, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3977, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.4055, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4086, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.4042, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3994, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3937, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3892, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3766, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3817, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3821, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3737, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.3833, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 4.3616, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3614, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3594, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3576, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3627, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.347, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3416, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3399, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3441, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3255, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111449897566966e-05, + "loss": 4.3178, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103063950056446e-05, + "loss": 4.3277, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094678002545926e-05, + "loss": 4.3325, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086292055035406e-05, + "loss": 4.3254, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.9077906107524886e-05, + "loss": 4.3222, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.9069520160014366e-05, + "loss": 4.3114, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.9061134212503846e-05, + "loss": 4.3221, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3049, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3119, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035992748776015e-05, + "loss": 4.3134, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.3124, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.3014, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.3005, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.3, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.3007, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2895, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2936, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2884, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2913, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2749, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2714, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2777, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.279, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2693, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2824, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2736, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2597, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2663, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2757, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2652, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2612, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2524, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2599, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2648, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2503, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2432, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2483, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.24, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.238, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2466, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.236, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2366, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2339, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2297, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.198172569274902, + "eval_runtime": 303.0817, + "eval_samples_per_second": 1259.037, + "eval_steps_per_second": 39.346, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2177, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2251, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2321, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2205, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.2239, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2168, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2159, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.2005, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2256, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2091, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2195, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2165, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.1987, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.1981, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.1957, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.1873, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1943, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.1865, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1822, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.2057, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1886, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1817, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1789, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1914, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1695, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1674, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1716, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1716, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1654, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.84994886537475e-05, + "loss": 4.1652, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1663, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1691, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1558, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846596124250916e-05, + "loss": 4.1647, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.1718, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.164, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1396, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843243383127081e-05, + "loss": 4.1464, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842404788376029e-05, + "loss": 4.1435, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.1504, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1424, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1507, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.8390520472521936e-05, + "loss": 4.1367, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382134525011416e-05, + "loss": 4.1469, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1451, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1454, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835699306128359e-05, + "loss": 4.1422, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834860711377307e-05, + "loss": 4.1227, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.139, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1418, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.134, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831507970253472e-05, + "loss": 4.1267, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.1205, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.1279, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.1106, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828155229129637e-05, + "loss": 4.1408, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1188, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1304, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256410827568545e-05, + "loss": 4.1292, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.1034, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1196, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1123, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222883416330194e-05, + "loss": 4.1013, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214497468819674e-05, + "loss": 4.0992, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1171, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.1066, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818935600509184e-05, + "loss": 4.1019, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818097005758132e-05, + "loss": 4.0912, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817258411007081e-05, + "loss": 4.1102, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816419816256029e-05, + "loss": 4.1136, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.81558285938535e-05, + "loss": 4.1068, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814744264634298e-05, + "loss": 4.1034, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813905669883246e-05, + "loss": 4.1147, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813067075132194e-05, + "loss": 4.1088, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812230118261515e-05, + "loss": 4.1085, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811391523510463e-05, + "loss": 4.0917, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810552928759411e-05, + "loss": 4.1033, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809714334008359e-05, + "loss": 4.0952, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887737713768e-05, + "loss": 4.0935, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808038782386628e-05, + "loss": 4.09, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.0953, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063615928845243e-05, + "loss": 4.1048, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805524636013845e-05, + "loss": 4.0998, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804686041262793e-05, + "loss": 4.0741, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803847446511741e-05, + "loss": 4.0838, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030088517606886e-05, + "loss": 4.0892, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.0875, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0875, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800496343268279e-05, + "loss": 4.0828, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799657748517227e-05, + "loss": 4.0834, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798819153766175e-05, + "loss": 4.0721, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.0812, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797141964264071e-05, + "loss": 4.0808, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796303369513019e-05, + "loss": 4.0778, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.086, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.0761, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793789223140236e-05, + "loss": 4.0694, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792950628389184e-05, + "loss": 4.0744, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792112033638132e-05, + "loss": 4.0743, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912750767674535e-05, + "loss": 4.0787, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790436482016401e-05, + "loss": 4.0665, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789597887265349e-05, + "loss": 4.0637, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788759292514297e-05, + "loss": 4.0647, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787920697763245e-05, + "loss": 4.0715, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870821030121935e-05, + "loss": 4.0566, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862451461415144e-05, + "loss": 4.0463, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854065513904624e-05, + "loss": 4.0621, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.0635, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.057, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.0587, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.0541, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812135776352024e-05, + "loss": 4.0613, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803749828841504e-05, + "loss": 4.0482, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779538026013471e-05, + "loss": 4.0581, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778699431262419e-05, + "loss": 4.0636, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777860836511367e-05, + "loss": 4.0628, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777023879640689e-05, + "loss": 4.0497, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.0498, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.0543, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774508095387533e-05, + "loss": 4.0564, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773669500636481e-05, + "loss": 4.041, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772830905885429e-05, + "loss": 4.0543, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771992311134377e-05, + "loss": 4.0433, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771153716383325e-05, + "loss": 4.0564, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0379, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0366, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0411, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0449, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.7669640183888106e-05, + "loss": 4.0361, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.7661254236377586e-05, + "loss": 4.0557, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765286828886707e-05, + "loss": 4.0441, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0343, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763611277264976e-05, + "loss": 4.0356, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762772682513924e-05, + "loss": 4.0524, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761934087762872e-05, + "loss": 4.0442, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.0373, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760258536141141e-05, + "loss": 4.0327, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759419941390089e-05, + "loss": 4.0427, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758581346639037e-05, + "loss": 4.0435, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577427518879844e-05, + "loss": 4.0324, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756905795017306e-05, + "loss": 4.0302, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756067200266254e-05, + "loss": 4.0327, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755228605515202e-05, + "loss": 4.0274, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543932865248965e-05, + "loss": 4.025, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535546917738445e-05, + "loss": 4.04, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527160970227925e-05, + "loss": 4.0271, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518775022717405e-05, + "loss": 4.0274, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510389075206885e-05, + "loss": 4.026, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502019506500094e-05, + "loss": 4.0224, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.027204513549805, + "eval_runtime": 303.964, + "eval_samples_per_second": 1255.382, + "eval_steps_per_second": 39.232, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493633558989574e-05, + "loss": 4.0115, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485247611479054e-05, + "loss": 4.0217, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476861663968534e-05, + "loss": 4.032, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468475716458014e-05, + "loss": 4.0213, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460089768947494e-05, + "loss": 4.0255, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451703821436974e-05, + "loss": 4.0163, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443317873926453e-05, + "loss": 4.0214, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434931926415933e-05, + "loss": 4.0029, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426545978905413e-05, + "loss": 4.0278, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741816003139489e-05, + "loss": 4.0225, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740977408388437e-05, + "loss": 4.0199, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740140451517758e-05, + "loss": 4.0273, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739303494647079e-05, + "loss": 4.0059, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738464899896027e-05, + "loss": 4.0075, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737626305144975e-05, + "loss": 4.0141, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736787710393923e-05, + "loss": 3.998, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735949115642871e-05, + "loss": 4.0051, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735112158772193e-05, + "loss": 4.0006, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734273564021141e-05, + "loss": 3.9996, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733434969270089e-05, + "loss": 4.026, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732596374519037e-05, + "loss": 4.0046, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731757779767985e-05, + "loss": 4.0082, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730919185016933e-05, + "loss": 3.9973, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0145, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292436333952016e-05, + "loss": 3.9873, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284050386441496e-05, + "loss": 3.9943, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275664438930976e-05, + "loss": 3.9933, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267294870224185e-05, + "loss": 4.0017, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258908922713665e-05, + "loss": 3.9908, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725052297520315e-05, + "loss": 3.9908, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724213702769263e-05, + "loss": 3.9973, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723375108018211e-05, + "loss": 4.0005, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722536513267159e-05, + "loss": 3.9818, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721697918516107e-05, + "loss": 3.9961, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720859323765055e-05, + "loss": 3.9991, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720022366894376e-05, + "loss": 3.9947, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 3.9745, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718345177392272e-05, + "loss": 3.9842, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.71750658264122e-05, + "loss": 3.971, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716667987890168e-05, + "loss": 3.9886, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158293931391154e-05, + "loss": 3.9811, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714992436268437e-05, + "loss": 3.9887, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714153841517385e-05, + "loss": 3.9778, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 3.9827, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.987, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116396951446025e-05, + "loss": 3.9873, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108011003935505e-05, + "loss": 3.9844, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709962505642498e-05, + "loss": 3.9627, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709123910891446e-05, + "loss": 3.9782, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708285316140394e-05, + "loss": 3.9893, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074483592697154e-05, + "loss": 3.9735, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706609764518663e-05, + "loss": 3.9714, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705771169767611e-05, + "loss": 3.9695, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704932575016559e-05, + "loss": 3.9735, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040939802655074e-05, + "loss": 3.9591, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703257023394828e-05, + "loss": 3.9822, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702418428643776e-05, + "loss": 3.9716, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701579833892724e-05, + "loss": 3.977, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700741239141672e-05, + "loss": 3.9828, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9553, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.9699, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698227092768889e-05, + "loss": 3.964, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697388498017837e-05, + "loss": 3.9575, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9523, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.968, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694874351645054e-05, + "loss": 3.9632, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694035756894003e-05, + "loss": 3.9556, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.947, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9676, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9724, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9636, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9626, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.9729, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.9663, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.9706, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9496, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9671, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848144903931765e-05, + "loss": 3.9611, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9549, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.9569, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.9589, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681461749269342e-05, + "loss": 3.9697, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.68062315451829e-05, + "loss": 3.9609, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.9398, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9477, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678109008145507e-05, + "loss": 3.954, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677270413394455e-05, + "loss": 3.9576, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676431818643403e-05, + "loss": 3.9541, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9485, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9517, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.941, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9508, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.947, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671401888017464e-05, + "loss": 3.9491, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9578, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9509, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.9403, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668049146893629e-05, + "loss": 3.9473, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672121900229504e-05, + "loss": 3.9461, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663735952718984e-05, + "loss": 3.9502, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665535000520846e-05, + "loss": 3.9418, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664696405769794e-05, + "loss": 3.9387, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663857811018742e-05, + "loss": 3.9352, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301921626769e-05, + "loss": 3.9465, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9356, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661343664645959e-05, + "loss": 3.9235, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9368, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.9425, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658829518273176e-05, + "loss": 3.9314, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657990923522124e-05, + "loss": 3.9422, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657152328771072e-05, + "loss": 3.9277, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9433, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655476777149341e-05, + "loss": 3.9286, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654638182398289e-05, + "loss": 3.9319, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653799587647237e-05, + "loss": 3.9468, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652960992896185e-05, + "loss": 3.9419, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521240360255066e-05, + "loss": 3.9322, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512854412744546e-05, + "loss": 3.9341, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504468465234026e-05, + "loss": 3.9302, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496082517723506e-05, + "loss": 3.9365, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487712949016715e-05, + "loss": 3.9251, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479327001506195e-05, + "loss": 3.9393, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470941053995675e-05, + "loss": 3.9264, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462555106485155e-05, + "loss": 3.9387, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454185537778364e-05, + "loss": 3.9178, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445799590267844e-05, + "loss": 3.9266, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437413642757324e-05, + "loss": 3.9226, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429027695246804e-05, + "loss": 3.9267, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642064174773629e-05, + "loss": 3.9222, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.64122721790295e-05, + "loss": 3.9442, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640388623151898e-05, + "loss": 3.9297, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639550028400846e-05, + "loss": 3.9231, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638711433649794e-05, + "loss": 3.9163, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637874476779115e-05, + "loss": 3.9367, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9337, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636197287277011e-05, + "loss": 3.9284, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635358692525959e-05, + "loss": 3.9213, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.63452173565528e-05, + "loss": 3.9296, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633683140904228e-05, + "loss": 3.9319, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632844546153176e-05, + "loss": 3.9225, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320059514021244e-05, + "loss": 3.9198, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311673566510724e-05, + "loss": 3.9232, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303303997803934e-05, + "loss": 3.9211, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294918050293413e-05, + "loss": 3.9132, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286532102782893e-05, + "loss": 3.9266, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278146155272373e-05, + "loss": 3.9238, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626976020776185e-05, + "loss": 3.9165, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.9151, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625300469154454e-05, + "loss": 3.9115, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.952998399734497, + "eval_runtime": 307.7424, + "eval_samples_per_second": 1239.969, + "eval_steps_per_second": 38.75, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624461874403402e-05, + "loss": 3.9151, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.62362327965235e-05, + "loss": 3.9131, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622786322781671e-05, + "loss": 3.9267, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.62194772803062e-05, + "loss": 3.9136, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621109133279568e-05, + "loss": 3.9235, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620270538528516e-05, + "loss": 3.9102, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619433581657837e-05, + "loss": 3.9166, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618594986906785e-05, + "loss": 3.8991, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617756392155733e-05, + "loss": 3.9234, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616917797404681e-05, + "loss": 3.9169, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160808405340016e-05, + "loss": 3.9163, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152422457829496e-05, + "loss": 3.9226, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144036510318976e-05, + "loss": 3.9019, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135650562808456e-05, + "loss": 3.9065, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127280994101665e-05, + "loss": 3.9132, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611889504659115e-05, + "loss": 3.8999, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611050909908063e-05, + "loss": 3.9016, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610212315157011e-05, + "loss": 3.8999, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609375358286332e-05, + "loss": 3.9001, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.60853676353528e-05, + "loss": 3.9262, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607698168784228e-05, + "loss": 3.9043, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606859574033176e-05, + "loss": 3.9058, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606022617162497e-05, + "loss": 3.9001, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605184022411445e-05, + "loss": 3.9082, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604345427660393e-05, + "loss": 3.8927, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603506832909341e-05, + "loss": 3.8949, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602669876038662e-05, + "loss": 3.8961, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.60183128128761e-05, + "loss": 3.9044, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009926865365585e-05, + "loss": 3.8885, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001540917855065e-05, + "loss": 3.8949, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993171349148274e-05, + "loss": 3.8965, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984785401637754e-05, + "loss": 3.9059, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976399454127234e-05, + "loss": 3.894, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5968013506616714e-05, + "loss": 3.8962, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959643937909923e-05, + "loss": 3.9011, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951257990399403e-05, + "loss": 3.8992, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594287204288888e-05, + "loss": 3.8796, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593448609537836e-05, + "loss": 3.8904, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926100147867836e-05, + "loss": 3.8767, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591773057916105e-05, + "loss": 3.8939, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590934463165054e-05, + "loss": 3.8837, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590095868414001e-05, + "loss": 3.8963, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589257273662949e-05, + "loss": 3.8873, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588420316792271e-05, + "loss": 3.8855, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587581722041219e-05, + "loss": 3.896, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586743127290166e-05, + "loss": 3.8928, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585904532539114e-05, + "loss": 3.8918, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585067575668436e-05, + "loss": 3.8773, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584228980917384e-05, + "loss": 3.8826, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583390386166331e-05, + "loss": 3.8967, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582551791415279e-05, + "loss": 3.8837, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817148345446006e-05, + "loss": 3.878, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808762397935486e-05, + "loss": 3.8804, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800376450424966e-05, + "loss": 3.8846, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791990502914446e-05, + "loss": 3.8677, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578362093420766e-05, + "loss": 3.8877, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5775234986697135e-05, + "loss": 3.8826, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766849039186615e-05, + "loss": 3.8886, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758463091676095e-05, + "loss": 3.89, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750077144165575e-05, + "loss": 3.8713, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741707575458784e-05, + "loss": 3.8742, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733321627948264e-05, + "loss": 3.8807, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724935680437744e-05, + "loss": 3.8683, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571654973292723e-05, + "loss": 3.8663, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570818016422044e-05, + "loss": 3.8773, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569979421670992e-05, + "loss": 3.8786, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.56914082691994e-05, + "loss": 3.8678, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568302232168888e-05, + "loss": 3.8607, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567465275298209e-05, + "loss": 3.8778, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566626680547157e-05, + "loss": 3.8843, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565788085796105e-05, + "loss": 3.8743, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564949491045053e-05, + "loss": 3.8793, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564112534174374e-05, + "loss": 3.8849, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563273939423322e-05, + "loss": 3.8815, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.56243534467227e-05, + "loss": 3.8881, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615967499212184e-05, + "loss": 3.8629, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560759793050539e-05, + "loss": 3.8804, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559921198299487e-05, + "loss": 3.8789, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559082603548435e-05, + "loss": 3.8676, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558244008797383e-05, + "loss": 3.8788, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557407051926704e-05, + "loss": 3.8722, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556568457175652e-05, + "loss": 3.8834, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557298624246e-05, + "loss": 3.8788, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554891267673548e-05, + "loss": 3.8534, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554052672922496e-05, + "loss": 3.8655, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553215716051817e-05, + "loss": 3.8669, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552377121300765e-05, + "loss": 3.8731, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551538526549714e-05, + "loss": 3.873, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550699931798662e-05, + "loss": 3.8657, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549862974927983e-05, + "loss": 3.8689, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549024380176931e-05, + "loss": 3.8586, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548185785425879e-05, + "loss": 3.8676, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547347190674827e-05, + "loss": 3.8626, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5465102338041476e-05, + "loss": 3.8691, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456716390530956e-05, + "loss": 3.8787, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448330443020436e-05, + "loss": 3.8696, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439944495509916e-05, + "loss": 3.8602, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431574926803125e-05, + "loss": 3.8673, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423188979292605e-05, + "loss": 3.8637, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541480303178209e-05, + "loss": 3.8705, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540641708427157e-05, + "loss": 3.8636, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539804751556478e-05, + "loss": 3.861, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538966156805426e-05, + "loss": 3.852, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538127562054374e-05, + "loss": 3.8711, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537288967303322e-05, + "loss": 3.851, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536452010432643e-05, + "loss": 3.8485, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535613415681591e-05, + "loss": 3.8545, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534774820930539e-05, + "loss": 3.8614, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533936226179487e-05, + "loss": 3.8533, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533099269308808e-05, + "loss": 3.8693, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532260674557756e-05, + "loss": 3.8521, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314220798067045e-05, + "loss": 3.8559, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305834850556525e-05, + "loss": 3.8566, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297465281849734e-05, + "loss": 3.8482, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289079334339214e-05, + "loss": 3.8724, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280693386828694e-05, + "loss": 3.8626, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.52723238181219e-05, + "loss": 3.8567, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526393787061138e-05, + "loss": 3.8556, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525555192310086e-05, + "loss": 3.8485, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524716597559034e-05, + "loss": 3.8594, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523878002807982e-05, + "loss": 3.8481, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.52303940805693e-05, + "loss": 3.8653, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522200813305878e-05, + "loss": 3.8482, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521362218554826e-05, + "loss": 3.8584, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520525261684148e-05, + "loss": 3.8465, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519686666933096e-05, + "loss": 3.8509, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518848072182044e-05, + "loss": 3.8463, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518009477430992e-05, + "loss": 3.8522, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517172520560313e-05, + "loss": 3.8454, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516333925809261e-05, + "loss": 3.8684, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515495331058209e-05, + "loss": 3.8565, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514656736307156e-05, + "loss": 3.85, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513819779436478e-05, + "loss": 3.8375, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512981184685426e-05, + "loss": 3.8616, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512142589934374e-05, + "loss": 3.8573, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511303995183322e-05, + "loss": 3.8576, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510467038312643e-05, + "loss": 3.8463, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509628443561591e-05, + "loss": 3.852, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508789848810539e-05, + "loss": 3.8561, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079512540594866e-05, + "loss": 3.8537, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507114297188808e-05, + "loss": 3.844, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506275702437756e-05, + "loss": 3.8501, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054371076867035e-05, + "loss": 3.8462, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045985129356515e-05, + "loss": 3.8396, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503761556064973e-05, + "loss": 3.8513, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502922961313921e-05, + "loss": 3.8554, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020843665628684e-05, + "loss": 3.8425, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501245771811817e-05, + "loss": 3.8398, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500407177060765e-05, + "loss": 3.8463, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.911311626434326, + "eval_runtime": 340.6022, + "eval_samples_per_second": 1120.342, + "eval_steps_per_second": 35.012, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499568582309713e-05, + "loss": 3.8378, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498729987558661e-05, + "loss": 3.8425, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497891392807609e-05, + "loss": 3.8509, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497052798056557e-05, + "loss": 3.843, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496214203305505e-05, + "loss": 3.8552, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495375608554453e-05, + "loss": 3.8385, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494537013803401e-05, + "loss": 3.8432, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493698419052349e-05, + "loss": 3.828, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.49286146218167e-05, + "loss": 3.8554, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492022867430618e-05, + "loss": 3.8452, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491184272679566e-05, + "loss": 3.8405, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490345677928514e-05, + "loss": 3.8539, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895087210578355e-05, + "loss": 3.8296, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886701263067835e-05, + "loss": 3.8415, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878315315557315e-05, + "loss": 3.8419, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869945746850524e-05, + "loss": 3.8307, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861559799340004e-05, + "loss": 3.8307, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853173851829484e-05, + "loss": 3.8306, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844787904318964e-05, + "loss": 3.8342, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483641833561217e-05, + "loss": 3.8514, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482803238810165e-05, + "loss": 3.8352, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481964644059113e-05, + "loss": 3.8365, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481126049308061e-05, + "loss": 3.8332, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480289092437382e-05, + "loss": 3.8411, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479450497686331e-05, + "loss": 3.8248, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478611902935279e-05, + "loss": 3.8281, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477773308184227e-05, + "loss": 3.8253, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476936351313548e-05, + "loss": 3.836, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476097756562496e-05, + "loss": 3.8201, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475259161811444e-05, + "loss": 3.8291, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474420567060392e-05, + "loss": 3.8295, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735836101897126e-05, + "loss": 3.8381, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727450154386606e-05, + "loss": 3.8254, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4719064206876086e-05, + "loss": 3.8295, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710678259365566e-05, + "loss": 3.8317, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702308690658775e-05, + "loss": 3.8317, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469392274314826e-05, + "loss": 3.8179, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468553679563774e-05, + "loss": 3.8211, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467715084812722e-05, + "loss": 3.8104, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466878127942043e-05, + "loss": 3.8271, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466039533190991e-05, + "loss": 3.8194, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465200938439939e-05, + "loss": 3.8312, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464362343688887e-05, + "loss": 3.8208, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463525386818208e-05, + "loss": 3.8244, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462686792067156e-05, + "loss": 3.8292, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461848197316104e-05, + "loss": 3.8272, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461009602565052e-05, + "loss": 3.8283, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460172645694373e-05, + "loss": 3.8153, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593340509433216e-05, + "loss": 3.8101, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584954561922696e-05, + "loss": 3.8328, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457656861441217e-05, + "loss": 3.8182, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568215424509114e-05, + "loss": 3.813, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559829476998594e-05, + "loss": 3.8156, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551443529488074e-05, + "loss": 3.8221, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4543057581977554e-05, + "loss": 3.8034, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534671634467034e-05, + "loss": 3.8248, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526285686956514e-05, + "loss": 3.819, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517899739445994e-05, + "loss": 3.8223, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450951379193547e-05, + "loss": 3.8279, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450114422322868e-05, + "loss": 3.811, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449275827571816e-05, + "loss": 3.8089, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448437232820764e-05, + "loss": 3.8242, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447598638069712e-05, + "loss": 3.8009, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446761681199034e-05, + "loss": 3.8044, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445923086447982e-05, + "loss": 3.8175, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445084491696929e-05, + "loss": 3.8172, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444245896945877e-05, + "loss": 3.8031, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443408940075199e-05, + "loss": 3.8, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442570345324147e-05, + "loss": 3.8145, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441731750573094e-05, + "loss": 3.8193, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440893155822042e-05, + "loss": 3.8153, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400561989513636e-05, + "loss": 3.8137, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392176042003116e-05, + "loss": 3.8246, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383790094492596e-05, + "loss": 3.8177, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375404146982076e-05, + "loss": 3.8293, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436703457827529e-05, + "loss": 3.8017, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358648630764765e-05, + "loss": 3.8216, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350262683254245e-05, + "loss": 3.8154, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341876735743725e-05, + "loss": 3.8046, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333507167036934e-05, + "loss": 3.821, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325121219526414e-05, + "loss": 3.8105, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316735272015894e-05, + "loss": 3.8184, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308349324505374e-05, + "loss": 3.8209, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429997975579859e-05, + "loss": 3.7942, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429159380828807e-05, + "loss": 3.8069, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428320786077755e-05, + "loss": 3.8054, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427482191326703e-05, + "loss": 3.815, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426645234456024e-05, + "loss": 3.8115, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425806639704972e-05, + "loss": 3.8027, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.42496804495392e-05, + "loss": 3.8105, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424129450202868e-05, + "loss": 3.8024, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423292493332189e-05, + "loss": 3.8051, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422453898581137e-05, + "loss": 3.8039, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421615303830085e-05, + "loss": 3.8125, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420776709079033e-05, + "loss": 3.8186, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199397522083544e-05, + "loss": 3.809, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4191011574573024e-05, + "loss": 3.7996, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182625627062504e-05, + "loss": 3.8077, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174239679551984e-05, + "loss": 3.8065, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416587011084519e-05, + "loss": 3.8123, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415748416333467e-05, + "loss": 3.8073, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414909821582415e-05, + "loss": 3.8002, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414071226831363e-05, + "loss": 3.7946, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413234269960684e-05, + "loss": 3.8088, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412395675209632e-05, + "loss": 3.7938, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.41155708045858e-05, + "loss": 3.7946, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410718485707528e-05, + "loss": 3.792, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.40988152883685e-05, + "loss": 3.8062, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409042934085798e-05, + "loss": 3.7912, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408204339334746e-05, + "loss": 3.8143, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407365744583694e-05, + "loss": 3.7903, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065287877130146e-05, + "loss": 3.802, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056901929619626e-05, + "loss": 3.7994, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048515982109106e-05, + "loss": 3.7898, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040146413402315e-05, + "loss": 3.8129, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031760465891795e-05, + "loss": 3.8073, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023374518381275e-05, + "loss": 3.7988, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014988570870755e-05, + "loss": 3.7995, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400661900216397e-05, + "loss": 3.793, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399823305465345e-05, + "loss": 3.804, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398984710714293e-05, + "loss": 3.785, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398146115963241e-05, + "loss": 3.8099, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397309159092562e-05, + "loss": 3.7964, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.39647056434151e-05, + "loss": 3.7975, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395631969590458e-05, + "loss": 3.7928, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394793374839406e-05, + "loss": 3.7952, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393954780088354e-05, + "loss": 3.7879, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393117823217675e-05, + "loss": 3.7984, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392279228466623e-05, + "loss": 3.7915, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391440633715571e-05, + "loss": 3.8084, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390602038964519e-05, + "loss": 3.801, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897650820938405e-05, + "loss": 3.7971, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889264873427885e-05, + "loss": 3.7811, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880878925917365e-05, + "loss": 3.803, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872492978406845e-05, + "loss": 3.8018, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864123409700054e-05, + "loss": 3.8002, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855737462189534e-05, + "loss": 3.7921, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847351514679014e-05, + "loss": 3.7957, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383898194597222e-05, + "loss": 3.797, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.38305959984617e-05, + "loss": 3.8029, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382221005095118e-05, + "loss": 3.7885, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381382410344066e-05, + "loss": 3.7966, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380545453473388e-05, + "loss": 3.7885, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379706858722336e-05, + "loss": 3.7867, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378869901851657e-05, + "loss": 3.801, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378031307100605e-05, + "loss": 3.7933, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377192712349553e-05, + "loss": 3.7917, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376354117598501e-05, + "loss": 3.7858, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375515522847449e-05, + "loss": 3.7908, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8864755630493164, + "eval_runtime": 310.1007, + "eval_samples_per_second": 1230.539, + "eval_steps_per_second": 38.455, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374676928096397e-05, + "loss": 3.7881, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373838333345345e-05, + "loss": 3.7855, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372999738594293e-05, + "loss": 3.8005, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721627817236136e-05, + "loss": 3.7918, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3713241869725616e-05, + "loss": 3.7963, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704855922215096e-05, + "loss": 3.7888, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369648635350831e-05, + "loss": 3.7865, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368810040599779e-05, + "loss": 3.7763, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367971445848727e-05, + "loss": 3.7968, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367132851097675e-05, + "loss": 3.7964, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366295894226996e-05, + "loss": 3.7879, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365457299475944e-05, + "loss": 3.7992, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364620342605265e-05, + "loss": 3.7779, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363781747854213e-05, + "loss": 3.786, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362943153103161e-05, + "loss": 3.7918, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362104558352109e-05, + "loss": 3.7758, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361265963601057e-05, + "loss": 3.7804, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360427368850005e-05, + "loss": 3.7789, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359588774098953e-05, + "loss": 3.7804, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358750179347901e-05, + "loss": 3.7979, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3579132224772226e-05, + "loss": 3.7857, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570746277261706e-05, + "loss": 3.7872, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562360329751186e-05, + "loss": 3.7784, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553974382240665e-05, + "loss": 3.7902, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545604813533875e-05, + "loss": 3.7724, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537218866023355e-05, + "loss": 3.7768, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528832918512834e-05, + "loss": 3.7776, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520446971002314e-05, + "loss": 3.7825, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3512077402295524e-05, + "loss": 3.7683, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503691454785003e-05, + "loss": 3.7764, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495305507274483e-05, + "loss": 3.7825, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486919559763963e-05, + "loss": 3.7848, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347854999105718e-05, + "loss": 3.7779, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347016404354666e-05, + "loss": 3.7773, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346177809603614e-05, + "loss": 3.7825, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345340852732935e-05, + "loss": 3.7776, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344502257981883e-05, + "loss": 3.7696, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343663663230831e-05, + "loss": 3.7686, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342825068479779e-05, + "loss": 3.7616, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419881116091e-05, + "loss": 3.7756, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341149516858048e-05, + "loss": 3.771, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340310922106996e-05, + "loss": 3.7801, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339472327355944e-05, + "loss": 3.7712, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338635370485265e-05, + "loss": 3.772, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337796775734213e-05, + "loss": 3.7823, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336958180983161e-05, + "loss": 3.7729, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3361195862321086e-05, + "loss": 3.7785, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.33528262936143e-05, + "loss": 3.7634, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334444034610378e-05, + "loss": 3.7621, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333605439859326e-05, + "loss": 3.7854, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327668451082735e-05, + "loss": 3.7687, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331929888237595e-05, + "loss": 3.7658, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331092931366916e-05, + "loss": 3.765, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330254336615864e-05, + "loss": 3.7745, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329415741864813e-05, + "loss": 3.7537, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328577147113761e-05, + "loss": 3.7737, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277385523627087e-05, + "loss": 3.7708, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326899957611656e-05, + "loss": 3.7673, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326061362860604e-05, + "loss": 3.7828, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252244059899256e-05, + "loss": 3.7612, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243858112388736e-05, + "loss": 3.7631, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323547216487821e-05, + "loss": 3.7756, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322708621736769e-05, + "loss": 3.756, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218716648660905e-05, + "loss": 3.7564, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321033070115038e-05, + "loss": 3.7642, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201944753639864e-05, + "loss": 3.7687, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193558806129344e-05, + "loss": 3.7578, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318518923742256e-05, + "loss": 3.7526, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176803289912033e-05, + "loss": 3.762, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168417342401513e-05, + "loss": 3.7684, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3160031394890993e-05, + "loss": 3.769, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315166182618421e-05, + "loss": 3.7685, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314327587867368e-05, + "loss": 3.7733, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313488993116316e-05, + "loss": 3.7728, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312650398365264e-05, + "loss": 3.7832, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311813441494585e-05, + "loss": 3.7532, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310974846743533e-05, + "loss": 3.7768, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310136251992482e-05, + "loss": 3.7709, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.30929765724143e-05, + "loss": 3.7508, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308460700370751e-05, + "loss": 3.7766, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307622105619699e-05, + "loss": 3.761, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306783510868647e-05, + "loss": 3.7718, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3059465539979676e-05, + "loss": 3.7743, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3051079592469156e-05, + "loss": 3.7493, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042693644958636e-05, + "loss": 3.7555, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034307697448116e-05, + "loss": 3.7576, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025921749937596e-05, + "loss": 3.7683, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017535802427076e-05, + "loss": 3.7625, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3009149854916556e-05, + "loss": 3.7593, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000763907406036e-05, + "loss": 3.7576, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299239433869925e-05, + "loss": 3.7609, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298400839118873e-05, + "loss": 3.7587, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297562244367821e-05, + "loss": 3.756, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296725287497142e-05, + "loss": 3.7688, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.29588669274609e-05, + "loss": 3.7679, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295048097995038e-05, + "loss": 3.7694, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294209503243986e-05, + "loss": 3.7497, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293372546373307e-05, + "loss": 3.7617, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292533951622255e-05, + "loss": 3.7573, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291695356871203e-05, + "loss": 3.765, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290856762120151e-05, + "loss": 3.7625, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900198052494725e-05, + "loss": 3.7561, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891812104984205e-05, + "loss": 3.7479, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883426157473685e-05, + "loss": 3.7625, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2875040209963165e-05, + "loss": 3.7524, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866670641256374e-05, + "loss": 3.7473, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858284693745854e-05, + "loss": 3.7435, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849915125039063e-05, + "loss": 3.7586, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841529177528543e-05, + "loss": 3.7524, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833143230018023e-05, + "loss": 3.7668, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.28247572825075e-05, + "loss": 3.7484, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281637133499698e-05, + "loss": 3.7559, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280798538748646e-05, + "loss": 3.7567, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279959943997594e-05, + "loss": 3.7455, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279121349246542e-05, + "loss": 3.7686, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278284392375864e-05, + "loss": 3.7622, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277447435505185e-05, + "loss": 3.7552, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276608840754133e-05, + "loss": 3.755, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275770246003081e-05, + "loss": 3.7498, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274931651252029e-05, + "loss": 3.7602, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274093056500977e-05, + "loss": 3.7379, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273254461749925e-05, + "loss": 3.7658, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272415866998873e-05, + "loss": 3.7477, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271577272247821e-05, + "loss": 3.7503, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270740315377142e-05, + "loss": 3.7515, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.26990172062609e-05, + "loss": 3.7485, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269064763755411e-05, + "loss": 3.7484, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268226169004359e-05, + "loss": 3.7523, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267387574253307e-05, + "loss": 3.7492, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266548979502255e-05, + "loss": 3.7625, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265710384751203e-05, + "loss": 3.754, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264871790000151e-05, + "loss": 3.7576, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640331952490986e-05, + "loss": 3.7351, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631946004980466e-05, + "loss": 3.7628, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262357643627368e-05, + "loss": 3.7553, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261519048876316e-05, + "loss": 3.757, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606804541252635e-05, + "loss": 3.7485, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598418593742115e-05, + "loss": 3.7509, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.259004902503533e-05, + "loss": 3.7586, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258166307752481e-05, + "loss": 3.7608, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257327713001429e-05, + "loss": 3.7441, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256489118250377e-05, + "loss": 3.7503, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2556521613796986e-05, + "loss": 3.7493, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254813566628646e-05, + "loss": 3.7431, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539766097579675e-05, + "loss": 3.7584, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.2531380150069155e-05, + "loss": 3.749, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522994202558635e-05, + "loss": 3.7528, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251460825504811e-05, + "loss": 3.738, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250622230753759e-05, + "loss": 3.7515, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8699309825897217, + "eval_runtime": 305.6067, + "eval_samples_per_second": 1248.634, + "eval_steps_per_second": 39.021, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249783636002707e-05, + "loss": 3.7461, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248945041251655e-05, + "loss": 3.7398, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2481064465006035e-05, + "loss": 3.7561, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472678517495515e-05, + "loss": 3.752, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464292569984995e-05, + "loss": 3.7516, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455923001278204e-05, + "loss": 3.7462, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447537053767684e-05, + "loss": 3.7392, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2439151106257164e-05, + "loss": 3.7401, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430765158746644e-05, + "loss": 3.7493, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422379211236124e-05, + "loss": 3.7565, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413993263725604e-05, + "loss": 3.7447, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405607316215084e-05, + "loss": 3.7578, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239723774750829e-05, + "loss": 3.7396, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238885179999777e-05, + "loss": 3.74, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238046585248725e-05, + "loss": 3.7514, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237207990497673e-05, + "loss": 3.7336, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236369395746622e-05, + "loss": 3.7381, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235532438875943e-05, + "loss": 3.737, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234693844124891e-05, + "loss": 3.7404, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233855249373839e-05, + "loss": 3.7507, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233016654622787e-05, + "loss": 3.7465, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232178059871735e-05, + "loss": 3.7477, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231339465120682e-05, + "loss": 3.7357, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.23050087036963e-05, + "loss": 3.7494, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229662275618578e-05, + "loss": 3.7335, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288253187479e-05, + "loss": 3.7357, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227986723996847e-05, + "loss": 3.732, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227148129245796e-05, + "loss": 3.739, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226309534494744e-05, + "loss": 3.7342, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254725776240646e-05, + "loss": 3.7319, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246339828730126e-05, + "loss": 3.7415, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237953881219606e-05, + "loss": 3.7427, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222958431251282e-05, + "loss": 3.7347, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221198365002295e-05, + "loss": 3.7407, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212812417491775e-05, + "loss": 3.7391, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220444284878499e-05, + "loss": 3.7374, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219605690127447e-05, + "loss": 3.7356, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187670953763944e-05, + "loss": 3.7237, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179285006253424e-05, + "loss": 3.7206, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217089905874291e-05, + "loss": 3.7335, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216251311123239e-05, + "loss": 3.7327, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215412716372187e-05, + "loss": 3.7382, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214574121621135e-05, + "loss": 3.7322, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213737164750456e-05, + "loss": 3.732, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212898569999404e-05, + "loss": 3.7416, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212059975248352e-05, + "loss": 3.7336, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112213804973e-05, + "loss": 3.7407, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210384423626621e-05, + "loss": 3.7236, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209545828875569e-05, + "loss": 3.7174, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208707234124517e-05, + "loss": 3.7471, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207870277253838e-05, + "loss": 3.732, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070316825027865e-05, + "loss": 3.7252, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061947256321074e-05, + "loss": 3.7295, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053561308810554e-05, + "loss": 3.731, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045175361300034e-05, + "loss": 3.7179, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036789413789514e-05, + "loss": 3.7286, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028403466278993e-05, + "loss": 3.7326, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2020017518768473e-05, + "loss": 3.7312, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011631571257953e-05, + "loss": 3.7424, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200326200255116e-05, + "loss": 3.7214, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199487605504064e-05, + "loss": 3.7237, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198649010753012e-05, + "loss": 3.7402, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.19781041600196e-05, + "loss": 3.7169, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196973459131281e-05, + "loss": 3.715, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19613486438023e-05, + "loss": 3.7271, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195296269629178e-05, + "loss": 3.7282, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194457674878126e-05, + "loss": 3.7168, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936223558878196e-05, + "loss": 3.7174, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927837611367676e-05, + "loss": 3.7164, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919451663857156e-05, + "loss": 3.7355, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1911065716346636e-05, + "loss": 3.7272, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902679768836116e-05, + "loss": 3.7301, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894293821325596e-05, + "loss": 3.7334, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885924252618805e-05, + "loss": 3.7315, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877538305108285e-05, + "loss": 3.7445, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1869152357597765e-05, + "loss": 3.7168, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186076641008725e-05, + "loss": 3.736, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185238046257673e-05, + "loss": 3.7307, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184401089386994e-05, + "loss": 3.7154, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183562494635942e-05, + "loss": 3.7358, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.18272389988489e-05, + "loss": 3.7256, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181885305133838e-05, + "loss": 3.7334, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181048348263159e-05, + "loss": 3.7357, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180209753512107e-05, + "loss": 3.7162, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179371158761055e-05, + "loss": 3.7121, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178532564010003e-05, + "loss": 3.7192, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177693969258951e-05, + "loss": 3.7318, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176855374507899e-05, + "loss": 3.724, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176016779756847e-05, + "loss": 3.7226, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175178185005795e-05, + "loss": 3.7225, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743412281351165e-05, + "loss": 3.721, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1735042712644375e-05, + "loss": 3.7229, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726656765133854e-05, + "loss": 3.7191, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718270817623334e-05, + "loss": 3.7308, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709884870112814e-05, + "loss": 3.7296, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701498922602294e-05, + "loss": 3.7301, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693112975091774e-05, + "loss": 3.7122, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168472702758125e-05, + "loss": 3.725, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167634108007073e-05, + "loss": 3.7243, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166798789016767e-05, + "loss": 3.7259, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165960194265716e-05, + "loss": 3.7264, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165121599514664e-05, + "loss": 3.7155, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164283004763612e-05, + "loss": 3.7158, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.16344441001256e-05, + "loss": 3.7218, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162605815261508e-05, + "loss": 3.7119, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161767220510455e-05, + "loss": 3.7196, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160928625759403e-05, + "loss": 3.7014, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160093306769098e-05, + "loss": 3.7252, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159254712018046e-05, + "loss": 3.7152, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158416117266994e-05, + "loss": 3.7252, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157577522515942e-05, + "loss": 3.7128, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15673892776489e-05, + "loss": 3.7212, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155900333013838e-05, + "loss": 3.7226, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155061738262786e-05, + "loss": 3.7048, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154223143511734e-05, + "loss": 3.7325, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153386186641055e-05, + "loss": 3.7234, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.1525475918900026e-05, + "loss": 3.7185, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1517089971389506e-05, + "loss": 3.7227, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508704023878986e-05, + "loss": 3.706, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500318076368466e-05, + "loss": 3.726, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491948507661675e-05, + "loss": 3.7049, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483562560151155e-05, + "loss": 3.7272, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475176612640635e-05, + "loss": 3.7085, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466790665130115e-05, + "loss": 3.7164, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458404717619595e-05, + "loss": 3.7122, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.145001877010908e-05, + "loss": 3.7155, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144164920140229e-05, + "loss": 3.7142, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143326325389177e-05, + "loss": 3.712, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142487730638125e-05, + "loss": 3.7147, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141649135887073e-05, + "loss": 3.7259, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140810541136021e-05, + "loss": 3.7139, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139971946384969e-05, + "loss": 3.7232, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139133351633917e-05, + "loss": 3.7007, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138294756882865e-05, + "loss": 3.7248, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137457800012186e-05, + "loss": 3.7254, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136619205261134e-05, + "loss": 3.718, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135780610510082e-05, + "loss": 3.7125, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.13494201575903e-05, + "loss": 3.7186, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1341050588883515e-05, + "loss": 3.7179, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332664641372995e-05, + "loss": 3.7274, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324278693862475e-05, + "loss": 3.7067, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315892746351955e-05, + "loss": 3.717, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307523177645164e-05, + "loss": 3.7113, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299137230134644e-05, + "loss": 3.7087, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129076766142785e-05, + "loss": 3.7197, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128238171391733e-05, + "loss": 3.7148, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127399576640681e-05, + "loss": 3.718, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126560981889629e-05, + "loss": 3.7038, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125722387138577e-05, + "loss": 3.7215, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8596904277801514, + "eval_runtime": 304.7292, + "eval_samples_per_second": 1252.23, + "eval_steps_per_second": 39.133, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124883792387525e-05, + "loss": 3.7073, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124046835516847e-05, + "loss": 3.7055, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123208240765795e-05, + "loss": 3.718, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122369646014743e-05, + "loss": 3.7176, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121531051263691e-05, + "loss": 3.7163, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120694094393012e-05, + "loss": 3.7136, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.11985549964196e-05, + "loss": 3.703, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119016904890908e-05, + "loss": 3.7034, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118178310139856e-05, + "loss": 3.7166, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117339715388803e-05, + "loss": 3.7211, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116501120637751e-05, + "loss": 3.7092, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115662525886699e-05, + "loss": 3.7205, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148255690160207e-05, + "loss": 3.7093, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139869742649686e-05, + "loss": 3.7048, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131483795139166e-05, + "loss": 3.7133, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123097847628646e-05, + "loss": 3.6965, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114711900118126e-05, + "loss": 3.7041, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1106342331411335e-05, + "loss": 3.7029, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097956383900815e-05, + "loss": 3.7069, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1089570436390295e-05, + "loss": 3.7135, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081184488879775e-05, + "loss": 3.7155, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072798541369255e-05, + "loss": 3.7106, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064412593858735e-05, + "loss": 3.7019, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1056043025151944e-05, + "loss": 3.7135, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047657077641424e-05, + "loss": 3.6965, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039271130130904e-05, + "loss": 3.7061, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103088518262039e-05, + "loss": 3.6963, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102249923510987e-05, + "loss": 3.7082, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101411328759935e-05, + "loss": 3.6967, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100572734008883e-05, + "loss": 3.7009, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099734139257831e-05, + "loss": 3.7047, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098897182387152e-05, + "loss": 3.7133, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980585876361e-05, + "loss": 3.702, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097219992885048e-05, + "loss": 3.7004, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096381398133996e-05, + "loss": 3.7045, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095544441263317e-05, + "loss": 3.7035, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094705846512265e-05, + "loss": 3.7038, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093867251761213e-05, + "loss": 3.6853, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093028657010161e-05, + "loss": 3.6897, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092190062259109e-05, + "loss": 3.6963, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913514675080575e-05, + "loss": 3.7038, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090512872757005e-05, + "loss": 3.7028, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089674278005953e-05, + "loss": 3.6977, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888373211352744e-05, + "loss": 3.6974, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087998726384222e-05, + "loss": 3.7082, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.08716013163317e-05, + "loss": 3.6959, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086321536882118e-05, + "loss": 3.7156, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085484580011439e-05, + "loss": 3.6883, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.0846459852603867e-05, + "loss": 3.6784, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0838073905093346e-05, + "loss": 3.7173, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829687957582826e-05, + "loss": 3.6959, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082131838887604e-05, + "loss": 3.699, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081294882016926e-05, + "loss": 3.6948, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080456287265874e-05, + "loss": 3.6954, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079617692514822e-05, + "loss": 3.6876, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078779097763769e-05, + "loss": 3.6962, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077940503012717e-05, + "loss": 3.6985, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077101908261665e-05, + "loss": 3.6969, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076263313510613e-05, + "loss": 3.7104, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075426356639934e-05, + "loss": 3.6876, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074587761888882e-05, + "loss": 3.6876, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.07374916713783e-05, + "loss": 3.7104, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072910572386778e-05, + "loss": 3.6819, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720736155160996e-05, + "loss": 3.6823, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0712350207650476e-05, + "loss": 3.6938, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0703964260139956e-05, + "loss": 3.6956, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695578312629436e-05, + "loss": 3.6808, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0687208743922645e-05, + "loss": 3.6882, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678822796412125e-05, + "loss": 3.6842, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670436848901605e-05, + "loss": 3.7002, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0662050901391085e-05, + "loss": 3.699, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653664953880565e-05, + "loss": 3.692, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645279006370045e-05, + "loss": 3.6998, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636893058859525e-05, + "loss": 3.6993, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628523490152734e-05, + "loss": 3.7148, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620137542642214e-05, + "loss": 3.6818, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.06117515951317e-05, + "loss": 3.7099, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060336564762118e-05, + "loss": 3.6947, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059497970011066e-05, + "loss": 3.6859, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058659375260014e-05, + "loss": 3.7011, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057820780508962e-05, + "loss": 3.6965, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.05698218575791e-05, + "loss": 3.6997, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056145228887231e-05, + "loss": 3.7058, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055306634136179e-05, + "loss": 3.6816, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054468039385127e-05, + "loss": 3.6787, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053629444634075e-05, + "loss": 3.6893, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052790849883023e-05, + "loss": 3.6999, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.05195225513197e-05, + "loss": 3.6945, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051113660380918e-05, + "loss": 3.6891, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050275065629867e-05, + "loss": 3.6846, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049438108759188e-05, + "loss": 3.6913, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048599514008136e-05, + "loss": 3.6902, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0477625571374574e-05, + "loss": 3.6905, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469239623864054e-05, + "loss": 3.6971, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046085367635353e-05, + "loss": 3.7006, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045246772884301e-05, + "loss": 3.6967, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044409816013622e-05, + "loss": 3.6836, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.04357122126257e-05, + "loss": 3.6964, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427326265115176e-05, + "loss": 3.6881, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418940317604656e-05, + "loss": 3.6934, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410554370094136e-05, + "loss": 3.6954, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040216842258362e-05, + "loss": 3.6882, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.03937824750731e-05, + "loss": 3.6796, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038539652756258e-05, + "loss": 3.6871, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037702695885579e-05, + "loss": 3.6874, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036864101134527e-05, + "loss": 3.6845, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036025506383475e-05, + "loss": 3.6718, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035188549512796e-05, + "loss": 3.6937, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034349954761744e-05, + "loss": 3.6889, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033511360010692e-05, + "loss": 3.691, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.03267276525964e-05, + "loss": 3.6791, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031834170508588e-05, + "loss": 3.6959, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030995575757536e-05, + "loss": 3.6869, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030156981006484e-05, + "loss": 3.6758, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029318386255432e-05, + "loss": 3.6982, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.6924, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276428346337016e-05, + "loss": 3.6861, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268042398826496e-05, + "loss": 3.6936, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259656451315976e-05, + "loss": 3.6768, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251270503805456e-05, + "loss": 3.6956, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242900935098665e-05, + "loss": 3.6773, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234514987588145e-05, + "loss": 3.6926, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226129040077625e-05, + "loss": 3.6786, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217743092567105e-05, + "loss": 3.6869, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209357145056585e-05, + "loss": 3.6823, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200987576349794e-05, + "loss": 3.6833, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192601628839274e-05, + "loss": 3.6805, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184215681328754e-05, + "loss": 3.6828, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017582973381824e-05, + "loss": 3.6895, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167443786307714e-05, + "loss": 3.6964, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159057838797194e-05, + "loss": 3.6786, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150671891286674e-05, + "loss": 3.6973, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014230232257989e-05, + "loss": 3.6698, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013391637506936e-05, + "loss": 3.6931, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012553042755884e-05, + "loss": 3.6927, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011716085885206e-05, + "loss": 3.6881, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010877491134154e-05, + "loss": 3.6805, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010038896383101e-05, + "loss": 3.688, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009200301632049e-05, + "loss": 3.6891, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008361706880998e-05, + "loss": 3.6987, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007523112129946e-05, + "loss": 3.6767, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006684517378894e-05, + "loss": 3.6859, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005845922627842e-05, + "loss": 3.681, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005008965757163e-05, + "loss": 3.684, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041720088864837e-05, + "loss": 3.6822, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033334141354317e-05, + "loss": 3.6828, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024948193843797e-05, + "loss": 3.6903, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016562246333276e-05, + "loss": 3.6707, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008176298822756e-05, + "loss": 3.6897, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.85237717628479, + "eval_runtime": 304.5845, + "eval_samples_per_second": 1252.825, + "eval_steps_per_second": 39.152, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999790351312236e-05, + "loss": 3.6806, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991404403801716e-05, + "loss": 3.6794, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983018456291196e-05, + "loss": 3.6842, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974632508780676e-05, + "loss": 3.6864, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996624656127016e-05, + "loss": 3.6882, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995787699256337e-05, + "loss": 3.6797, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994949104505285e-05, + "loss": 3.6785, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994110509754233e-05, + "loss": 3.6773, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993271915003181e-05, + "loss": 3.6823, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992433320252129e-05, + "loss": 3.6913, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.99159636338145e-05, + "loss": 3.6819, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990757768630398e-05, + "loss": 3.6895, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989919173879346e-05, + "loss": 3.6766, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989080579128294e-05, + "loss": 3.6766, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988241984377242e-05, + "loss": 3.6851, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987405027506563e-05, + "loss": 3.6691, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986566432755512e-05, + "loss": 3.6741, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857278380044597e-05, + "loss": 3.6728, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848892432534077e-05, + "loss": 3.6771, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984050648502355e-05, + "loss": 3.6822, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983212053751303e-05, + "loss": 3.6897, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823750968806246e-05, + "loss": 3.6802, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815365021295726e-05, + "loss": 3.6742, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.98069790737852e-05, + "loss": 3.6811, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979859312627468e-05, + "loss": 3.6722, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979020717876416e-05, + "loss": 3.6772, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978182123125364e-05, + "loss": 3.6653, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977343528374312e-05, + "loss": 3.6781, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97650493362326e-05, + "loss": 3.6724, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756679767525814e-05, + "loss": 3.666, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748293820015294e-05, + "loss": 3.6717, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739924251308503e-05, + "loss": 3.686, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973153830379798e-05, + "loss": 3.6716, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972315235628746e-05, + "loss": 3.6735, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971476640877694e-05, + "loss": 3.6751, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970638046126642e-05, + "loss": 3.6797, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.96979945137559e-05, + "loss": 3.6723, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968960856624538e-05, + "loss": 3.6591, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968122261873486e-05, + "loss": 3.6631, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967286942883181e-05, + "loss": 3.6677, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966448348132129e-05, + "loss": 3.6732, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965609753381077e-05, + "loss": 3.6722, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964771158630025e-05, + "loss": 3.672, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963932563878973e-05, + "loss": 3.67, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963095607008294e-05, + "loss": 3.6781, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962257012257242e-05, + "loss": 3.6674, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.96141841750619e-05, + "loss": 3.6828, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960579822755138e-05, + "loss": 3.6641, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959741228004086e-05, + "loss": 3.6483, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958902633253034e-05, + "loss": 3.6882, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580656763823546e-05, + "loss": 3.6658, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572270816313026e-05, + "loss": 3.671, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9563884868802506e-05, + "loss": 3.6652, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555498921291986e-05, + "loss": 3.6658, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954711297378147e-05, + "loss": 3.658, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953872702627095e-05, + "loss": 3.6653, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953034107876043e-05, + "loss": 3.6739, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952195513124991e-05, + "loss": 3.6718, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951358556254312e-05, + "loss": 3.6833, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.95051996150326e-05, + "loss": 3.6608, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949681366752208e-05, + "loss": 3.6594, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948842772001156e-05, + "loss": 3.6841, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948005815130477e-05, + "loss": 3.6517, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947167220379425e-05, + "loss": 3.6538, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946328625628373e-05, + "loss": 3.6647, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945490030877321e-05, + "loss": 3.6669, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944651436126269e-05, + "loss": 3.6554, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943812841375217e-05, + "loss": 3.6604, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429758845045386e-05, + "loss": 3.6559, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942137289753486e-05, + "loss": 3.6729, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941298695002434e-05, + "loss": 3.6687, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940460100251382e-05, + "loss": 3.6689, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939623143380703e-05, + "loss": 3.6723, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938784548629651e-05, + "loss": 3.671, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937945953878599e-05, + "loss": 3.6847, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937107359127547e-05, + "loss": 3.6576, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936268764376495e-05, + "loss": 3.6795, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935430169625443e-05, + "loss": 3.6612, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345932127547644e-05, + "loss": 3.6592, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337546180037124e-05, + "loss": 3.674, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329160232526604e-05, + "loss": 3.6709, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320774285016084e-05, + "loss": 3.6701, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931240471630929e-05, + "loss": 3.6804, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930401876879877e-05, + "loss": 3.6527, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929563282128825e-05, + "loss": 3.6473, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928724687377773e-05, + "loss": 3.6629, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927886092626721e-05, + "loss": 3.6727, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927047497875669e-05, + "loss": 3.6675, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621054100499e-05, + "loss": 3.6626, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925371946253938e-05, + "loss": 3.656, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924533351502886e-05, + "loss": 3.6616, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923694756751835e-05, + "loss": 3.6658, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922856162000783e-05, + "loss": 3.6606, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922017567249731e-05, + "loss": 3.6674, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921178972498679e-05, + "loss": 3.6716, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920342015628e-05, + "loss": 3.6705, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919503420876948e-05, + "loss": 3.6578, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918664826125896e-05, + "loss": 3.6647, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917826231374844e-05, + "loss": 3.6624, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169892745041646e-05, + "loss": 3.6646, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161506797531126e-05, + "loss": 3.6689, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153120850020606e-05, + "loss": 3.6626, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144734902510086e-05, + "loss": 3.6571, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136348954999566e-05, + "loss": 3.653, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912797938629278e-05, + "loss": 3.6652, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911959343878226e-05, + "loss": 3.6562, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911120749127174e-05, + "loss": 3.6431, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910282154376122e-05, + "loss": 3.667, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909445197505443e-05, + "loss": 3.6613, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908606602754391e-05, + "loss": 3.6631, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907768008003339e-05, + "loss": 3.6482, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069294132522864e-05, + "loss": 3.6653, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060908185012344e-05, + "loss": 3.6605, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905253861630556e-05, + "loss": 3.6491, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904415266879504e-05, + "loss": 3.6735, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903576672128452e-05, + "loss": 3.667, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027380773774e-05, + "loss": 3.6595, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901899482626348e-05, + "loss": 3.6649, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010625257556696e-05, + "loss": 3.6492, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900223931004617e-05, + "loss": 3.6667, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899385336253565e-05, + "loss": 3.6541, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898546741502513e-05, + "loss": 3.6623, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897709784631834e-05, + "loss": 3.6519, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896871189880782e-05, + "loss": 3.6616, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.89603259512973e-05, + "loss": 3.6561, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895194000378678e-05, + "loss": 3.6558, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943570435079994e-05, + "loss": 3.653, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935184487569473e-05, + "loss": 3.6603, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926798540058953e-05, + "loss": 3.6569, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891841259254843e-05, + "loss": 3.6677, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891002664503791e-05, + "loss": 3.6537, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890164069752739e-05, + "loss": 3.6726, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889325475001687e-05, + "loss": 3.6427, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888486880250635e-05, + "loss": 3.6646, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887649923379956e-05, + "loss": 3.6661, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886811328628904e-05, + "loss": 3.6635, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885972733877852e-05, + "loss": 3.6531, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851341391268e-05, + "loss": 3.66, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884295544375748e-05, + "loss": 3.6581, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883456949624696e-05, + "loss": 3.6777, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882618354873644e-05, + "loss": 3.6506, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881781398002966e-05, + "loss": 3.6563, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880942803251914e-05, + "loss": 3.6518, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880104208500862e-05, + "loss": 3.6621, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.87926561374981e-05, + "loss": 3.6505, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878427018998758e-05, + "loss": 3.6617, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877588424247705e-05, + "loss": 3.6624, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876751467377027e-05, + "loss": 3.6515, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875912872625975e-05, + "loss": 3.6601, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.848733425140381, + "eval_runtime": 305.8739, + "eval_samples_per_second": 1247.544, + "eval_steps_per_second": 38.987, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875074277874923e-05, + "loss": 3.6485, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.87423568312387e-05, + "loss": 3.6489, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873397088372818e-05, + "loss": 3.6602, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872558493621766e-05, + "loss": 3.6597, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871719898870714e-05, + "loss": 3.6637, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708829420000356e-05, + "loss": 3.6556, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8700443472489836e-05, + "loss": 3.6512, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8692057524979316e-05, + "loss": 3.6535, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683671577468795e-05, + "loss": 3.6507, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675285629958275e-05, + "loss": 3.6669, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8666899682447755e-05, + "loss": 3.6588, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8658513734937235e-05, + "loss": 3.6597, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8650144166230444e-05, + "loss": 3.6607, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641758218719924e-05, + "loss": 3.6422, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633372271209404e-05, + "loss": 3.6594, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624986323698884e-05, + "loss": 3.6453, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616616754992093e-05, + "loss": 3.6474, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860823080748158e-05, + "loss": 3.6497, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859984485997106e-05, + "loss": 3.6462, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859145891246054e-05, + "loss": 3.6542, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858307296495002e-05, + "loss": 3.6649, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857470339624323e-05, + "loss": 3.6585, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856631744873271e-05, + "loss": 3.6486, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855793150122219e-05, + "loss": 3.6513, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854954555371167e-05, + "loss": 3.6461, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854115960620115e-05, + "loss": 3.6514, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853277365869063e-05, + "loss": 3.6408, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852438771118011e-05, + "loss": 3.6588, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851600176366959e-05, + "loss": 3.6421, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507648573766534e-05, + "loss": 3.6448, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499262626256014e-05, + "loss": 3.6427, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8490876678745494e-05, + "loss": 3.66, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482490731234974e-05, + "loss": 3.6494, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474104783724454e-05, + "loss": 3.6471, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846573521501766e-05, + "loss": 3.6498, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845734926750714e-05, + "loss": 3.6505, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844896331999662e-05, + "loss": 3.6511, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.84405773724861e-05, + "loss": 3.6359, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843219142497558e-05, + "loss": 3.6356, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842382185626879e-05, + "loss": 3.6427, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841543590875827e-05, + "loss": 3.6437, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840704996124775e-05, + "loss": 3.6466, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839866401373723e-05, + "loss": 3.6466, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839027806622671e-05, + "loss": 3.6501, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838190849751993e-05, + "loss": 3.6455, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837352255000941e-05, + "loss": 3.647, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836513660249889e-05, + "loss": 3.655, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835675065498836e-05, + "loss": 3.641, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834836470747784e-05, + "loss": 3.6245, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339995138771056e-05, + "loss": 3.6585, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331609191260536e-05, + "loss": 3.6397, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832322324375001e-05, + "loss": 3.6488, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831483729623949e-05, + "loss": 3.6459, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306467727532705e-05, + "loss": 3.6383, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298081780022185e-05, + "loss": 3.6331, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289695832511665e-05, + "loss": 3.6391, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281309885001145e-05, + "loss": 3.6507, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8272923937490625e-05, + "loss": 3.6426, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8264537989980105e-05, + "loss": 3.6559, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8256152042469585e-05, + "loss": 3.6414, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247766094959065e-05, + "loss": 3.6298, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.8239396526252274e-05, + "loss": 3.6591, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8231010578741754e-05, + "loss": 3.6303, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.8222624631231234e-05, + "loss": 3.6278, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8214238683720714e-05, + "loss": 3.6422, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820586911501392e-05, + "loss": 3.6396, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.81974831675034e-05, + "loss": 3.6325, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818909721999289e-05, + "loss": 3.6337, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818071127248237e-05, + "loss": 3.632, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817232532497185e-05, + "loss": 3.6472, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816393937746133e-05, + "loss": 3.6463, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815556980875454e-05, + "loss": 3.6417, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814718386124402e-05, + "loss": 3.6482, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.81387979137335e-05, + "loss": 3.6444, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813041196622298e-05, + "loss": 3.658, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812202601871246e-05, + "loss": 3.634, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811364007120194e-05, + "loss": 3.6557, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810525412369142e-05, + "loss": 3.6354, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809688455498463e-05, + "loss": 3.6372, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808849860747411e-05, + "loss": 3.6448, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808011265996359e-05, + "loss": 3.6457, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071726712453074e-05, + "loss": 3.6487, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806335714374628e-05, + "loss": 3.6549, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805497119623576e-05, + "loss": 3.6272, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804658524872524e-05, + "loss": 3.6269, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803819930121472e-05, + "loss": 3.6378, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802982973250793e-05, + "loss": 3.6471, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802144378499741e-05, + "loss": 3.6392, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801305783748689e-05, + "loss": 3.636, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800467188997637e-05, + "loss": 3.6369, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996285942465845e-05, + "loss": 3.6406, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798791637375906e-05, + "loss": 3.6369, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797953042624854e-05, + "loss": 3.6363, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797114447873802e-05, + "loss": 3.6448, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.79627585312275e-05, + "loss": 3.647, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795437258371698e-05, + "loss": 3.6494, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794598663620646e-05, + "loss": 3.6345, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793760068869594e-05, + "loss": 3.6396, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792923111998915e-05, + "loss": 3.6379, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792084517247863e-05, + "loss": 3.639, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791245922496811e-05, + "loss": 3.6447, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790407327745759e-05, + "loss": 3.6389, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789568732994707e-05, + "loss": 3.6312, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788731776124028e-05, + "loss": 3.6274, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7878931813729766e-05, + "loss": 3.6439, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870545866219246e-05, + "loss": 3.6319, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7862159918708725e-05, + "loss": 3.6185, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853773971198205e-05, + "loss": 3.6401, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845404402491415e-05, + "loss": 3.6467, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7837018454980894e-05, + "loss": 3.6343, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7828632507470374e-05, + "loss": 3.6284, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7820246559959854e-05, + "loss": 3.637, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811860612449334e-05, + "loss": 3.6366, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7803474664938814e-05, + "loss": 3.6247, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795088717428294e-05, + "loss": 3.6503, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.77867191487215e-05, + "loss": 3.6457, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777833320121098e-05, + "loss": 3.6339, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776994725370046e-05, + "loss": 3.6393, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776156130618994e-05, + "loss": 3.6286, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775317535867943e-05, + "loss": 3.6414, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774480578997264e-05, + "loss": 3.6305, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773641984246212e-05, + "loss": 3.637, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.77280338949516e-05, + "loss": 3.6297, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771964794744108e-05, + "loss": 3.6386, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771127837873429e-05, + "loss": 3.6335, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770289243122377e-05, + "loss": 3.6331, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769450648371325e-05, + "loss": 3.6284, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768612053620273e-05, + "loss": 3.6358, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767773458869221e-05, + "loss": 3.6318, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766936501998542e-05, + "loss": 3.6442, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.76609790724749e-05, + "loss": 3.6329, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652593124964384e-05, + "loss": 3.6461, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764420717745386e-05, + "loss": 3.619, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763582122994334e-05, + "loss": 3.6446, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762743528243282e-05, + "loss": 3.6397, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761906571372603e-05, + "loss": 3.6396, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610679766215506e-05, + "loss": 3.6325, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602293818704986e-05, + "loss": 3.635, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593907871194466e-05, + "loss": 3.6341, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585521923683946e-05, + "loss": 3.656, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577135976173426e-05, + "loss": 3.6231, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568766407466635e-05, + "loss": 3.637, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756038045995612e-05, + "loss": 3.6316, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.75519945124456e-05, + "loss": 3.6361, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754360856493508e-05, + "loss": 3.6261, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753523899622829e-05, + "loss": 3.6394, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752685304871777e-05, + "loss": 3.636, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751846710120725e-05, + "loss": 3.635, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751008115369673e-05, + "loss": 3.6335, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8447084426879883, + "eval_runtime": 305.1431, + "eval_samples_per_second": 1250.531, + "eval_steps_per_second": 39.08, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750171158498994e-05, + "loss": 3.6297, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749332563747942e-05, + "loss": 3.626, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.74849396899689e-05, + "loss": 3.6354, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747655374245838e-05, + "loss": 3.641, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746816779494786e-05, + "loss": 3.6393, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459798226241075e-05, + "loss": 3.6321, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451412278730555e-05, + "loss": 3.6278, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7443026331220035e-05, + "loss": 3.6289, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7434640383709515e-05, + "loss": 3.6284, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7426254436198995e-05, + "loss": 3.6438, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417868488688475e-05, + "loss": 3.6333, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409482541177955e-05, + "loss": 3.6366, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401112972471164e-05, + "loss": 3.6406, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392727024960644e-05, + "loss": 3.6168, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384341077450124e-05, + "loss": 3.6395, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7375955129939604e-05, + "loss": 3.6166, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736758556123281e-05, + "loss": 3.6259, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735919961372229e-05, + "loss": 3.6264, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735081366621177e-05, + "loss": 3.624, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734242771870125e-05, + "loss": 3.6326, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733404177119074e-05, + "loss": 3.6395, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732567220248395e-05, + "loss": 3.6374, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731728625497343e-05, + "loss": 3.626, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730890030746291e-05, + "loss": 3.625, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730051435995239e-05, + "loss": 3.6295, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729212841244187e-05, + "loss": 3.6245, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728374246493134e-05, + "loss": 3.6192, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727535651742082e-05, + "loss": 3.6338, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.72669705699103e-05, + "loss": 3.6164, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258617380007246e-05, + "loss": 3.6235, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250231432496726e-05, + "loss": 3.6169, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7241845484986206e-05, + "loss": 3.6346, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723345953747569e-05, + "loss": 3.6302, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7225073589965166e-05, + "loss": 3.6201, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721670402125838e-05, + "loss": 3.6294, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720831807374786e-05, + "loss": 3.6216, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719993212623734e-05, + "loss": 3.6312, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191546178726815e-05, + "loss": 3.6192, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183160231216295e-05, + "loss": 3.6102, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717479066250951e-05, + "loss": 3.617, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166404714998984e-05, + "loss": 3.6261, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158018767488464e-05, + "loss": 3.6208, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149632819977944e-05, + "loss": 3.6225, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714124687246743e-05, + "loss": 3.628, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713287730376064e-05, + "loss": 3.6232, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712449135625012e-05, + "loss": 3.6269, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.71161054087396e-05, + "loss": 3.6376, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710771946122908e-05, + "loss": 3.6176, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709933351371856e-05, + "loss": 3.6002, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709096394501177e-05, + "loss": 3.6349, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708257799750125e-05, + "loss": 3.6179, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707419204999073e-05, + "loss": 3.6259, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706580610248021e-05, + "loss": 3.6205, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705742015496969e-05, + "loss": 3.6183, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704903420745917e-05, + "loss": 3.6109, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704064825994865e-05, + "loss": 3.6141, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703226231243813e-05, + "loss": 3.6328, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7023892743731345e-05, + "loss": 3.6175, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015506796220824e-05, + "loss": 3.6358, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7007120848710304e-05, + "loss": 3.6187, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998734901199784e-05, + "loss": 3.6061, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990365332492993e-05, + "loss": 3.6338, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981979384982473e-05, + "loss": 3.6174, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697359343747195e-05, + "loss": 3.6022, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696520748996143e-05, + "loss": 3.6192, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695683792125464e-05, + "loss": 3.6174, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694845197374412e-05, + "loss": 3.6098, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.69400660262336e-05, + "loss": 3.6123, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693168007872308e-05, + "loss": 3.6099, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692329413121257e-05, + "loss": 3.6249, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691492456250578e-05, + "loss": 3.628, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690653861499526e-05, + "loss": 3.616, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689815266748474e-05, + "loss": 3.6278, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688976671997422e-05, + "loss": 3.6211, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.68813807724637e-05, + "loss": 3.6357, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687301120375691e-05, + "loss": 3.6137, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686462525624639e-05, + "loss": 3.6354, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685623930873587e-05, + "loss": 3.6139, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684785336122535e-05, + "loss": 3.6117, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683946741371482e-05, + "loss": 3.6252, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831097845008036e-05, + "loss": 3.6207, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682271189749752e-05, + "loss": 3.6258, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814325949987e-05, + "loss": 3.6334, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6805940002476476e-05, + "loss": 3.6083, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797554054965956e-05, + "loss": 3.605, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789168107455436e-05, + "loss": 3.614, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780798538748645e-05, + "loss": 3.6295, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772412591238125e-05, + "loss": 3.6133, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764026643727605e-05, + "loss": 3.6145, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755640696217085e-05, + "loss": 3.6194, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747254748706565e-05, + "loss": 3.6112, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738868801196045e-05, + "loss": 3.6201, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673049923248926e-05, + "loss": 3.614, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672211328497874e-05, + "loss": 3.6217, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671372733746822e-05, + "loss": 3.6219, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.67053413899577e-05, + "loss": 3.6305, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669695544244718e-05, + "loss": 3.6111, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668856949493666e-05, + "loss": 3.6206, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668019992622987e-05, + "loss": 3.6155, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667181397871935e-05, + "loss": 3.6189, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666342803120883e-05, + "loss": 3.6246, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665504208369831e-05, + "loss": 3.613, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664665613618779e-05, + "loss": 3.6154, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638286567481e-05, + "loss": 3.6084, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662990061997048e-05, + "loss": 3.6168, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662151467245996e-05, + "loss": 3.6137, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661312872494944e-05, + "loss": 3.5959, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604742777438925e-05, + "loss": 3.6204, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596373208732134e-05, + "loss": 3.621, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6587987261221614e-05, + "loss": 3.6124, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579601313711094e-05, + "loss": 3.6084, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571215366200574e-05, + "loss": 3.6137, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562829418690054e-05, + "loss": 3.6173, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655445984998326e-05, + "loss": 3.6031, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654607390247274e-05, + "loss": 3.6309, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653768795496222e-05, + "loss": 3.621, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.65293020074517e-05, + "loss": 3.6115, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652091605994118e-05, + "loss": 3.6189, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651254649123439e-05, + "loss": 3.6067, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650416054372388e-05, + "loss": 3.6187, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649577459621336e-05, + "loss": 3.6137, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648738864870284e-05, + "loss": 3.6094, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647901907999605e-05, + "loss": 3.6115, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647063313248553e-05, + "loss": 3.6161, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646224718497501e-05, + "loss": 3.6148, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645386123746448e-05, + "loss": 3.6103, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445491668757697e-05, + "loss": 3.6116, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437105721247176e-05, + "loss": 3.6105, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428719773736656e-05, + "loss": 3.612, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642033382622613e-05, + "loss": 3.6256, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6411947878715616e-05, + "loss": 3.6128, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640357831000883e-05, + "loss": 3.6224, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395192362498305e-05, + "loss": 3.5943, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386806414987785e-05, + "loss": 3.6268, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6378420467477265e-05, + "loss": 3.6178, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6370034519966745e-05, + "loss": 3.6182, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6361648572456225e-05, + "loss": 3.6123, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6353279003749434e-05, + "loss": 3.6107, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344893056238914e-05, + "loss": 3.6143, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336507108728394e-05, + "loss": 3.6325, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328121161217874e-05, + "loss": 3.6034, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631975159251108e-05, + "loss": 3.6158, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631136564500057e-05, + "loss": 3.6082, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630297969749005e-05, + "loss": 3.6123, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629461012878326e-05, + "loss": 3.6084, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628622418127274e-05, + "loss": 3.6148, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627783823376222e-05, + "loss": 3.6138, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.62694522862517e-05, + "loss": 3.6165, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626106633874118e-05, + "loss": 3.6117, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8431999683380127, + "eval_runtime": 306.7877, + "eval_samples_per_second": 1243.828, + "eval_steps_per_second": 38.871, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625268039123066e-05, + "loss": 3.6061, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624429444372014e-05, + "loss": 3.6048, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623590849620962e-05, + "loss": 3.6154, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622753892750283e-05, + "loss": 3.6177, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621915297999231e-05, + "loss": 3.6197, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621076703248179e-05, + "loss": 3.6093, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620238108497127e-05, + "loss": 3.6078, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6193995137460754e-05, + "loss": 3.6129, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185625568753964e-05, + "loss": 3.6059, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177239621243443e-05, + "loss": 3.6204, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6168853673732923e-05, + "loss": 3.6143, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160467726222403e-05, + "loss": 3.6199, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615209815751561e-05, + "loss": 3.6163, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614371221000509e-05, + "loss": 3.5976, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613532626249457e-05, + "loss": 3.6191, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612694031498405e-05, + "loss": 3.5956, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611857074627726e-05, + "loss": 3.6077, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611018479876674e-05, + "loss": 3.6057, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610179885125622e-05, + "loss": 3.5999, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609341290374571e-05, + "loss": 3.6107, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608502695623519e-05, + "loss": 3.6208, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.60766573875284e-05, + "loss": 3.6126, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606827144001788e-05, + "loss": 3.6115, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605988549250736e-05, + "loss": 3.6077, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605149954499684e-05, + "loss": 3.6054, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604311359748632e-05, + "loss": 3.6045, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034744028779526e-05, + "loss": 3.5969, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026358081269006e-05, + "loss": 3.6115, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6017972133758486e-05, + "loss": 3.5986, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009586186247966e-05, + "loss": 3.6027, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001216617541175e-05, + "loss": 3.5978, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992830670030655e-05, + "loss": 3.6151, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598444472252014e-05, + "loss": 3.6035, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5976058775009615e-05, + "loss": 3.6064, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596768920630283e-05, + "loss": 3.608, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595930325879231e-05, + "loss": 3.6031, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595091731128179e-05, + "loss": 3.6125, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942531363771264e-05, + "loss": 3.5948, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593416179506448e-05, + "loss": 3.593, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592577584755396e-05, + "loss": 3.5964, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591738990004344e-05, + "loss": 3.6041, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590900395253291e-05, + "loss": 3.599, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590061800502239e-05, + "loss": 3.6032, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589224843631561e-05, + "loss": 3.6045, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588386248880509e-05, + "loss": 3.6027, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587547654129457e-05, + "loss": 3.6047, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586709059378405e-05, + "loss": 3.6117, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858721025077264e-05, + "loss": 3.6019, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585033507756674e-05, + "loss": 3.5819, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584194913005622e-05, + "loss": 3.6164, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.58335631825457e-05, + "loss": 3.6011, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582517723503518e-05, + "loss": 3.6033, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5816807666328387e-05, + "loss": 3.5992, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808421718817867e-05, + "loss": 3.5983, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800035771307346e-05, + "loss": 3.5912, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579164982379683e-05, + "loss": 3.5915, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578328025509004e-05, + "loss": 3.6153, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577489430757952e-05, + "loss": 3.5965, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766508360069e-05, + "loss": 3.6168, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575812241255848e-05, + "loss": 3.5968, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574973646504796e-05, + "loss": 3.5837, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574136689634117e-05, + "loss": 3.6145, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573298094883065e-05, + "loss": 3.5965, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572459500132013e-05, + "loss": 3.5851, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571620905380961e-05, + "loss": 3.5988, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570783948510282e-05, + "loss": 3.5948, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.56994535375923e-05, + "loss": 3.5874, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569106759008179e-05, + "loss": 3.5967, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568268164257127e-05, + "loss": 3.5914, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567429569506075e-05, + "loss": 3.6018, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5665926126353956e-05, + "loss": 3.6078, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657540178843436e-05, + "loss": 3.5983, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649154231332916e-05, + "loss": 3.6054, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640768283822396e-05, + "loss": 3.6011, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632398715115605e-05, + "loss": 3.6166, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624012767605085e-05, + "loss": 3.5964, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615626820094565e-05, + "loss": 3.6142, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607240872584045e-05, + "loss": 3.594, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598854925073525e-05, + "loss": 3.5933, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559048535636674e-05, + "loss": 3.6014, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558209940885622e-05, + "loss": 3.6015, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.55737134613457e-05, + "loss": 3.6059, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556532751383518e-05, + "loss": 3.6142, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555694156632466e-05, + "loss": 3.5911, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554857199761787e-05, + "loss": 3.5824, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554018605010735e-05, + "loss": 3.5913, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553180010259683e-05, + "loss": 3.6122, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552341415508631e-05, + "loss": 3.5912, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551504458637952e-05, + "loss": 3.5994, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5506658638869e-05, + "loss": 3.5997, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549827269135848e-05, + "loss": 3.5899, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548988674384796e-05, + "loss": 3.5966, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548150079633744e-05, + "loss": 3.596, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473131227630654e-05, + "loss": 3.5983, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464745280120134e-05, + "loss": 3.6054, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456359332609614e-05, + "loss": 3.6076, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5447973385099094e-05, + "loss": 3.5935, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.54396038163923e-05, + "loss": 3.5999, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543121786888178e-05, + "loss": 3.594, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542283192137126e-05, + "loss": 3.5992, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541444597386074e-05, + "loss": 3.6024, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540607640515395e-05, + "loss": 3.5928, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539769045764343e-05, + "loss": 3.5956, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538930451013291e-05, + "loss": 3.5881, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538091856262239e-05, + "loss": 3.6003, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537254899391561e-05, + "loss": 3.5944, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536416304640509e-05, + "loss": 3.5774, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535577709889457e-05, + "loss": 3.5983, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534739115138405e-05, + "loss": 3.601, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533900520387352e-05, + "loss": 3.5934, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533063563516674e-05, + "loss": 3.5888, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532224968765622e-05, + "loss": 3.5933, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531386374014569e-05, + "loss": 3.597, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530547779263517e-05, + "loss": 3.5837, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529709184512465e-05, + "loss": 3.6061, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5288722276417866e-05, + "loss": 3.6009, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280336328907346e-05, + "loss": 3.5957, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5271950381396826e-05, + "loss": 3.6008, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5263564433886305e-05, + "loss": 3.5906, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525519486517952e-05, + "loss": 3.5976, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5246808917668995e-05, + "loss": 3.596, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238422970158474e-05, + "loss": 3.5912, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230037022647954e-05, + "loss": 3.592, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5221667453941164e-05, + "loss": 3.5929, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213281506430643e-05, + "loss": 3.5944, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5204895558920123e-05, + "loss": 3.591, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196509611409603e-05, + "loss": 3.5885, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518812366389908e-05, + "loss": 3.593, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.51797540951923e-05, + "loss": 3.5898, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517136814768178e-05, + "loss": 3.6075, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516298220017126e-05, + "loss": 3.5919, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515459625266074e-05, + "loss": 3.6062, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514622668395395e-05, + "loss": 3.5747, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513784073644343e-05, + "loss": 3.6083, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512945478893291e-05, + "loss": 3.5946, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512106884142239e-05, + "loss": 3.6039, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511268289391187e-05, + "loss": 3.5929, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510431332520508e-05, + "loss": 3.5861, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509592737769456e-05, + "loss": 3.5985, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508754143018404e-05, + "loss": 3.6163, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507915548267352e-05, + "loss": 3.58, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507078591396673e-05, + "loss": 3.5974, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506239996645621e-05, + "loss": 3.5911, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505401401894569e-05, + "loss": 3.5941, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504562807143517e-05, + "loss": 3.5906, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503724212392465e-05, + "loss": 3.5954, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502887255521786e-05, + "loss": 3.5892, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502048660770734e-05, + "loss": 3.5949, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501210066019682e-05, + "loss": 3.5921, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8430161476135254, + "eval_runtime": 306.7347, + "eval_samples_per_second": 1244.043, + "eval_steps_per_second": 38.877, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.50037147126863e-05, + "loss": 3.6009, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499532876517578e-05, + "loss": 3.5837, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498694281766526e-05, + "loss": 3.5962, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497855687015474e-05, + "loss": 3.6019, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497017092264422e-05, + "loss": 3.5961, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496180135393744e-05, + "loss": 3.5917, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495341540642692e-05, + "loss": 3.5945, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.49450294589164e-05, + "loss": 3.5914, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493664351140588e-05, + "loss": 3.5855, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492825756389535e-05, + "loss": 3.5966, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4919887995188566e-05, + "loss": 3.601, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911502047678046e-05, + "loss": 3.5987, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903132478971255e-05, + "loss": 3.6022, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894746531460735e-05, + "loss": 3.5775, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886360583950215e-05, + "loss": 3.5997, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4877974636439695e-05, + "loss": 3.5759, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869588688929175e-05, + "loss": 3.5917, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861202741418655e-05, + "loss": 3.5846, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4852816793908135e-05, + "loss": 3.5822, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4844430846397615e-05, + "loss": 3.5908, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4836044898887095e-05, + "loss": 3.6024, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4827675330180304e-05, + "loss": 3.5935, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819289382669784e-05, + "loss": 3.5913, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4810903435159264e-05, + "loss": 3.5877, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4802517487648744e-05, + "loss": 3.5902, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479414791894195e-05, + "loss": 3.5864, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478576197143143e-05, + "loss": 3.5757, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477737602392091e-05, + "loss": 3.5943, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476899007641039e-05, + "loss": 3.58, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476062050770361e-05, + "loss": 3.5839, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475223456019309e-05, + "loss": 3.583, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474384861268257e-05, + "loss": 3.5926, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473546266517205e-05, + "loss": 3.5811, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472709309646526e-05, + "loss": 3.587, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471870714895474e-05, + "loss": 3.5872, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471032120144422e-05, + "loss": 3.5859, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.47019352539337e-05, + "loss": 3.5953, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469354930642318e-05, + "loss": 3.5722, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468517973771639e-05, + "loss": 3.5766, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4676793790205867e-05, + "loss": 3.5792, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668407842695347e-05, + "loss": 3.5835, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466002189518483e-05, + "loss": 3.5793, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465165232647804e-05, + "loss": 3.5863, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464326637896752e-05, + "loss": 3.5889, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4634880431457e-05, + "loss": 3.5832, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462649448394648e-05, + "loss": 3.583, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461810853643596e-05, + "loss": 3.5961, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460972258892544e-05, + "loss": 3.5801, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460133664141492e-05, + "loss": 3.5648, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.45929506939044e-05, + "loss": 3.5964, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458459750400134e-05, + "loss": 3.5842, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457621155649082e-05, + "loss": 3.5822, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.45678256089803e-05, + "loss": 3.5823, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455943966146978e-05, + "loss": 3.5785, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455105371395927e-05, + "loss": 3.5738, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454266776644875e-05, + "loss": 3.5737, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534298197741956e-05, + "loss": 3.5962, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4525912250231436e-05, + "loss": 3.5782, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517526302720916e-05, + "loss": 3.5985, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509140355210396e-05, + "loss": 3.5808, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4500754407699876e-05, + "loss": 3.562, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4492384838993085e-05, + "loss": 3.593, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4483998891482565e-05, + "loss": 3.5774, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475612943972045e-05, + "loss": 3.5686, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467226996461525e-05, + "loss": 3.5752, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458841048951005e-05, + "loss": 3.5793, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445047148024422e-05, + "loss": 3.5712, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.44420855327337e-05, + "loss": 3.5803, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443369958522318e-05, + "loss": 3.5697, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442531363771266e-05, + "loss": 3.5844, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416927690202134e-05, + "loss": 3.5881, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440855812149535e-05, + "loss": 3.5777, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440017217398483e-05, + "loss": 3.5884, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439178622647431e-05, + "loss": 3.5828, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438340027896378e-05, + "loss": 3.5978, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437501433145326e-05, + "loss": 3.5795, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436662838394274e-05, + "loss": 3.5917, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435825881523596e-05, + "loss": 3.5792, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434987286772544e-05, + "loss": 3.5742, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434148692021492e-05, + "loss": 3.5871, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.43331009727044e-05, + "loss": 3.5781, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432473140399761e-05, + "loss": 3.5888, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431634545648709e-05, + "loss": 3.5961, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430795950897657e-05, + "loss": 3.5767, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429957356146605e-05, + "loss": 3.5597, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291203992759256e-05, + "loss": 3.5738, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282818045248736e-05, + "loss": 3.5893, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274432097738216e-05, + "loss": 3.5757, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266046150227696e-05, + "loss": 3.5776, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4257660202717176e-05, + "loss": 3.5842, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424929063401039e-05, + "loss": 3.5705, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424090468649987e-05, + "loss": 3.5824, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423251873898935e-05, + "loss": 3.5761, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422413279147883e-05, + "loss": 3.5849, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421574684396831e-05, + "loss": 3.5857, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420737727526152e-05, + "loss": 3.5901, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4198991327751e-05, + "loss": 3.571, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419060538024048e-05, + "loss": 3.5808, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418221943272996e-05, + "loss": 3.581, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417383348521944e-05, + "loss": 3.5791, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416544753770892e-05, + "loss": 3.5857, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.41570615901984e-05, + "loss": 3.575, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414869202149161e-05, + "loss": 3.5752, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140306073981096e-05, + "loss": 3.5734, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4131920126470576e-05, + "loss": 3.5802, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123534178960056e-05, + "loss": 3.5759, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115164610253265e-05, + "loss": 3.5616, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4106778662742745e-05, + "loss": 3.5794, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098392715232225e-05, + "loss": 3.5862, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090006767721705e-05, + "loss": 3.5711, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4081620820211185e-05, + "loss": 3.5754, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073234872700665e-05, + "loss": 3.5719, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4064865303993874e-05, + "loss": 3.5813, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056479356483354e-05, + "loss": 3.5709, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048093408972834e-05, + "loss": 3.5823, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4039707461462314e-05, + "loss": 3.5786, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031321513951794e-05, + "loss": 3.5836, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4022935566441274e-05, + "loss": 3.5799, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401456599773449e-05, + "loss": 3.5729, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400618005022397e-05, + "loss": 3.5785, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399779410271344e-05, + "loss": 3.5776, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398940815520292e-05, + "loss": 3.5758, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398103858649614e-05, + "loss": 3.5754, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397265263898561e-05, + "loss": 3.5722, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396426669147509e-05, + "loss": 3.5778, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395588074396457e-05, + "loss": 3.5729, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394749479645405e-05, + "loss": 3.5726, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393912522774727e-05, + "loss": 3.5702, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393073928023675e-05, + "loss": 3.5733, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392235333272623e-05, + "loss": 3.5883, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391396738521571e-05, + "loss": 3.5726, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390559781650892e-05, + "loss": 3.591, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.38972118689984e-05, + "loss": 3.5606, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388882592148788e-05, + "loss": 3.5839, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388043997397736e-05, + "loss": 3.5804, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387205402646684e-05, + "loss": 3.5837, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386366807895632e-05, + "loss": 3.5763, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855298510249526e-05, + "loss": 3.5702, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3846912562739006e-05, + "loss": 3.5784, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838526615228486e-05, + "loss": 3.5941, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830140667717966e-05, + "loss": 3.5662, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382177109901118e-05, + "loss": 3.5769, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381338515150066e-05, + "loss": 3.5754, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380499920399014e-05, + "loss": 3.5734, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379661325647962e-05, + "loss": 3.5746, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.37882273089691e-05, + "loss": 3.5779, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377985774026231e-05, + "loss": 3.5717, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377147179275179e-05, + "loss": 3.5792, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376308584524127e-05, + "loss": 3.5737, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.842865228652954, + "eval_runtime": 302.734, + "eval_samples_per_second": 1260.483, + "eval_steps_per_second": 39.391, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375469989773075e-05, + "loss": 3.5726, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374633032902396e-05, + "loss": 3.5645, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373794438151344e-05, + "loss": 3.5779, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372955843400292e-05, + "loss": 3.5865, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721172486492406e-05, + "loss": 3.5755, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3712802917785615e-05, + "loss": 3.5761, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704416970275095e-05, + "loss": 3.5746, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696031022764575e-05, + "loss": 3.5763, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3687645075254055e-05, + "loss": 3.5644, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679275506547264e-05, + "loss": 3.5834, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3670889559036744e-05, + "loss": 3.5839, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662503611526224e-05, + "loss": 3.5787, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365413404281943e-05, + "loss": 3.5864, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364574809530891e-05, + "loss": 3.5579, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363736214779839e-05, + "loss": 3.5756, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362897620028787e-05, + "loss": 3.5625, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362059025277736e-05, + "loss": 3.576, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361220430526684e-05, + "loss": 3.567, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360381835775632e-05, + "loss": 3.5626, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.35954324102458e-05, + "loss": 3.5657, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358704646273528e-05, + "loss": 3.5892, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357867689402849e-05, + "loss": 3.5775, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357029094651797e-05, + "loss": 3.5722, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356190499900745e-05, + "loss": 3.5706, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355351905149692e-05, + "loss": 3.5768, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354514948279014e-05, + "loss": 3.5658, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353676353527962e-05, + "loss": 3.5598, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.35283775877691e-05, + "loss": 3.5754, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351999164025858e-05, + "loss": 3.5644, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351162207155179e-05, + "loss": 3.5632, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350323612404127e-05, + "loss": 3.5667, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349485017653075e-05, + "loss": 3.5724, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486464229020226e-05, + "loss": 3.5684, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3478078281509706e-05, + "loss": 3.5699, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3469692333999186e-05, + "loss": 3.5675, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461306386488666e-05, + "loss": 3.5746, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3452920438978146e-05, + "loss": 3.5774, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444550870271355e-05, + "loss": 3.552, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343618130156457e-05, + "loss": 3.5608, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342779535405405e-05, + "loss": 3.5619, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341940940654353e-05, + "loss": 3.564, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341102345903301e-05, + "loss": 3.5641, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340265389032623e-05, + "loss": 3.5717, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.33942679428157e-05, + "loss": 3.5671, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338588199530518e-05, + "loss": 3.5677, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337749604779466e-05, + "loss": 3.5682, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336912647908787e-05, + "loss": 3.5745, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336074053157735e-05, + "loss": 3.5664, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335235458406683e-05, + "loss": 3.5458, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334396863655631e-05, + "loss": 3.576, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333559906784952e-05, + "loss": 3.5662, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3327213120339005e-05, + "loss": 3.5671, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3318827172828485e-05, + "loss": 3.5637, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3310441225317965e-05, + "loss": 3.5618, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302055277807445e-05, + "loss": 3.5576, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3293685709100654e-05, + "loss": 3.5572, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285299761590134e-05, + "loss": 3.5778, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3276913814079614e-05, + "loss": 3.5587, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3268527866569094e-05, + "loss": 3.581, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.32601582978623e-05, + "loss": 3.5703, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325177235035178e-05, + "loss": 3.5453, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324338640284126e-05, + "loss": 3.5742, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323500045533074e-05, + "loss": 3.5584, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322663088662396e-05, + "loss": 3.5529, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321824493911344e-05, + "loss": 3.556, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320985899160292e-05, + "loss": 3.5616, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.32014730440924e-05, + "loss": 3.559, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319308709658188e-05, + "loss": 3.56, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318471752787509e-05, + "loss": 3.5501, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317633158036457e-05, + "loss": 3.5688, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316794563285405e-05, + "loss": 3.5717, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315955968534353e-05, + "loss": 3.5639, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3151190116636736e-05, + "loss": 3.5675, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3142804169126216e-05, + "loss": 3.5665, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3134418221615696e-05, + "loss": 3.5787, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126032274105176e-05, + "loss": 3.5612, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311766270539839e-05, + "loss": 3.5722, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310927675788787e-05, + "loss": 3.568, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310089081037735e-05, + "loss": 3.5589, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309250486286683e-05, + "loss": 3.5677, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308413529416004e-05, + "loss": 3.5611, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307574934664952e-05, + "loss": 3.5727, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067363399139e-05, + "loss": 3.5799, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305897745162848e-05, + "loss": 3.5614, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305060788292169e-05, + "loss": 3.5436, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304222193541117e-05, + "loss": 3.5555, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303383598790065e-05, + "loss": 3.5691, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302545004039013e-05, + "loss": 3.5629, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301706409287961e-05, + "loss": 3.5599, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3008694524172826e-05, + "loss": 3.5659, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000308576662306e-05, + "loss": 3.5588, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2991922629151786e-05, + "loss": 3.559, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2983536681641266e-05, + "loss": 3.5618, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975167112934475e-05, + "loss": 3.5657, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2966781165423955e-05, + "loss": 3.5692, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2958395217913435e-05, + "loss": 3.5753, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2950009270402915e-05, + "loss": 3.5531, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2941623322892394e-05, + "loss": 3.5634, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2933253754185604e-05, + "loss": 3.5657, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2924867806675084e-05, + "loss": 3.5592, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916481859164563e-05, + "loss": 3.5707, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908095911654043e-05, + "loss": 3.559, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289970996414353e-05, + "loss": 3.5562, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289134039543674e-05, + "loss": 3.5558, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288295444792622e-05, + "loss": 3.5644, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.28745685004157e-05, + "loss": 3.5572, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286618255290518e-05, + "loss": 3.5416, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285781298419839e-05, + "loss": 3.5628, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284942703668787e-05, + "loss": 3.5677, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284104108917735e-05, + "loss": 3.5561, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283265514166683e-05, + "loss": 3.5556, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.28242691941563e-05, + "loss": 3.5549, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281588324664578e-05, + "loss": 3.563, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2807513677939e-05, + "loss": 3.5552, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279912773042848e-05, + "loss": 3.562, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279074178291796e-05, + "loss": 3.5689, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278235583540744e-05, + "loss": 3.5668, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277396988789692e-05, + "loss": 3.5616, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2765600319190126e-05, + "loss": 3.558, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757214371679606e-05, + "loss": 3.5594, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2748828424169086e-05, + "loss": 3.5598, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740442476658566e-05, + "loss": 3.5578, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732072907951775e-05, + "loss": 3.5607, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2723686960441255e-05, + "loss": 3.5554, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715301012930735e-05, + "loss": 3.5613, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270691506542022e-05, + "loss": 3.5534, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.26985291179097e-05, + "loss": 3.5579, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269014317039918e-05, + "loss": 3.5514, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268177360169239e-05, + "loss": 3.5576, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267338765418187e-05, + "loss": 3.572, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266500170667135e-05, + "loss": 3.5579, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265661575916083e-05, + "loss": 3.5736, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264824619045404e-05, + "loss": 3.5414, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263986024294352e-05, + "loss": 3.5667, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2631474295433e-05, + "loss": 3.5679, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262308834792248e-05, + "loss": 3.5638, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261471877921569e-05, + "loss": 3.5597, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2606332831705175e-05, + "loss": 3.5491, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2597946884194655e-05, + "loss": 3.5671, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2589560936684135e-05, + "loss": 3.5755, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581191367977344e-05, + "loss": 3.5521, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2572805420466824e-05, + "loss": 3.5549, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2564419472956304e-05, + "loss": 3.5627, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556033525445784e-05, + "loss": 3.5582, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254766395673899e-05, + "loss": 3.5553, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253927800922847e-05, + "loss": 3.5625, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253089206171795e-05, + "loss": 3.5532, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252250611420743e-05, + "loss": 3.5678, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251413654550064e-05, + "loss": 3.5535, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.84291672706604, + "eval_runtime": 307.2272, + "eval_samples_per_second": 1242.048, + "eval_steps_per_second": 38.815, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250575059799012e-05, + "loss": 3.564, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249736465047961e-05, + "loss": 3.55, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248897870296909e-05, + "loss": 3.5605, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248059275545857e-05, + "loss": 3.5707, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247220680794805e-05, + "loss": 3.5621, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246383723924126e-05, + "loss": 3.5577, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245545129173074e-05, + "loss": 3.5556, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244706534422022e-05, + "loss": 3.5589, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.24386793967097e-05, + "loss": 3.5467, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243029344919918e-05, + "loss": 3.5709, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242192388049239e-05, + "loss": 3.5651, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241353793298187e-05, + "loss": 3.5634, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240515198547135e-05, + "loss": 3.5706, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239676603796083e-05, + "loss": 3.5408, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238838009045031e-05, + "loss": 3.5623, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238001052174352e-05, + "loss": 3.545, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2371624574233e-05, + "loss": 3.5601, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236323862672248e-05, + "loss": 3.5478, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235485267921196e-05, + "loss": 3.5504, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346466731701436e-05, + "loss": 3.5475, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338080784190915e-05, + "loss": 3.5721, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232971121548413e-05, + "loss": 3.5604, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321325267973605e-05, + "loss": 3.5562, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2312939320463085e-05, + "loss": 3.554, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304553372952564e-05, + "loss": 3.5625, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229618380424578e-05, + "loss": 3.5449, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228779785673526e-05, + "loss": 3.5452, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227941190922474e-05, + "loss": 3.5583, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227102596171422e-05, + "loss": 3.5501, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2262656393007436e-05, + "loss": 3.5457, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225427044549691e-05, + "loss": 3.5494, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224588449798639e-05, + "loss": 3.5535, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223749855047587e-05, + "loss": 3.5555, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222912898176908e-05, + "loss": 3.5511, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222074303425856e-05, + "loss": 3.5484, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221235708674804e-05, + "loss": 3.5648, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220397113923752e-05, + "loss": 3.5589, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2195601570530734e-05, + "loss": 3.5372, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187215623020214e-05, + "loss": 3.5455, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2178829675509694e-05, + "loss": 3.5454, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170443727999174e-05, + "loss": 3.5465, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162057780488654e-05, + "loss": 3.5493, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215368821178186e-05, + "loss": 3.5567, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214530226427134e-05, + "loss": 3.5486, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213691631676082e-05, + "loss": 3.5493, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.21285303692503e-05, + "loss": 3.5579, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212016080054351e-05, + "loss": 3.5544, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211177485303299e-05, + "loss": 3.5549, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210338890552247e-05, + "loss": 3.5301, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209500295801195e-05, + "loss": 3.5574, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208663338930517e-05, + "loss": 3.5553, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207824744179465e-05, + "loss": 3.5496, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206986149428413e-05, + "loss": 3.5451, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206147554677361e-05, + "loss": 3.5491, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205308959926309e-05, + "loss": 3.5333, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2044720030556297e-05, + "loss": 3.5453, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036334083045776e-05, + "loss": 3.561, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2027948135535256e-05, + "loss": 3.546, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2019562188024736e-05, + "loss": 3.5594, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011192619317946e-05, + "loss": 3.555, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2002806671807425e-05, + "loss": 3.5323, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994420724296905e-05, + "loss": 3.5595, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198603477678639e-05, + "loss": 3.5405, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.19776652080796e-05, + "loss": 3.5359, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196927926056908e-05, + "loss": 3.5397, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196089331305856e-05, + "loss": 3.5491, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195250736554804e-05, + "loss": 3.5412, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194413779684125e-05, + "loss": 3.539, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193575184933073e-05, + "loss": 3.5342, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192736590182021e-05, + "loss": 3.5533, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191897995430969e-05, + "loss": 3.5539, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191059400679917e-05, + "loss": 3.5486, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190222443809238e-05, + "loss": 3.5511, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189383849058186e-05, + "loss": 3.5501, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1885452543071346e-05, + "loss": 3.5602, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1877066595560826e-05, + "loss": 3.5531, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1868697026854035e-05, + "loss": 3.5503, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860311079343515e-05, + "loss": 3.5502, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1851925131832995e-05, + "loss": 3.5454, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1843539184322475e-05, + "loss": 3.551, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835169615615684e-05, + "loss": 3.5449, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1826783668105164e-05, + "loss": 3.5551, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818397720594644e-05, + "loss": 3.5642, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810011773084124e-05, + "loss": 3.5474, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801625825573604e-05, + "loss": 3.5258, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179325625686681e-05, + "loss": 3.5433, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178487030935629e-05, + "loss": 3.5507, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177648436184578e-05, + "loss": 3.5457, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176809841433526e-05, + "loss": 3.5464, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175972884562847e-05, + "loss": 3.5527, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175134289811795e-05, + "loss": 3.5382, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174295695060743e-05, + "loss": 3.545, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173457100309691e-05, + "loss": 3.5448, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172620143439012e-05, + "loss": 3.5535, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.17178154868796e-05, + "loss": 3.5493, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170942953936908e-05, + "loss": 3.5613, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170104359185856e-05, + "loss": 3.5341, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1692674023151766e-05, + "loss": 3.5492, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684288075641246e-05, + "loss": 3.55, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167590212813073e-05, + "loss": 3.5462, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166751618062021e-05, + "loss": 3.5578, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165914661191342e-05, + "loss": 3.5388, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.16507606644029e-05, + "loss": 3.5406, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164237471689238e-05, + "loss": 3.5419, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163398876938186e-05, + "loss": 3.5502, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162561920067507e-05, + "loss": 3.5405, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161723325316455e-05, + "loss": 3.5298, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160884730565403e-05, + "loss": 3.546, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160046135814351e-05, + "loss": 3.5473, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159209178943672e-05, + "loss": 3.5412, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.15837058419262e-05, + "loss": 3.5478, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157531989441569e-05, + "loss": 3.5342, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156693394690516e-05, + "loss": 3.5491, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1558564378198376e-05, + "loss": 3.5405, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1550178430687856e-05, + "loss": 3.5447, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1541792483177336e-05, + "loss": 3.5552, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153340653566681e-05, + "loss": 3.5521, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152502058815629e-05, + "loss": 3.545, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516651019449505e-05, + "loss": 3.5406, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508265071938985e-05, + "loss": 3.5458, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149987912442846e-05, + "loss": 3.5432, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149149317691794e-05, + "loss": 3.5396, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483123608211154e-05, + "loss": 3.5481, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1474737660700634e-05, + "loss": 3.5387, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466351713190114e-05, + "loss": 3.5419, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1457965765679594e-05, + "loss": 3.5377, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1449579818169074e-05, + "loss": 3.5433, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144121024946228e-05, + "loss": 3.5375, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143282430195176e-05, + "loss": 3.5399, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142443835444124e-05, + "loss": 3.5557, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141605240693072e-05, + "loss": 3.5452, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140768283822393e-05, + "loss": 3.5565, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139929689071341e-05, + "loss": 3.5321, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139091094320289e-05, + "loss": 3.548, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138252499569238e-05, + "loss": 3.5538, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137415542698559e-05, + "loss": 3.549, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136576947947507e-05, + "loss": 3.5398, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135738353196455e-05, + "loss": 3.5356, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134899758445403e-05, + "loss": 3.5527, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134061163694351e-05, + "loss": 3.56, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332242068236716e-05, + "loss": 3.5392, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1323856120726196e-05, + "loss": 3.5379, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315470173215676e-05, + "loss": 3.5459, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307084225705156e-05, + "loss": 3.5402, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1298714656998365e-05, + "loss": 3.5387, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290328709487845e-05, + "loss": 3.549, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128194276197733e-05, + "loss": 3.5374, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127355681446681e-05, + "loss": 3.5518, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126518724576002e-05, + "loss": 3.5355, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.843055248260498, + "eval_runtime": 304.7659, + "eval_samples_per_second": 1252.079, + "eval_steps_per_second": 39.128, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.12568012982495e-05, + "loss": 3.5378, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124841535073898e-05, + "loss": 3.5398, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124002940322846e-05, + "loss": 3.5446, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123165983452167e-05, + "loss": 3.5525, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122327388701115e-05, + "loss": 3.5468, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121488793950063e-05, + "loss": 3.5437, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120650199199011e-05, + "loss": 3.5403, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119813242328332e-05, + "loss": 3.5407, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.11897464757728e-05, + "loss": 3.5348, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1181360528262286e-05, + "loss": 3.5502, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1172974580751766e-05, + "loss": 3.5482, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1164588633241245e-05, + "loss": 3.5487, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156219064534455e-05, + "loss": 3.5556, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1147833117023935e-05, + "loss": 3.5261, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1139447169513414e-05, + "loss": 3.5462, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1131061222002894e-05, + "loss": 3.5287, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1122675274492374e-05, + "loss": 3.5468, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114305705785583e-05, + "loss": 3.5286, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1105919758275063e-05, + "loss": 3.5366, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1097533810764543e-05, + "loss": 3.5367, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108914786325402e-05, + "loss": 3.5547, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108077829454724e-05, + "loss": 3.5472, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107239234703672e-05, + "loss": 3.535, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.10640063995262e-05, + "loss": 3.5378, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105562045201568e-05, + "loss": 3.5501, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104725088330889e-05, + "loss": 3.5286, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103886493579837e-05, + "loss": 3.5286, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103047898828785e-05, + "loss": 3.5447, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102209304077733e-05, + "loss": 3.5309, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101372347207054e-05, + "loss": 3.5324, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100533752456002e-05, + "loss": 3.5332, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.09969515770495e-05, + "loss": 3.5374, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098856562953898e-05, + "loss": 3.5438, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980196060832186e-05, + "loss": 3.5329, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097181011332167e-05, + "loss": 3.535, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096342416581115e-05, + "loss": 3.5473, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095503821830063e-05, + "loss": 3.5442, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094666864959384e-05, + "loss": 3.5227, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093828270208332e-05, + "loss": 3.5324, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.09298967545728e-05, + "loss": 3.5243, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092151080706228e-05, + "loss": 3.5315, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091312485955176e-05, + "loss": 3.5326, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090475529084497e-05, + "loss": 3.5429, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089636934333445e-05, + "loss": 3.5351, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088798339582393e-05, + "loss": 3.5333, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087959744831341e-05, + "loss": 3.541, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871227879606627e-05, + "loss": 3.5434, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0862841932096106e-05, + "loss": 3.5365, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0854455984585586e-05, + "loss": 3.5181, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0846070037075066e-05, + "loss": 3.5398, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0837700468368275e-05, + "loss": 3.5411, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829314520857755e-05, + "loss": 3.5343, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0820928573347235e-05, + "loss": 3.5283, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081254262583671e-05, + "loss": 3.5317, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804173057129924e-05, + "loss": 3.5265, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0795787109619404e-05, + "loss": 3.5217, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787401162108884e-05, + "loss": 3.5482, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779015214598364e-05, + "loss": 3.5319, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077064564589158e-05, + "loss": 3.5417, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076225969838106e-05, + "loss": 3.5411, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075387375087053e-05, + "loss": 3.5168, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074548780336001e-05, + "loss": 3.5391, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073711823465323e-05, + "loss": 3.5303, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072873228714271e-05, + "loss": 3.5251, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072034633963218e-05, + "loss": 3.5193, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071196039212166e-05, + "loss": 3.5352, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070357444461114e-05, + "loss": 3.5307, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069520487590436e-05, + "loss": 3.5196, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068681892839383e-05, + "loss": 3.5203, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067843298088332e-05, + "loss": 3.5396, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.06700470333728e-05, + "loss": 3.5396, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066166108586228e-05, + "loss": 3.5347, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065329151715549e-05, + "loss": 3.5364, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064490556964497e-05, + "loss": 3.5357, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063651962213445e-05, + "loss": 3.5413, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062813367462393e-05, + "loss": 3.5401, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0619764105917136e-05, + "loss": 3.5364, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611378158406616e-05, + "loss": 3.5365, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0602992210896096e-05, + "loss": 3.5299, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0594606263385576e-05, + "loss": 3.5367, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586236694678785e-05, + "loss": 3.5302, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057785074716827e-05, + "loss": 3.5413, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056946479965775e-05, + "loss": 3.5444, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056107885214723e-05, + "loss": 3.5363, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055269290463671e-05, + "loss": 3.5111, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054432333592992e-05, + "loss": 3.526, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.05359373884194e-05, + "loss": 3.5361, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052755144090888e-05, + "loss": 3.5331, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051916549339836e-05, + "loss": 3.5299, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051079592469157e-05, + "loss": 3.5387, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050240997718105e-05, + "loss": 3.5287, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494024029670533e-05, + "loss": 3.5228, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485638082160013e-05, + "loss": 3.5291, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477268513453222e-05, + "loss": 3.5363, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0468882565942702e-05, + "loss": 3.5332, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460496618432182e-05, + "loss": 3.5467, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452110670921662e-05, + "loss": 3.522, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443741102214874e-05, + "loss": 3.5338, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435355154704354e-05, + "loss": 3.5362, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0426969207193834e-05, + "loss": 3.5296, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418583259683314e-05, + "loss": 3.5381, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410213690976523e-05, + "loss": 3.5296, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0401827743466003e-05, + "loss": 3.5251, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393441795955487e-05, + "loss": 3.5254, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385055848444966e-05, + "loss": 3.5367, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376686279738176e-05, + "loss": 3.5225, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368300332227656e-05, + "loss": 3.5146, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0359914384717136e-05, + "loss": 3.5335, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351528437206615e-05, + "loss": 3.5318, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343158868499828e-05, + "loss": 3.5268, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334772920989308e-05, + "loss": 3.5324, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326386973478788e-05, + "loss": 3.5204, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318001025968268e-05, + "loss": 3.5359, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309631457261477e-05, + "loss": 3.5226, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301245509750957e-05, + "loss": 3.5303, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029285956224044e-05, + "loss": 3.5373, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028447361472992e-05, + "loss": 3.5398, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.02760876672194e-05, + "loss": 3.5284, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026771809851261e-05, + "loss": 3.5267, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025933215100209e-05, + "loss": 3.5326, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.025094620349157e-05, + "loss": 3.5287, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024256025598105e-05, + "loss": 3.5208, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234174308470532e-05, + "loss": 3.5344, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022580473976374e-05, + "loss": 3.5249, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021741879225322e-05, + "loss": 3.5266, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.02090328447427e-05, + "loss": 3.5251, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020064689723218e-05, + "loss": 3.5259, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192277328525394e-05, + "loss": 3.5289, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0183891381014874e-05, + "loss": 3.527, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175505433504354e-05, + "loss": 3.5342, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167119485993834e-05, + "loss": 3.5355, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0158749917287043e-05, + "loss": 3.5411, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150363969776523e-05, + "loss": 3.5169, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0141978022266003e-05, + "loss": 3.5356, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133592074755486e-05, + "loss": 3.5369, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125222506048695e-05, + "loss": 3.5342, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0116836558538175e-05, + "loss": 3.527, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108450611027655e-05, + "loss": 3.5227, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100064663517135e-05, + "loss": 3.5375, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091695094810348e-05, + "loss": 3.544, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083309147299827e-05, + "loss": 3.5265, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0074923199789307e-05, + "loss": 3.5229, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066537252278787e-05, + "loss": 3.5319, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058167683571997e-05, + "loss": 3.5241, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049781736061476e-05, + "loss": 3.5254, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041395788550956e-05, + "loss": 3.5369, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003300984104044e-05, + "loss": 3.5231, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002464027233365e-05, + "loss": 3.5372, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001625432482313e-05, + "loss": 3.5225, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000786837731261e-05, + "loss": 3.5257, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.845200538635254, + "eval_runtime": 306.2218, + "eval_samples_per_second": 1246.126, + "eval_steps_per_second": 38.942, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999482429802085e-05, + "loss": 3.5205, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991096482291565e-05, + "loss": 3.5279, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982710534781045e-05, + "loss": 3.539, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974324587270525e-05, + "loss": 3.5314, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9965955018563734e-05, + "loss": 3.5298, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957569071053214e-05, + "loss": 3.5274, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949183123542694e-05, + "loss": 3.5277, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940797176032178e-05, + "loss": 3.5154, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932427607325387e-05, + "loss": 3.5424, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924041659814867e-05, + "loss": 3.5278, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915655712304347e-05, + "loss": 3.5394, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907269764793827e-05, + "loss": 3.5404, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989890019608704e-05, + "loss": 3.5162, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989051424857652e-05, + "loss": 3.5272, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882128301066e-05, + "loss": 3.5177, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987374235355548e-05, + "loss": 3.5266, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865372784848688e-05, + "loss": 3.5248, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9856986837338168e-05, + "loss": 3.5199, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848600889827648e-05, + "loss": 3.5206, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984021494231713e-05, + "loss": 3.5371, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983184537361034e-05, + "loss": 3.5324, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982345942609982e-05, + "loss": 3.5233, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.98150734785893e-05, + "loss": 3.5241, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980668753107878e-05, + "loss": 3.5362, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798317962371993e-05, + "loss": 3.5159, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9789932014861473e-05, + "loss": 3.5138, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781546067350953e-05, + "loss": 3.5278, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773160119840433e-05, + "loss": 3.5182, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976479055113364e-05, + "loss": 3.5177, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975640460362312e-05, + "loss": 3.5169, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.97480186561126e-05, + "loss": 3.5236, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973963270860208e-05, + "loss": 3.527, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731263139895294e-05, + "loss": 3.5184, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9722877192384774e-05, + "loss": 3.5226, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714491244874254e-05, + "loss": 3.5341, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706105297363734e-05, + "loss": 3.5291, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697735728656946e-05, + "loss": 3.5099, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689349781146426e-05, + "loss": 3.5193, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9680963833635906e-05, + "loss": 3.5077, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672577886125386e-05, + "loss": 3.5248, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664208317418595e-05, + "loss": 3.5162, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655822369908075e-05, + "loss": 3.5266, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647436422397555e-05, + "loss": 3.5186, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639050474887035e-05, + "loss": 3.5228, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630680906180248e-05, + "loss": 3.5233, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622294958669728e-05, + "loss": 3.529, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9613909011159208e-05, + "loss": 3.5206, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605523063648688e-05, + "loss": 3.5048, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597137116138167e-05, + "loss": 3.5237, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958876754743138e-05, + "loss": 3.5292, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958038159992086e-05, + "loss": 3.5178, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957199565241034e-05, + "loss": 3.514, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956360970489982e-05, + "loss": 3.514, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955524013619303e-05, + "loss": 3.5146, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954685418868251e-05, + "loss": 3.5063, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953846824117199e-05, + "loss": 3.5336, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530082293661472e-05, + "loss": 3.5183, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952171272495468e-05, + "loss": 3.5284, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951332677744416e-05, + "loss": 3.5239, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950494082993364e-05, + "loss": 3.5054, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949655488242312e-05, + "loss": 3.5249, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488185313716334e-05, + "loss": 3.5187, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9479799366205814e-05, + "loss": 3.5079, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471413418695294e-05, + "loss": 3.5052, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463027471184773e-05, + "loss": 3.5241, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454657902477983e-05, + "loss": 3.5141, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446271954967463e-05, + "loss": 3.5079, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9437886007456943e-05, + "loss": 3.502, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429500059946426e-05, + "loss": 3.5242, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421130491239635e-05, + "loss": 3.526, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9412744543729115e-05, + "loss": 3.5194, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404358596218595e-05, + "loss": 3.5212, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9395972648708075e-05, + "loss": 3.5253, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387603080001287e-05, + "loss": 3.5252, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379217132490767e-05, + "loss": 3.5267, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9370831184980247e-05, + "loss": 3.5177, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362445237469727e-05, + "loss": 3.5252, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354075668762936e-05, + "loss": 3.5167, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345689721252416e-05, + "loss": 3.5194, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337303773741896e-05, + "loss": 3.5156, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932891782623138e-05, + "loss": 3.5244, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932054825752459e-05, + "loss": 3.5311, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931216231001407e-05, + "loss": 3.5207, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930377636250355e-05, + "loss": 3.4992, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929539041499303e-05, + "loss": 3.5112, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928702084628624e-05, + "loss": 3.5236, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927863489877572e-05, + "loss": 3.5198, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.92702489512652e-05, + "loss": 3.5186, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926186300375468e-05, + "loss": 3.5199, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925349343504789e-05, + "loss": 3.5168, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924510748753737e-05, + "loss": 3.5084, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923672154002685e-05, + "loss": 3.5144, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228335592516333e-05, + "loss": 3.523, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9219966023809542e-05, + "loss": 3.5183, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211580076299022e-05, + "loss": 3.5317, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203194128788502e-05, + "loss": 3.512, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194808181277982e-05, + "loss": 3.5176, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186438612571195e-05, + "loss": 3.5217, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178052665060675e-05, + "loss": 3.5164, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169666717550155e-05, + "loss": 3.5244, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161280770039634e-05, + "loss": 3.515, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9152894822529108e-05, + "loss": 3.5095, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144525253822324e-05, + "loss": 3.5131, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136139306311804e-05, + "loss": 3.5225, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127753358801287e-05, + "loss": 3.5078, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911936741129076e-05, + "loss": 3.5002, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9110997842583976e-05, + "loss": 3.5171, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102611895073456e-05, + "loss": 3.5222, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094225947562936e-05, + "loss": 3.512, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9085856378856148e-05, + "loss": 3.5186, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077470431345628e-05, + "loss": 3.5075, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069084483835108e-05, + "loss": 3.5206, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.906069853632458e-05, + "loss": 3.5073, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052328967617797e-05, + "loss": 3.5167, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9043943020107277e-05, + "loss": 3.5251, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035557072596757e-05, + "loss": 3.5266, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027171125086234e-05, + "loss": 3.5116, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901880155637945e-05, + "loss": 3.5161, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901041560886893e-05, + "loss": 3.5171, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900202966135841e-05, + "loss": 3.5161, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993643713847886e-05, + "loss": 3.5085, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985274145141102e-05, + "loss": 3.5152, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8976888197630582e-05, + "loss": 3.5147, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968502250120055e-05, + "loss": 3.5197, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960116302609535e-05, + "loss": 3.511, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951730355099015e-05, + "loss": 3.5099, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894336078639223e-05, + "loss": 3.5128, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8934974838881707e-05, + "loss": 3.5163, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926588891371187e-05, + "loss": 3.5132, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918219322664403e-05, + "loss": 3.5258, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8909833375153883e-05, + "loss": 3.5243, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901447427643356e-05, + "loss": 3.5061, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889306148013284e-05, + "loss": 3.5168, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8884691911426052e-05, + "loss": 3.5271, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887630596391553e-05, + "loss": 3.5221, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886792001640501e-05, + "loss": 3.5133, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885953406889449e-05, + "loss": 3.5073, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851164500187705e-05, + "loss": 3.5255, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884277855267718e-05, + "loss": 3.5241, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883439260516666e-05, + "loss": 3.5154, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882600665765614e-05, + "loss": 3.5104, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881763708894935e-05, + "loss": 3.5132, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880925114143883e-05, + "loss": 3.5136, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.880086519392831e-05, + "loss": 3.5082, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.879247924641779e-05, + "loss": 3.5246, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784109677711003e-05, + "loss": 3.5151, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775723730200482e-05, + "loss": 3.5181, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767337782689962e-05, + "loss": 3.5096, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8758951835179442e-05, + "loss": 3.5073, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.845940351486206, + "eval_runtime": 302.9101, + "eval_samples_per_second": 1259.75, + "eval_steps_per_second": 39.368, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750582266472655e-05, + "loss": 3.5076, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742196318962135e-05, + "loss": 3.5174, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8733810371451615e-05, + "loss": 3.5212, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725424423941095e-05, + "loss": 3.5151, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717038476430575e-05, + "loss": 3.5198, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708668907723784e-05, + "loss": 3.5143, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700282960213264e-05, + "loss": 3.5138, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8691897012702744e-05, + "loss": 3.5011, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683511065192227e-05, + "loss": 3.5287, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675141496485436e-05, + "loss": 3.5155, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8666755548974916e-05, + "loss": 3.5264, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658369601464396e-05, + "loss": 3.5217, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8649983653953876e-05, + "loss": 3.5085, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864161408524709e-05, + "loss": 3.5089, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863322813773657e-05, + "loss": 3.5101, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862484219022605e-05, + "loss": 3.5071, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861645624271553e-05, + "loss": 3.5118, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608086674008737e-05, + "loss": 3.5083, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599700726498217e-05, + "loss": 3.504, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591314778987697e-05, + "loss": 3.5291, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858292883147718e-05, + "loss": 3.5176, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857455926277039e-05, + "loss": 3.5121, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856617331525987e-05, + "loss": 3.5095, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855778736774935e-05, + "loss": 3.5236, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854940142023883e-05, + "loss": 3.5, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541031851532042e-05, + "loss": 3.5024, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532645904021522e-05, + "loss": 3.5096, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524259956511002e-05, + "loss": 3.5096, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8515874009000482e-05, + "loss": 3.5031, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850750444029369e-05, + "loss": 3.5055, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849911849278317e-05, + "loss": 3.5114, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849073254527265e-05, + "loss": 3.5159, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482346597762134e-05, + "loss": 3.5017, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8473977029055343e-05, + "loss": 3.5092, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465591081544823e-05, + "loss": 3.5193, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457205134034303e-05, + "loss": 3.514, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8448819186523783e-05, + "loss": 3.4988, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440449617816996e-05, + "loss": 3.5011, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432063670306476e-05, + "loss": 3.5001, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423677722795956e-05, + "loss": 3.5082, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415291775285436e-05, + "loss": 3.5004, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8406922206578645e-05, + "loss": 3.5117, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398536259068125e-05, + "loss": 3.5038, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390150311557605e-05, + "loss": 3.5081, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381764364047088e-05, + "loss": 3.5139, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373394795340297e-05, + "loss": 3.5136, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365008847829777e-05, + "loss": 3.5102, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356622900319257e-05, + "loss": 3.4912, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348236952808737e-05, + "loss": 3.5116, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.833986738410195e-05, + "loss": 3.5134, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833148143659143e-05, + "loss": 3.5091, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832309548908091e-05, + "loss": 3.5044, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831470954157039e-05, + "loss": 3.4982, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.83063399728636e-05, + "loss": 3.5062, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829795402535308e-05, + "loss": 3.4902, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.828956807784256e-05, + "loss": 3.5199, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281182130332042e-05, + "loss": 3.5059, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827281256162525e-05, + "loss": 3.5179, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826442661411473e-05, + "loss": 3.5111, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825604066660421e-05, + "loss": 3.4919, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824765471909369e-05, + "loss": 3.5088, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239285150386903e-05, + "loss": 3.5072, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8230899202876383e-05, + "loss": 3.4918, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222513255365863e-05, + "loss": 3.4909, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214127307855343e-05, + "loss": 3.509, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205757739148552e-05, + "loss": 3.5037, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197371791638032e-05, + "loss": 3.4952, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8188985844127512e-05, + "loss": 3.4905, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180599896616995e-05, + "loss": 3.5108, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172230327910204e-05, + "loss": 3.5104, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8163844380399684e-05, + "loss": 3.5076, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155458432889164e-05, + "loss": 3.5058, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147072485378644e-05, + "loss": 3.5158, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138702916671857e-05, + "loss": 3.5102, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130316969161337e-05, + "loss": 3.5163, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8121931021650817e-05, + "loss": 3.5, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113545074140297e-05, + "loss": 3.5141, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105175505433506e-05, + "loss": 3.5033, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096789557922986e-05, + "loss": 3.506, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088403610412466e-05, + "loss": 3.5037, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080017662901946e-05, + "loss": 3.5085, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071648094195158e-05, + "loss": 3.5174, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063262146684638e-05, + "loss": 3.5097, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8054876199174118e-05, + "loss": 3.4871, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046490251663598e-05, + "loss": 3.4962, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803812068295681e-05, + "loss": 3.508, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802973473544629e-05, + "loss": 3.5056, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802134878793577e-05, + "loss": 3.5085, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801296284042525e-05, + "loss": 3.5066, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800459327171846e-05, + "loss": 3.503, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799620732420794e-05, + "loss": 3.4947, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798782137669742e-05, + "loss": 3.5024, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.79794354291869e-05, + "loss": 3.5054, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971065860480112e-05, + "loss": 3.5074, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7962679912969592e-05, + "loss": 3.5135, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954293965459072e-05, + "loss": 3.5065, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.794590801794855e-05, + "loss": 3.5006, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793753844924176e-05, + "loss": 3.5078, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929152501731244e-05, + "loss": 3.5063, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920766554220724e-05, + "loss": 3.5119, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912380606710204e-05, + "loss": 3.4999, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904011038003413e-05, + "loss": 3.4964, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895625090492893e-05, + "loss": 3.4993, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887239142982373e-05, + "loss": 3.5101, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787885319547185e-05, + "loss": 3.4981, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870483626765065e-05, + "loss": 3.4854, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862097679254545e-05, + "loss": 3.5045, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853711731744025e-05, + "loss": 3.5075, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.78453257842335e-05, + "loss": 3.498, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7836956215526714e-05, + "loss": 3.5045, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828570268016198e-05, + "loss": 3.4942, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820184320505678e-05, + "loss": 3.5034, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.781179837299515e-05, + "loss": 3.4953, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803428804288367e-05, + "loss": 3.503, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795042856777847e-05, + "loss": 3.5124, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786656909267323e-05, + "loss": 3.5156, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778270961756803e-05, + "loss": 3.497, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.776990139305002e-05, + "loss": 3.5005, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.77615154455395e-05, + "loss": 3.5054, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753129498028972e-05, + "loss": 3.5044, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7744743550518452e-05, + "loss": 3.4928, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736373981811668e-05, + "loss": 3.504, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772798803430115e-05, + "loss": 3.499, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719602086790625e-05, + "loss": 3.508, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711216139280105e-05, + "loss": 3.4955, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770284657057332e-05, + "loss": 3.4971, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694460623062797e-05, + "loss": 3.499, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686074675552277e-05, + "loss": 3.5041, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677688728041757e-05, + "loss": 3.498, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669319159334973e-05, + "loss": 3.5146, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7660933211824446e-05, + "loss": 3.5097, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652547264313926e-05, + "loss": 3.495, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644161316803406e-05, + "loss": 3.4999, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635791748096622e-05, + "loss": 3.5114, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.76274058005861e-05, + "loss": 3.5098, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619019853075578e-05, + "loss": 3.4999, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610633905565058e-05, + "loss": 3.4956, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602264336858267e-05, + "loss": 3.5127, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759387838934775e-05, + "loss": 3.509, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758549244183723e-05, + "loss": 3.4999, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757710649432671e-05, + "loss": 3.5014, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.756872054681619e-05, + "loss": 3.5015, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.75603509781094e-05, + "loss": 3.4992, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755196503059888e-05, + "loss": 3.496, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754357908308836e-05, + "loss": 3.5146, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535193135577843e-05, + "loss": 3.5019, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7526823566871052e-05, + "loss": 3.5052, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518437619360532e-05, + "loss": 3.4967, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510051671850012e-05, + "loss": 3.4958, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8470802307128906, + "eval_runtime": 303.3297, + "eval_samples_per_second": 1258.007, + "eval_steps_per_second": 39.314, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501665724339492e-05, + "loss": 3.4925, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493279776828972e-05, + "loss": 3.5046, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7484893829318452e-05, + "loss": 3.5105, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476507881807935e-05, + "loss": 3.5033, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468138313101144e-05, + "loss": 3.5064, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459752365590624e-05, + "loss": 3.5, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451366418080104e-05, + "loss": 3.5016, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7442980470569584e-05, + "loss": 3.4892, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434610901862797e-05, + "loss": 3.5119, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426224954352277e-05, + "loss": 3.5091, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417839006841756e-05, + "loss": 3.5051, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409453059331236e-05, + "loss": 3.5103, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401083490624446e-05, + "loss": 3.4957, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392697543113926e-05, + "loss": 3.4958, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384311595603405e-05, + "loss": 3.5019, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737592564809289e-05, + "loss": 3.4917, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367556079386098e-05, + "loss": 3.4985, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359170131875578e-05, + "loss": 3.4944, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7350784184365058e-05, + "loss": 3.4914, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342414615658267e-05, + "loss": 3.5175, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733402866814775e-05, + "loss": 3.5018, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732564272063723e-05, + "loss": 3.5061, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731725677312671e-05, + "loss": 3.4953, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730887082561619e-05, + "loss": 3.5094, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.73005012569094e-05, + "loss": 3.4849, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729211530939888e-05, + "loss": 3.4925, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728372936188836e-05, + "loss": 3.4931, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275343414377842e-05, + "loss": 3.4997, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726697384567105e-05, + "loss": 3.4906, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725858789816053e-05, + "loss": 3.4903, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725020195065001e-05, + "loss": 3.4999, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724183238194322e-05, + "loss": 3.504, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233446434432704e-05, + "loss": 3.4875, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225060486922184e-05, + "loss": 3.5, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216674539411664e-05, + "loss": 3.5042, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208288591901144e-05, + "loss": 3.4988, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7199919023194353e-05, + "loss": 3.4874, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191533075683833e-05, + "loss": 3.4911, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183147128173313e-05, + "loss": 3.4805, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174761180662793e-05, + "loss": 3.4976, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166391611956005e-05, + "loss": 3.4885, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158005664445485e-05, + "loss": 3.5004, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149619716934965e-05, + "loss": 3.4919, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141233769424445e-05, + "loss": 3.4927, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7132864200717658e-05, + "loss": 3.5011, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124478253207138e-05, + "loss": 3.5026, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116092305696617e-05, + "loss": 3.4991, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107706358186097e-05, + "loss": 3.4766, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099336789479307e-05, + "loss": 3.4943, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7090950841968787e-05, + "loss": 3.5032, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082564894458266e-05, + "loss": 3.4945, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074178946947746e-05, + "loss": 3.4914, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706580937824096e-05, + "loss": 3.4875, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705742343073044e-05, + "loss": 3.4909, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.704903748321992e-05, + "loss": 3.4796, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.70406515357094e-05, + "loss": 3.5028, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032281967002608e-05, + "loss": 3.4941, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702389601949209e-05, + "loss": 3.5002, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701551007198157e-05, + "loss": 3.5037, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700712412447105e-05, + "loss": 3.4793, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699875455576426e-05, + "loss": 3.4952, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.699036860825374e-05, + "loss": 3.4918, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698198266074322e-05, + "loss": 3.4828, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.69735967132327e-05, + "loss": 3.4796, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965227144525913e-05, + "loss": 3.4943, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956841197015393e-05, + "loss": 3.494, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948455249504872e-05, + "loss": 3.4826, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940069301994346e-05, + "loss": 3.4748, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693169973328756e-05, + "loss": 3.4987, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923313785777045e-05, + "loss": 3.5013, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6914927838266525e-05, + "loss": 3.492, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906541890755998e-05, + "loss": 3.4931, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898172322049214e-05, + "loss": 3.5038, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6889786374538694e-05, + "loss": 3.4978, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688140042702817e-05, + "loss": 3.5045, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687301447951765e-05, + "loss": 3.4839, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864644910810866e-05, + "loss": 3.5017, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856258963300346e-05, + "loss": 3.4946, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684787301578982e-05, + "loss": 3.4892, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.68394870682793e-05, + "loss": 3.4954, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831117499572515e-05, + "loss": 3.4935, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822731552062e-05, + "loss": 3.5048, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814345604551472e-05, + "loss": 3.4956, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680595965704095e-05, + "loss": 3.4756, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797590088334168e-05, + "loss": 3.4842, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789204140823644e-05, + "loss": 3.4941, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6780818193313124e-05, + "loss": 3.4963, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772432245802604e-05, + "loss": 3.4946, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676406267709582e-05, + "loss": 3.4897, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755676729585293e-05, + "loss": 3.491, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747290782074773e-05, + "loss": 3.4842, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6738904834564253e-05, + "loss": 3.4912, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.673053526585747e-05, + "loss": 3.4874, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722149318346945e-05, + "loss": 3.4966, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713763370836425e-05, + "loss": 3.5006, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705377423325905e-05, + "loss": 3.4969, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697007854619114e-05, + "loss": 3.488, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688621907108598e-05, + "loss": 3.495, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680235959598078e-05, + "loss": 3.4917, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6671850012087558e-05, + "loss": 3.4965, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663480443380767e-05, + "loss": 3.4884, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655094495870247e-05, + "loss": 3.4873, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646708548359727e-05, + "loss": 3.4825, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638322600849207e-05, + "loss": 3.497, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.662995303214242e-05, + "loss": 3.4859, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.66215670846319e-05, + "loss": 3.4773, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661318113712138e-05, + "loss": 3.4872, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.660479518961086e-05, + "loss": 3.4949, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596425620904068e-05, + "loss": 3.4837, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658803967339355e-05, + "loss": 3.4964, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657965372588303e-05, + "loss": 3.4799, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657126777837251e-05, + "loss": 3.4944, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656289820966572e-05, + "loss": 3.4829, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.65545122621552e-05, + "loss": 3.4855, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654612631464468e-05, + "loss": 3.5031, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653774036713416e-05, + "loss": 3.501, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529370798427373e-05, + "loss": 3.4847, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6520984850916853e-05, + "loss": 3.4897, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512598903406333e-05, + "loss": 3.4892, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504212955895813e-05, + "loss": 3.4922, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6495843387189022e-05, + "loss": 3.483, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487457439678505e-05, + "loss": 3.4919, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479071492167985e-05, + "loss": 3.4852, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470685544657465e-05, + "loss": 3.494, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462315975950674e-05, + "loss": 3.4782, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6453930028440154e-05, + "loss": 3.49, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445544080929634e-05, + "loss": 3.4843, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437158133419114e-05, + "loss": 3.4893, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6428788564712326e-05, + "loss": 3.4844, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420402617201806e-05, + "loss": 3.5052, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412016669691286e-05, + "loss": 3.4947, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403630722180766e-05, + "loss": 3.4872, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395261153473975e-05, + "loss": 3.4806, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638687520596346e-05, + "loss": 3.4983, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637848925845294e-05, + "loss": 3.4971, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.637010331094242e-05, + "loss": 3.4895, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361733742235628e-05, + "loss": 3.4845, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353347794725108e-05, + "loss": 3.4983, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6344961847214588e-05, + "loss": 3.4955, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336575899704068e-05, + "loss": 3.4882, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632820633099728e-05, + "loss": 3.4885, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.631982038348676e-05, + "loss": 3.4895, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.631143443597624e-05, + "loss": 3.4902, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630304848846572e-05, + "loss": 3.4811, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629467891975893e-05, + "loss": 3.4979, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286292972248412e-05, + "loss": 3.4945, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6277907024737892e-05, + "loss": 3.4891, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269521077227372e-05, + "loss": 3.4827, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626115150852058e-05, + "loss": 3.4805, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8488123416900635, + "eval_runtime": 306.881, + "eval_samples_per_second": 1243.449, + "eval_steps_per_second": 38.859, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625276556101006e-05, + "loss": 3.4869, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624437961349954e-05, + "loss": 3.4877, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623599366598902e-05, + "loss": 3.4965, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227624097282234e-05, + "loss": 3.4904, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219238149771714e-05, + "loss": 3.4974, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6210852202261194e-05, + "loss": 3.4838, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202466254750674e-05, + "loss": 3.4907, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194096686043883e-05, + "loss": 3.4772, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6185710738533366e-05, + "loss": 3.5, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177324791022846e-05, + "loss": 3.4947, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6168938843512326e-05, + "loss": 3.4936, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160569274805535e-05, + "loss": 3.4968, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152183327295015e-05, + "loss": 3.4811, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143797379784495e-05, + "loss": 3.4846, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135427811077708e-05, + "loss": 3.4934, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127041863567187e-05, + "loss": 3.4825, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118655916056667e-05, + "loss": 3.4808, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110269968546147e-05, + "loss": 3.481, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6101884021035627e-05, + "loss": 3.4801, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093514452328836e-05, + "loss": 3.5088, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085128504818316e-05, + "loss": 3.489, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.60767425573078e-05, + "loss": 3.4896, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606835660979728e-05, + "loss": 3.4866, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.605998704109049e-05, + "loss": 3.493, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605160109357997e-05, + "loss": 3.4753, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.604321514606945e-05, + "loss": 3.4805, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603482919855893e-05, + "loss": 3.4814, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.602645962985214e-05, + "loss": 3.4873, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.601807368234162e-05, + "loss": 3.4749, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.60096877348311e-05, + "loss": 3.4789, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600130178732058e-05, + "loss": 3.4823, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599293221861379e-05, + "loss": 3.4927, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598454627110327e-05, + "loss": 3.479, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976160323592753e-05, + "loss": 3.486, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967774376082233e-05, + "loss": 3.4889, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959404807375442e-05, + "loss": 3.4878, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951018859864922e-05, + "loss": 3.4748, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942632912354402e-05, + "loss": 3.4826, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934246964843882e-05, + "loss": 3.4666, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5925877396137095e-05, + "loss": 3.4863, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917491448626575e-05, + "loss": 3.4749, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909105501116055e-05, + "loss": 3.4881, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900735932409264e-05, + "loss": 3.4821, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892349984898744e-05, + "loss": 3.4777, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5883964037388224e-05, + "loss": 3.4926, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875578089877707e-05, + "loss": 3.4873, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867208521170916e-05, + "loss": 3.4867, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5858822573660396e-05, + "loss": 3.471, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850436626149876e-05, + "loss": 3.4769, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842050678639356e-05, + "loss": 3.4917, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583368110993257e-05, + "loss": 3.4788, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582529516242205e-05, + "loss": 3.477, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581690921491153e-05, + "loss": 3.4788, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.580852326740101e-05, + "loss": 3.4811, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800153698694217e-05, + "loss": 3.4677, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791767751183697e-05, + "loss": 3.4866, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783381803673177e-05, + "loss": 3.4831, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577499585616266e-05, + "loss": 3.4888, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576662628745587e-05, + "loss": 3.4881, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575824033994535e-05, + "loss": 3.471, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.574985439243483e-05, + "loss": 3.4784, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.574146844492431e-05, + "loss": 3.4838, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733098876217522e-05, + "loss": 3.4722, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724712928707002e-05, + "loss": 3.4701, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716326981196482e-05, + "loss": 3.4794, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5707941033685962e-05, + "loss": 3.4851, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569957146497917e-05, + "loss": 3.4712, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.569118551746865e-05, + "loss": 3.4647, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568279956995813e-05, + "loss": 3.482, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674413622447614e-05, + "loss": 3.489, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666044053740824e-05, + "loss": 3.478, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657658106230303e-05, + "loss": 3.4843, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649272158719783e-05, + "loss": 3.4906, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5640886211209263e-05, + "loss": 3.4855, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632516642502476e-05, + "loss": 3.4943, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624130694991956e-05, + "loss": 3.4708, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615744747481436e-05, + "loss": 3.4873, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560735879997091e-05, + "loss": 3.4849, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5598989231264125e-05, + "loss": 3.4749, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590603283753605e-05, + "loss": 3.4878, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582217336243085e-05, + "loss": 3.4816, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557383138873256e-05, + "loss": 3.4912, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565461820025777e-05, + "loss": 3.4845, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557075872515257e-05, + "loss": 3.4618, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548689925004737e-05, + "loss": 3.4748, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540303977494214e-05, + "loss": 3.4778, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.553193440878743e-05, + "loss": 3.4831, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552354846127691e-05, + "loss": 3.4839, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515162513766383e-05, + "loss": 3.4794, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5506776566255863e-05, + "loss": 3.4783, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.549840699754908e-05, + "loss": 3.4728, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.549002105003856e-05, + "loss": 3.4776, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481635102528035e-05, + "loss": 3.4743, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473249155017515e-05, + "loss": 3.4862, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.546487958631073e-05, + "loss": 3.4903, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545649363880021e-05, + "loss": 3.4849, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448107691289684e-05, + "loss": 3.4739, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5439721743779167e-05, + "loss": 3.4849, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431352175072383e-05, + "loss": 3.4784, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5422966227561856e-05, + "loss": 3.4873, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414580280051336e-05, + "loss": 3.4807, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406194332540816e-05, + "loss": 3.4765, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397824763834032e-05, + "loss": 3.4684, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538943881632351e-05, + "loss": 3.4858, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538105286881299e-05, + "loss": 3.472, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537266692130247e-05, + "loss": 3.4682, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364297352595685e-05, + "loss": 3.4733, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5355911405085158e-05, + "loss": 3.4816, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347525457574638e-05, + "loss": 3.4719, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533913951006412e-05, + "loss": 3.4876, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533076994135733e-05, + "loss": 3.4712, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.532238399384681e-05, + "loss": 3.4739, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.531399804633629e-05, + "loss": 3.4766, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530561209882577e-05, + "loss": 3.4697, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297242530118982e-05, + "loss": 3.4932, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5288856582608462e-05, + "loss": 3.4871, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280470635097942e-05, + "loss": 3.4754, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272084687587422e-05, + "loss": 3.4794, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526371511888063e-05, + "loss": 3.4734, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525532917137011e-05, + "loss": 3.4816, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524694322385959e-05, + "loss": 3.4694, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238557276349075e-05, + "loss": 3.4855, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230187707642284e-05, + "loss": 3.4722, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221801760131764e-05, + "loss": 3.4782, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213415812621244e-05, + "loss": 3.4708, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205029865110724e-05, + "loss": 3.4773, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196660296403936e-05, + "loss": 3.4714, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188274348893416e-05, + "loss": 3.4775, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5179888401382896e-05, + "loss": 3.474, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171502453872376e-05, + "loss": 3.4924, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163132885165585e-05, + "loss": 3.4842, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154746937655065e-05, + "loss": 3.4767, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146360990144545e-05, + "loss": 3.4647, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5137975042634025e-05, + "loss": 3.4879, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129605473927237e-05, + "loss": 3.4827, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121219526416717e-05, + "loss": 3.4834, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5112833578906197e-05, + "loss": 3.472, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104447631395677e-05, + "loss": 3.4818, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096078062688886e-05, + "loss": 3.4828, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508769211517837e-05, + "loss": 3.4813, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507930616766785e-05, + "loss": 3.475, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507092022015733e-05, + "loss": 3.4784, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506255065145054e-05, + "loss": 3.4758, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505416470394002e-05, + "loss": 3.4704, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.50457787564295e-05, + "loss": 3.4829, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503739280891898e-05, + "loss": 3.4862, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502902324021219e-05, + "loss": 3.4755, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.502063729270167e-05, + "loss": 3.4686, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501225134519115e-05, + "loss": 3.476, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.850715160369873, + "eval_runtime": 306.7557, + "eval_samples_per_second": 1243.958, + "eval_steps_per_second": 38.875, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500386539768063e-05, + "loss": 3.4707, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499547945017011e-05, + "loss": 3.4763, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498709350265959e-05, + "loss": 3.4827, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497870755514907e-05, + "loss": 3.4786, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970337986442283e-05, + "loss": 3.4875, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4961952038931763e-05, + "loss": 3.4718, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953566091421243e-05, + "loss": 3.4774, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945180143910723e-05, + "loss": 3.4652, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936810575203932e-05, + "loss": 3.4891, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928424627693416e-05, + "loss": 3.4821, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920038680182896e-05, + "loss": 3.4753, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911652732672372e-05, + "loss": 3.4882, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903283163965585e-05, + "loss": 3.4682, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4894897216455065e-05, + "loss": 3.4739, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886511268944545e-05, + "loss": 3.4788, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878125321434024e-05, + "loss": 3.4699, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869755752727237e-05, + "loss": 3.4706, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861369805216717e-05, + "loss": 3.4678, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4852983857706197e-05, + "loss": 3.4718, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844597910195673e-05, + "loss": 3.4906, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836228341488886e-05, + "loss": 3.4763, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482784239397837e-05, + "loss": 3.4766, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819456446467846e-05, + "loss": 3.474, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811070498957326e-05, + "loss": 3.4809, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802700930250538e-05, + "loss": 3.4644, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794314982740018e-05, + "loss": 3.471, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4785929035229495e-05, + "loss": 3.4672, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477755946652271e-05, + "loss": 3.4774, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476917351901219e-05, + "loss": 3.4621, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476078757150167e-05, + "loss": 3.4689, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752401623991147e-05, + "loss": 3.4734, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474403205528436e-05, + "loss": 3.48, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.473564610777384e-05, + "loss": 3.4676, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.472726016026332e-05, + "loss": 3.4759, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.47188742127528e-05, + "loss": 3.4766, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710504644046012e-05, + "loss": 3.4768, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702118696535492e-05, + "loss": 3.4658, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469373274902497e-05, + "loss": 3.4668, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468534680151445e-05, + "loss": 3.458, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4676977232807664e-05, + "loss": 3.4751, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668591285297144e-05, + "loss": 3.4636, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.466020533778662e-05, + "loss": 3.4761, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.46518193902761e-05, + "loss": 3.4686, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643449821569313e-05, + "loss": 3.4709, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635063874058793e-05, + "loss": 3.4774, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626677926548273e-05, + "loss": 3.4749, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618291979037753e-05, + "loss": 3.4774, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609922410330966e-05, + "loss": 3.4597, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601536462820442e-05, + "loss": 3.4592, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593150515309922e-05, + "loss": 3.4808, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584764567799402e-05, + "loss": 3.4691, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576394999092618e-05, + "loss": 3.466, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568009051582095e-05, + "loss": 3.4659, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559623104071575e-05, + "loss": 3.4707, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551237156561054e-05, + "loss": 3.4545, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542867587854264e-05, + "loss": 3.4757, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534481640343747e-05, + "loss": 3.4709, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526095692833227e-05, + "loss": 3.4733, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517709745322707e-05, + "loss": 3.4783, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509340176615916e-05, + "loss": 3.4641, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4500954229105396e-05, + "loss": 3.4616, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492568281594876e-05, + "loss": 3.479, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484182334084356e-05, + "loss": 3.454, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475812765377568e-05, + "loss": 3.4582, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467426817867048e-05, + "loss": 3.4693, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459040870356528e-05, + "loss": 3.4735, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450654922846008e-05, + "loss": 3.4564, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442285354139217e-05, + "loss": 3.453, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.44338994066287e-05, + "loss": 3.4697, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442551345911818e-05, + "loss": 3.4732, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441712751160766e-05, + "loss": 3.4705, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440875794290087e-05, + "loss": 3.4687, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440037199539035e-05, + "loss": 3.4804, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439198604787983e-05, + "loss": 3.4704, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438360010036931e-05, + "loss": 3.4885, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375230531662522e-05, + "loss": 3.4577, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366844584152002e-05, + "loss": 3.4771, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358458636641482e-05, + "loss": 3.4712, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350072689130962e-05, + "loss": 3.4621, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434170312042417e-05, + "loss": 3.4788, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333317172913654e-05, + "loss": 3.4682, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4324931225403134e-05, + "loss": 3.4761, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316545277892614e-05, + "loss": 3.4793, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308175709185823e-05, + "loss": 3.4504, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299789761675303e-05, + "loss": 3.4651, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291403814164783e-05, + "loss": 3.4625, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283017866654263e-05, + "loss": 3.4727, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274648297947476e-05, + "loss": 3.4708, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266262350436956e-05, + "loss": 3.4652, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257876402926436e-05, + "loss": 3.4707, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249490455415915e-05, + "loss": 3.463, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241120886709125e-05, + "loss": 3.4631, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232734939198608e-05, + "loss": 3.464, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224348991688088e-05, + "loss": 3.4743, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4215963044177568e-05, + "loss": 3.4768, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207593475470777e-05, + "loss": 3.4712, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199207527960257e-05, + "loss": 3.4617, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190821580449737e-05, + "loss": 3.4704, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182435632939217e-05, + "loss": 3.469, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417406606423243e-05, + "loss": 3.4753, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416568011672191e-05, + "loss": 3.4687, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415729416921139e-05, + "loss": 3.4618, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148908221700866e-05, + "loss": 3.458, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140538652994078e-05, + "loss": 3.4729, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.413215270548356e-05, + "loss": 3.4601, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412376675797304e-05, + "loss": 3.4594, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115380810462518e-05, + "loss": 3.4563, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410701124175573e-05, + "loss": 3.471, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409862529424521e-05, + "loss": 3.459, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090239346734687e-05, + "loss": 3.4785, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408185339922417e-05, + "loss": 3.4584, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073483830517383e-05, + "loss": 3.4677, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065097883006863e-05, + "loss": 3.4644, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405671193549634e-05, + "loss": 3.4579, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404832598798582e-05, + "loss": 3.4809, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4039956419279032e-05, + "loss": 3.4762, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031570471768515e-05, + "loss": 3.4642, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023184524257992e-05, + "loss": 3.468, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014798576747472e-05, + "loss": 3.462, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006429008040684e-05, + "loss": 3.4702, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399804306053016e-05, + "loss": 3.454, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398965711301964e-05, + "loss": 3.4765, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981271165509124e-05, + "loss": 3.4647, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972901596802337e-05, + "loss": 3.4636, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964515649291813e-05, + "loss": 3.4618, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956129701781293e-05, + "loss": 3.4636, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947743754270773e-05, + "loss": 3.4577, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939374185563986e-05, + "loss": 3.4675, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3930988238053466e-05, + "loss": 3.4618, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922602290542946e-05, + "loss": 3.4787, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914216343032425e-05, + "loss": 3.4733, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905846774325635e-05, + "loss": 3.4683, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897460826815115e-05, + "loss": 3.4538, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889074879304594e-05, + "loss": 3.4716, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880688931794078e-05, + "loss": 3.471, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872319363087287e-05, + "loss": 3.469, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3863933415576767e-05, + "loss": 3.4597, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855547468066247e-05, + "loss": 3.4708, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847161520555727e-05, + "loss": 3.4698, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.383879195184894e-05, + "loss": 3.4754, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.383040600433842e-05, + "loss": 3.4618, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.38220200568279e-05, + "loss": 3.4671, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381363410931738e-05, + "loss": 3.4619, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805264540610588e-05, + "loss": 3.4605, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796878593100068e-05, + "loss": 3.4753, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788492645589548e-05, + "loss": 3.4683, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378010669807903e-05, + "loss": 3.467, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.377173712937224e-05, + "loss": 3.4585, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376335118186172e-05, + "loss": 3.4642, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.852036952972412, + "eval_runtime": 304.4686, + "eval_samples_per_second": 1253.302, + "eval_steps_per_second": 39.167, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.37549652343512e-05, + "loss": 3.4633, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374657928684068e-05, + "loss": 3.4626, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738209718133893e-05, + "loss": 3.4723, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729823770623373e-05, + "loss": 3.4714, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721437823112853e-05, + "loss": 3.4703, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713068254406062e-05, + "loss": 3.4654, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3704682306895542e-05, + "loss": 3.4624, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696296359385022e-05, + "loss": 3.4558, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3687910411874502e-05, + "loss": 3.4719, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679524464363985e-05, + "loss": 3.4726, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671138516853465e-05, + "loss": 3.4656, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.366275256934294e-05, + "loss": 3.4753, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.365436662183242e-05, + "loss": 3.4568, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3645997053125634e-05, + "loss": 3.4618, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363761110561511e-05, + "loss": 3.469, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629225158104594e-05, + "loss": 3.4556, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620839210594074e-05, + "loss": 3.4599, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612469641887286e-05, + "loss": 3.4581, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604083694376763e-05, + "loss": 3.459, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595697746866243e-05, + "loss": 3.4779, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587311799355723e-05, + "loss": 3.4653, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357894223064894e-05, + "loss": 3.4682, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570556283138415e-05, + "loss": 3.4598, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562170335627895e-05, + "loss": 3.4696, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553784388117375e-05, + "loss": 3.4522, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545414819410584e-05, + "loss": 3.4579, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537028871900064e-05, + "loss": 3.4575, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528642924389548e-05, + "loss": 3.4629, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520256976879028e-05, + "loss": 3.4508, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3511887408172237e-05, + "loss": 3.4581, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503501460661717e-05, + "loss": 3.4642, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495115513151197e-05, + "loss": 3.4678, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486729565640677e-05, + "loss": 3.4605, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.347835999693389e-05, + "loss": 3.4607, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.346997404942337e-05, + "loss": 3.4647, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346158810191285e-05, + "loss": 3.4633, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345320215440233e-05, + "loss": 3.458, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444832585695538e-05, + "loss": 3.4524, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436446638185018e-05, + "loss": 3.4458, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.34280606906745e-05, + "loss": 3.4607, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.341967474316398e-05, + "loss": 3.4515, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.341130517445719e-05, + "loss": 3.4646, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340291922694667e-05, + "loss": 3.457, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339453327943615e-05, + "loss": 3.4571, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338614733192563e-05, + "loss": 3.4703, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377777763218843e-05, + "loss": 3.4605, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369391815708323e-05, + "loss": 3.4673, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361005868197803e-05, + "loss": 3.4477, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352619920687283e-05, + "loss": 3.4472, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344250351980492e-05, + "loss": 3.4705, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333586440446997e-05, + "loss": 3.4587, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327478456959455e-05, + "loss": 3.4561, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319092509448935e-05, + "loss": 3.455, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310722940742144e-05, + "loss": 3.4597, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302336993231624e-05, + "loss": 3.4423, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3293951045721104e-05, + "loss": 3.4625, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285565098210584e-05, + "loss": 3.4582, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277195529503796e-05, + "loss": 3.4581, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268809581993276e-05, + "loss": 3.4715, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260423634482756e-05, + "loss": 3.4504, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252037686972236e-05, + "loss": 3.452, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243668118265445e-05, + "loss": 3.4681, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235282170754925e-05, + "loss": 3.4467, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322689622324441e-05, + "loss": 3.4468, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3218526654537618e-05, + "loss": 3.4544, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210140707027098e-05, + "loss": 3.4604, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201754759516578e-05, + "loss": 3.4495, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193368812006058e-05, + "loss": 3.4434, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.318499924329927e-05, + "loss": 3.4529, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317661329578875e-05, + "loss": 3.4609, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316822734827823e-05, + "loss": 3.4593, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.315984140076771e-05, + "loss": 3.4581, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315147183206092e-05, + "loss": 3.4659, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.31430858845504e-05, + "loss": 3.4627, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.313469993703988e-05, + "loss": 3.4763, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126313989529362e-05, + "loss": 3.4461, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311794442082257e-05, + "loss": 3.4692, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310955847331205e-05, + "loss": 3.4622, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310117252580153e-05, + "loss": 3.4449, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309278657829101e-05, + "loss": 3.4703, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084417009584224e-05, + "loss": 3.4554, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076031062073704e-05, + "loss": 3.4656, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067645114563184e-05, + "loss": 3.4676, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305925916705266e-05, + "loss": 3.4418, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3050889598345873e-05, + "loss": 3.4492, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042503650835353e-05, + "loss": 3.4519, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034117703324833e-05, + "loss": 3.4622, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025731755814313e-05, + "loss": 3.4581, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017362187107525e-05, + "loss": 3.4561, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3008976239597005e-05, + "loss": 3.4533, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000590292086485e-05, + "loss": 3.4541, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299220434457596e-05, + "loss": 3.4536, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2983834775869174e-05, + "loss": 3.4516, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2975448828358657e-05, + "loss": 3.4656, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967062880848134e-05, + "loss": 3.4653, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958676933337614e-05, + "loss": 3.4647, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950307364630826e-05, + "loss": 3.4472, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2941921417120306e-05, + "loss": 3.4617, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933535469609786e-05, + "loss": 3.4553, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925149522099266e-05, + "loss": 3.4609, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291677995339248e-05, + "loss": 3.4597, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908394005881955e-05, + "loss": 3.4539, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900008058371435e-05, + "loss": 3.4489, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891622110860915e-05, + "loss": 3.4586, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883252542154128e-05, + "loss": 3.4513, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2874866594643608e-05, + "loss": 3.4463, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866480647133088e-05, + "loss": 3.4413, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858094699622568e-05, + "loss": 3.4592, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.284972513091578e-05, + "loss": 3.4505, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841339183405257e-05, + "loss": 3.4646, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.283295323589474e-05, + "loss": 3.4475, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.282456728838422e-05, + "loss": 3.4525, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281619771967743e-05, + "loss": 3.4557, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280781177216691e-05, + "loss": 3.4441, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279942582465639e-05, + "loss": 3.4688, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279103987714587e-05, + "loss": 3.4637, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.278267030843908e-05, + "loss": 3.4511, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277428436092856e-05, + "loss": 3.4543, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276589841341804e-05, + "loss": 3.4519, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275751246590752e-05, + "loss": 3.4596, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274914289720073e-05, + "loss": 3.4387, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274075694969021e-05, + "loss": 3.4634, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732371002179694e-05, + "loss": 3.4497, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2723985054669174e-05, + "loss": 3.4517, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715615485962383e-05, + "loss": 3.4539, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707229538451863e-05, + "loss": 3.4515, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2698843590941343e-05, + "loss": 3.4529, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690457643430823e-05, + "loss": 3.4533, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682088074724035e-05, + "loss": 3.4549, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673702127213515e-05, + "loss": 3.4618, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665316179702995e-05, + "loss": 3.4578, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2656930232192475e-05, + "loss": 3.4599, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648560663485684e-05, + "loss": 3.4417, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640174715975164e-05, + "loss": 3.4642, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631788768464647e-05, + "loss": 3.458, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623402820954127e-05, + "loss": 3.458, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615033252247336e-05, + "loss": 3.4515, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606647304736816e-05, + "loss": 3.4548, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598261357226296e-05, + "loss": 3.4623, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.258989178851951e-05, + "loss": 3.4609, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.258150584100899e-05, + "loss": 3.4491, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257311989349847e-05, + "loss": 3.4538, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256473394598795e-05, + "loss": 3.454, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556364377281158e-05, + "loss": 3.4485, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2547978429770638e-05, + "loss": 3.464, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539592482260118e-05, + "loss": 3.4561, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531206534749598e-05, + "loss": 3.4614, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.252283696604281e-05, + "loss": 3.442, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251445101853229e-05, + "loss": 3.4558, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8521957397460938, + "eval_runtime": 303.2951, + "eval_samples_per_second": 1258.151, + "eval_steps_per_second": 39.318, + "step": 1679040 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.1734780806289981e+18, + "trial_name": null, + "trial_params": null +}