diff --git "a/checkpoint-2671200/trainer_state.json" "b/checkpoint-2671200/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2671200/trainer_state.json" @@ -0,0 +1,31607 @@ +{ + "best_metric": 3.850759506225586, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/3/checkpoints/checkpoint-839520", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2671200, + "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": 10.9751, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8389, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1964, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9913, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.831, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.729, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6181, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5466, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4708, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4107, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3693, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3226, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2769, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.2265, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.2016, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.1534, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 5.1278, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.1024, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0704, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0395, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.024, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9922, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9741, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9492, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9421, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9073, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.8925, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8648, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8574, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.835, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.8275, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.8153, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7978, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7871, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7747, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7605, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7562, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7263, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7161, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6945, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6983, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6842, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6841, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6636, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.658, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6533, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6467, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6345, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6175, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.607, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.626, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.6135, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.594, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.58, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5894, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5654, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5763, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5455, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5663, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5519, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5308, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5254, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5371, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4981, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5097, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5177, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.5039, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4962, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4801, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4776, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4747, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4897, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4655, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.477, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4706, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4679, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.451, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4509, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4463, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4422, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4351, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4272, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4292, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.429, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4078, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.4161, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4141, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.4159, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.4003, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3988, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.389, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3841, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.386, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3884, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3837, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3889, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3802, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3615, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.363, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3707, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3667, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.365, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.355, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3449, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3576, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3364, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3404, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3355, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3354, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.327, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3271, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3205, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3286, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3227, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3148, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3247, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3281, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.3174, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.3046, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.3016, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.3007, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.3064, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.3021, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2912, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.3, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2918, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2915, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2856, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2863, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2782, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2889, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2873, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2855, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2637, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2777, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2728, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2745, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2644, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2725, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2626, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2801, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2486, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2673, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2524, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2501, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2526, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2388, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2436, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2508, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.238, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.206758975982666, + "eval_runtime": 303.3129, + "eval_samples_per_second": 1258.077, + "eval_steps_per_second": 39.316, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2339, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2289, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2439, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2338, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.2424, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2215, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2239, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.2119, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2221, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2176, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2141, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2205, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1997, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.2117, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.197, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.1969, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.2043, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.1963, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.198, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.2132, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1907, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856655985502793e-05, + "loss": 4.1932, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855817390751741e-05, + "loss": 4.1915, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854978796000689e-05, + "loss": 4.1981, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1901, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853303244378958e-05, + "loss": 4.1893, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852464649627906e-05, + "loss": 4.1739, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851626054876854e-05, + "loss": 4.1814, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850787460125802e-05, + "loss": 4.1703, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.84994886537475e-05, + "loss": 4.1817, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849111908504072e-05, + "loss": 4.1757, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482749516333934e-05, + "loss": 4.1788, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847436356882341e-05, + "loss": 4.1832, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846597762131289e-05, + "loss": 4.1711, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845759167380237e-05, + "loss": 4.1762, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844920572629185e-05, + "loss": 4.172, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844081977878133e-05, + "loss": 4.1624, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843243383127081e-05, + "loss": 4.1557, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8424064262564016e-05, + "loss": 4.1473, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415678315053496e-05, + "loss": 4.1549, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407292367542976e-05, + "loss": 4.1553, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398906420032456e-05, + "loss": 4.1624, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839053685132567e-05, + "loss": 4.1507, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838215090381515e-05, + "loss": 4.1486, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837376495630463e-05, + "loss": 4.1542, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836537900879411e-05, + "loss": 4.1477, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835700944008732e-05, + "loss": 4.1483, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.83486234925768e-05, + "loss": 4.1356, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834023754506628e-05, + "loss": 4.1328, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833185159755576e-05, + "loss": 4.1569, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.1533, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831509608133845e-05, + "loss": 4.137, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830671013382793e-05, + "loss": 4.1392, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829834056512114e-05, + "loss": 4.1433, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289954617610625e-05, + "loss": 4.1246, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281568670100105e-05, + "loss": 4.1434, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273182722589585e-05, + "loss": 4.1177, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264796775079065e-05, + "loss": 4.1445, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256410827568545e-05, + "loss": 4.1392, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.121, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239655311351234e-05, + "loss": 4.1194, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231269363840714e-05, + "loss": 4.1344, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222883416330194e-05, + "loss": 4.1004, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214497468819674e-05, + "loss": 4.1178, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820612790011288e-05, + "loss": 4.1285, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819774195260236e-05, + "loss": 4.1218, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818935600509184e-05, + "loss": 4.1126, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818097005758132e-05, + "loss": 4.1008, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817260048887454e-05, + "loss": 4.1089, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816421454136402e-05, + "loss": 4.1099, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.81558285938535e-05, + "loss": 4.1186, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814744264634298e-05, + "loss": 4.1073, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813907307763619e-05, + "loss": 4.1162, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813068713012567e-05, + "loss": 4.1182, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812230118261515e-05, + "loss": 4.1164, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811391523510463e-05, + "loss": 4.1007, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810554566639784e-05, + "loss": 4.1078, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809715971888732e-05, + "loss": 4.1074, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887737713768e-05, + "loss": 4.1014, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808038782386628e-05, + "loss": 4.1036, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807201825515949e-05, + "loss": 4.0974, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806363230764897e-05, + "loss": 4.1048, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805524636013845e-05, + "loss": 4.1024, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804686041262793e-05, + "loss": 4.0836, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803849084392114e-05, + "loss": 4.0912, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803010489641062e-05, + "loss": 4.0954, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.1019, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0921, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800496343268279e-05, + "loss": 4.0892, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799657748517227e-05, + "loss": 4.0846, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798819153766175e-05, + "loss": 4.0763, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.0809, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971436021444446e-05, + "loss": 4.0893, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963050073933926e-05, + "loss": 4.0859, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954664126423406e-05, + "loss": 4.0948, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946278178912886e-05, + "loss": 4.0854, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937908610206095e-05, + "loss": 4.0774, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929522662695575e-05, + "loss": 4.0753, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921136715185055e-05, + "loss": 4.0832, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912750767674535e-05, + "loss": 4.0869, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904381198967744e-05, + "loss": 4.0845, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895995251457224e-05, + "loss": 4.0764, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887609303946704e-05, + "loss": 4.0669, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879223356436184e-05, + "loss": 4.0843, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708537877294e-05, + "loss": 4.064, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786246784021888e-05, + "loss": 4.0713, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785408189270836e-05, + "loss": 4.0704, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784569594519783e-05, + "loss": 4.069, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783734275529478e-05, + "loss": 4.0601, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782895680778426e-05, + "loss": 4.0697, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782057086027374e-05, + "loss": 4.0576, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781218491276322e-05, + "loss": 4.0676, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.78037989652527e-05, + "loss": 4.0658, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779541301774218e-05, + "loss": 4.0582, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778702707023166e-05, + "loss": 4.0777, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777864112272114e-05, + "loss": 4.0754, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770271554014354e-05, + "loss": 4.0677, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761885606503834e-05, + "loss": 4.058, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775349965899331e-05, + "loss": 4.0522, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774511371148279e-05, + "loss": 4.0587, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773672776397227e-05, + "loss": 4.0553, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728341816461747e-05, + "loss": 4.0645, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719955868951227e-05, + "loss": 4.046, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711569921440707e-05, + "loss": 4.0568, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703200352733916e-05, + "loss": 4.0583, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694814405223396e-05, + "loss": 4.06, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686428457712876e-05, + "loss": 4.0453, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767805888900609e-05, + "loss": 4.0531, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766967294149557e-05, + "loss": 4.0514, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766128699398505e-05, + "loss": 4.0542, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765290104647453e-05, + "loss": 4.0592, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764453147776774e-05, + "loss": 4.0587, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763614553025722e-05, + "loss": 4.0364, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.76277595827467e-05, + "loss": 4.0494, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761939001403991e-05, + "loss": 4.0513, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761100406652939e-05, + "loss": 4.05, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760261811901887e-05, + "loss": 4.047, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759423217150835e-05, + "loss": 4.0517, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758584622399783e-05, + "loss": 4.0453, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757746027648731e-05, + "loss": 4.0607, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569090707780525e-05, + "loss": 4.0361, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560704760270005e-05, + "loss": 4.0509, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552318812759485e-05, + "loss": 4.0399, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543932865248965e-05, + "loss": 4.0374, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535563296542174e-05, + "loss": 4.0418, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527177349031654e-05, + "loss": 4.0319, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518791401521134e-05, + "loss": 4.0351, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510405454010614e-05, + "loss": 4.0369, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502019506500094e-05, + "loss": 4.0326, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.035162925720215, + "eval_runtime": 303.1156, + "eval_samples_per_second": 1258.896, + "eval_steps_per_second": 39.341, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493633558989574e-05, + "loss": 4.0293, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485247611479054e-05, + "loss": 4.0246, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476861663968534e-05, + "loss": 4.041, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468475716458014e-05, + "loss": 4.0305, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460089768947494e-05, + "loss": 4.048, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451703821436974e-05, + "loss": 4.0216, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443317873926453e-05, + "loss": 4.0286, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434931926415933e-05, + "loss": 4.0127, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426545978905413e-05, + "loss": 4.0294, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741816003139489e-05, + "loss": 4.0244, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740977408388437e-05, + "loss": 4.0201, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740140451517758e-05, + "loss": 4.0309, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739303494647079e-05, + "loss": 4.008, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738464899896027e-05, + "loss": 4.0249, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737626305144975e-05, + "loss": 4.0077, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736787710393923e-05, + "loss": 4.0097, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735949115642871e-05, + "loss": 4.0099, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.73511052089182e-05, + "loss": 4.0181, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734271926140768e-05, + "loss": 4.0111, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733433331389716e-05, + "loss": 4.0303, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325980123994096e-05, + "loss": 4.0102, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317594176483576e-05, + "loss": 4.0132, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309208228973056e-05, + "loss": 4.0122, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300822281462536e-05, + "loss": 4.0211, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292436333952016e-05, + "loss": 4.0076, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284050386441496e-05, + "loss": 4.0136, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275664438930976e-05, + "loss": 3.9999, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267278491420456e-05, + "loss": 4.0062, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258908922713665e-05, + "loss": 3.9943, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725052297520315e-05, + "loss": 4.009, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724213702769263e-05, + "loss": 4.0067, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723376745898584e-05, + "loss": 4.0094, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722538151147532e-05, + "loss": 4.0147, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.72169955639648e-05, + "loss": 4.0008, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720860961645428e-05, + "loss": 4.0003, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720022366894376e-05, + "loss": 4.0055, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 3.9971, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718345177392272e-05, + "loss": 3.9903, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717508220521593e-05, + "loss": 3.9818, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716671263650914e-05, + "loss": 3.9915, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715832668899862e-05, + "loss": 3.9904, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149940741488105e-05, + "loss": 4.0001, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141554793977585e-05, + "loss": 3.9924, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133168846467065e-05, + "loss": 3.984, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124799277760274e-05, + "loss": 3.9977, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116413330249754e-05, + "loss": 3.9897, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108027382739234e-05, + "loss": 3.9858, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099641435228714e-05, + "loss": 3.9811, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091255487718194e-05, + "loss": 3.9748, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082869540207674e-05, + "loss": 3.9998, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074483592697154e-05, + "loss": 3.9977, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706609764518663e-05, + "loss": 3.9833, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705772807647984e-05, + "loss": 3.9833, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704934212896932e-05, + "loss": 3.9917, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.70409561814588e-05, + "loss": 3.968, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703257023394828e-05, + "loss": 3.9898, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702418428643776e-05, + "loss": 3.968, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701579833892724e-05, + "loss": 3.9903, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700741239141672e-05, + "loss": 3.9943, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9756, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699067325400315e-05, + "loss": 3.9667, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698228730649263e-05, + "loss": 3.9871, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.69739013589821e-05, + "loss": 3.9568, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696551541147158e-05, + "loss": 3.9719, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695712946396106e-05, + "loss": 3.9813, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694874351645054e-05, + "loss": 3.9793, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694035756894003e-05, + "loss": 3.9692, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.9583, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692361843152645e-05, + "loss": 3.9626, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915232484015926e-05, + "loss": 3.9651, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906846536505406e-05, + "loss": 3.9758, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898460588994886e-05, + "loss": 3.9646, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890074641484366e-05, + "loss": 3.9762, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881688693973846e-05, + "loss": 3.9784, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873319125267055e-05, + "loss": 3.978, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864933177756535e-05, + "loss": 3.9581, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856547230246015e-05, + "loss": 3.9692, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848161282735495e-05, + "loss": 3.9716, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683977533522498e-05, + "loss": 3.9626, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683140576651819e-05, + "loss": 3.9665, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682301981900767e-05, + "loss": 3.9638, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681463387149715e-05, + "loss": 3.9646, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680624792398663e-05, + "loss": 3.9694, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.9479, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9603, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.67811064602588e-05, + "loss": 3.9578, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677272051274828e-05, + "loss": 3.9692, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676433456523776e-05, + "loss": 3.958, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.9579, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9531, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739193101509935e-05, + "loss": 3.9471, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730807153999415e-05, + "loss": 3.9469, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.9571, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9653, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705665690271584e-05, + "loss": 3.9628, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697279742761064e-05, + "loss": 3.9553, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688893795250544e-05, + "loss": 3.9491, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680507847740024e-05, + "loss": 3.9497, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667213827903323e-05, + "loss": 3.9537, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666375233152271e-05, + "loss": 3.9605, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665536638401219e-05, + "loss": 3.9576, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664698043650167e-05, + "loss": 3.9503, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663859448899115e-05, + "loss": 3.9415, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663022492028437e-05, + "loss": 3.9625, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662183897277385e-05, + "loss": 3.9389, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661345302526333e-05, + "loss": 3.9486, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660506707775281e-05, + "loss": 3.9421, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659668113024229e-05, + "loss": 3.9482, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65883115615355e-05, + "loss": 3.9386, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657992561402498e-05, + "loss": 3.948, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9395, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656315371900393e-05, + "loss": 3.9403, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655476777149341e-05, + "loss": 3.9496, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546398202786626e-05, + "loss": 3.9345, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538012255276106e-05, + "loss": 3.9567, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529626307765586e-05, + "loss": 3.9549, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521240360255066e-05, + "loss": 3.9486, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512854412744546e-05, + "loss": 3.9397, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650448484403776e-05, + "loss": 3.9356, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496098896527235e-05, + "loss": 3.9368, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487712949016715e-05, + "loss": 3.9377, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479327001506195e-05, + "loss": 3.9462, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470941053995675e-05, + "loss": 3.9279, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462555106485155e-05, + "loss": 3.9419, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454169158974635e-05, + "loss": 3.9439, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445783211464115e-05, + "loss": 3.9414, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437413642757324e-05, + "loss": 3.9315, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429027695246804e-05, + "loss": 3.9368, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642064174773629e-05, + "loss": 3.9391, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641225580022577e-05, + "loss": 3.9395, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640386985271525e-05, + "loss": 3.9414, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639548390520473e-05, + "loss": 3.9466, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638711433649794e-05, + "loss": 3.9217, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637872838898742e-05, + "loss": 3.9372, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.63703424414769e-05, + "loss": 3.9392, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636195649396638e-05, + "loss": 3.9344, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635358692525959e-05, + "loss": 3.9331, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634520097774907e-05, + "loss": 3.9433, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633681503023855e-05, + "loss": 3.9355, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632842908272803e-05, + "loss": 3.9488, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632004313521751e-05, + "loss": 3.9256, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631165718770699e-05, + "loss": 3.9364, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303271240196475e-05, + "loss": 3.9325, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294901671489684e-05, + "loss": 3.9283, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286515723979164e-05, + "loss": 3.9312, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278129776468644e-05, + "loss": 3.9253, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626974382895812e-05, + "loss": 3.9216, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626137426025133e-05, + "loss": 3.9274, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625298831274081e-05, + "loss": 3.9254, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9593703746795654, + "eval_runtime": 320.1607, + "eval_samples_per_second": 1191.873, + "eval_steps_per_second": 37.247, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624460236523029e-05, + "loss": 3.9267, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236216417719766e-05, + "loss": 3.9158, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227830470209246e-05, + "loss": 3.9321, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621946090150246e-05, + "loss": 3.9244, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621107495399194e-05, + "loss": 3.9444, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620268900648142e-05, + "loss": 3.9171, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.61943030589709e-05, + "loss": 3.9238, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618591711146038e-05, + "loss": 3.9084, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617753116394986e-05, + "loss": 3.926, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616914521643934e-05, + "loss": 3.9221, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616075926892882e-05, + "loss": 3.9155, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615238970022203e-05, + "loss": 3.9228, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614400375271151e-05, + "loss": 3.9106, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613561780520099e-05, + "loss": 3.9223, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612723185769047e-05, + "loss": 3.9074, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611886228898368e-05, + "loss": 3.9052, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611047634147316e-05, + "loss": 3.9094, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610209039396265e-05, + "loss": 3.9141, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609370444645213e-05, + "loss": 3.9097, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085334877745336e-05, + "loss": 3.9284, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076948930234816e-05, + "loss": 3.9101, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068562982724296e-05, + "loss": 3.9195, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060177035213776e-05, + "loss": 3.9102, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051791087703256e-05, + "loss": 3.9171, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043421518996465e-05, + "loss": 3.9085, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035035571485945e-05, + "loss": 3.9153, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026649623975425e-05, + "loss": 3.9073, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018263676464904e-05, + "loss": 3.9032, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009894107758114e-05, + "loss": 3.8995, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60015081602476e-05, + "loss": 3.9082, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599312221273708e-05, + "loss": 3.9122, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598473626522656e-05, + "loss": 3.9118, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597635031771604e-05, + "loss": 3.9205, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.9068, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595959480149873e-05, + "loss": 3.9036, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595120885398821e-05, + "loss": 3.9084, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.9088, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.8918, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592605101145665e-05, + "loss": 3.8886, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591768144274986e-05, + "loss": 3.8944, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590929549523934e-05, + "loss": 3.9021, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.9043, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.58925236002183e-05, + "loss": 3.9019, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884137652707785e-05, + "loss": 3.8894, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587575170519726e-05, + "loss": 3.9038, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586736575768674e-05, + "loss": 3.8976, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585897981017622e-05, + "loss": 3.894, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585061024146943e-05, + "loss": 3.8865, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584224067276264e-05, + "loss": 3.8761, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583385472525212e-05, + "loss": 3.9142, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.58254687777416e-05, + "loss": 3.9028, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817082830231076e-05, + "loss": 3.8936, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580871326152429e-05, + "loss": 3.8942, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580032731401377e-05, + "loss": 3.8961, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579194136650325e-05, + "loss": 3.8807, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578355541899273e-05, + "loss": 3.8966, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577516947148221e-05, + "loss": 3.882, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576679990277543e-05, + "loss": 3.8946, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.57584139552649e-05, + "loss": 3.9082, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575002800775438e-05, + "loss": 3.8864, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574164206024386e-05, + "loss": 3.8737, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573325611273334e-05, + "loss": 3.9029, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572487016522282e-05, + "loss": 3.8694, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571650059651603e-05, + "loss": 3.88, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570811464900551e-05, + "loss": 3.8978, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569972870149499e-05, + "loss": 3.89, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691342753984476e-05, + "loss": 3.8799, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682973185277685e-05, + "loss": 3.8763, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674587237767165e-05, + "loss": 3.8714, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666201290256645e-05, + "loss": 3.8772, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657815342746125e-05, + "loss": 3.8912, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649445774039334e-05, + "loss": 3.8758, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641059826528814e-05, + "loss": 3.8917, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632673879018294e-05, + "loss": 3.887, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624287931507774e-05, + "loss": 3.8945, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561591836280098e-05, + "loss": 3.8767, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560753241529046e-05, + "loss": 3.8804, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559914646777994e-05, + "loss": 3.8874, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559076052026943e-05, + "loss": 3.8749, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558239095156264e-05, + "loss": 3.8868, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557400500405212e-05, + "loss": 3.8786, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.55656190565416e-05, + "loss": 3.8784, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.8822, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554884716152056e-05, + "loss": 3.8667, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554047759281377e-05, + "loss": 3.8749, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553209164530325e-05, + "loss": 3.8786, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552370569779273e-05, + "loss": 3.8814, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551531975028221e-05, + "loss": 3.8715, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550693380277169e-05, + "loss": 3.8766, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.54985642340649e-05, + "loss": 3.8692, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5490178286554384e-05, + "loss": 3.8645, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481792339043864e-05, + "loss": 3.8658, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473406391533343e-05, + "loss": 3.8729, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546503682282655e-05, + "loss": 3.884, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545665087531603e-05, + "loss": 3.8854, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544826492780551e-05, + "loss": 3.8753, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543987898029499e-05, + "loss": 3.8639, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543149303278447e-05, + "loss": 3.8693, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542312346407768e-05, + "loss": 3.8745, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541473751656716e-05, + "loss": 3.8786, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540635156905664e-05, + "loss": 3.8775, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539796562154612e-05, + "loss": 3.8706, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538959605283933e-05, + "loss": 3.8615, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538121010532882e-05, + "loss": 3.8846, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.53728241578183e-05, + "loss": 3.8542, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536443821030778e-05, + "loss": 3.8714, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8601, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8705, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339296746579946e-05, + "loss": 3.8619, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330910799069426e-05, + "loss": 3.8684, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322524851558906e-05, + "loss": 3.8615, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.8624, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.8665, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297383387831075e-05, + "loss": 3.8607, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.877, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528062787161377e-05, + "loss": 3.8776, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.8724, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.8615, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.861, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524710046037542e-05, + "loss": 3.8594, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.52387145128649e-05, + "loss": 3.8605, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523032856535438e-05, + "loss": 3.8719, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522194261784386e-05, + "loss": 3.848, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521355667033333e-05, + "loss": 3.8655, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520518710162655e-05, + "loss": 3.8628, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519680115411603e-05, + "loss": 3.8697, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518841520660551e-05, + "loss": 3.8542, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5180045637898725e-05, + "loss": 3.8624, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171659690388204e-05, + "loss": 3.8579, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163273742877684e-05, + "loss": 3.8702, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515488779536716e-05, + "loss": 3.8645, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146518226660373e-05, + "loss": 3.8712, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5138132279149853e-05, + "loss": 3.8475, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129746331639333e-05, + "loss": 3.8646, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121360384128807e-05, + "loss": 3.8655, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511299081542202e-05, + "loss": 3.8547, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.51046048679115e-05, + "loss": 3.8613, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096218920400976e-05, + "loss": 3.8702, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508783297289046e-05, + "loss": 3.8621, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507944702537994e-05, + "loss": 3.8769, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507107745667316e-05, + "loss": 3.8509, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506269150916263e-05, + "loss": 3.8642, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505430556165211e-05, + "loss": 3.8531, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504591961414159e-05, + "loss": 3.8555, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.50375500454348e-05, + "loss": 3.8588, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502916409792428e-05, + "loss": 3.8521, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502077815041376e-05, + "loss": 3.8509, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012408581706976e-05, + "loss": 3.8512, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500402263419645e-05, + "loss": 3.8541, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.917726993560791, + "eval_runtime": 316.9205, + "eval_samples_per_second": 1204.059, + "eval_steps_per_second": 37.628, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499563668668593e-05, + "loss": 3.8512, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987250739175416e-05, + "loss": 3.8443, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978864791664896e-05, + "loss": 3.8611, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970478844154376e-05, + "loss": 3.8527, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962092896643856e-05, + "loss": 3.8695, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953706949133336e-05, + "loss": 3.8503, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945321001622816e-05, + "loss": 3.8525, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936935054112296e-05, + "loss": 3.8392, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928549106601776e-05, + "loss": 3.853, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920179537894985e-05, + "loss": 3.8507, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911793590384465e-05, + "loss": 3.8482, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903407642873945e-05, + "loss": 3.8493, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895038074167154e-05, + "loss": 3.8386, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886652126656634e-05, + "loss": 3.8529, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878266179146114e-05, + "loss": 3.8366, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698802316356e-05, + "loss": 3.8353, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486149428412508e-05, + "loss": 3.838, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485310833661456e-05, + "loss": 3.8466, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484472238910404e-05, + "loss": 3.8391, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483633644159352e-05, + "loss": 3.8573, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482796687288673e-05, + "loss": 3.8426, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481958092537621e-05, + "loss": 3.8525, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481119497786569e-05, + "loss": 3.8416, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480280903035516e-05, + "loss": 3.8455, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479442308284464e-05, + "loss": 3.8402, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478605351413786e-05, + "loss": 3.8482, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477766756662734e-05, + "loss": 3.8392, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476928161911682e-05, + "loss": 3.8387, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.47608956716063e-05, + "loss": 3.8305, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752526102899514e-05, + "loss": 3.8399, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744140155388994e-05, + "loss": 3.8454, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473575420787847e-05, + "loss": 3.8458, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472736826036795e-05, + "loss": 3.8487, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471899869166116e-05, + "loss": 3.8361, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710612744150636e-05, + "loss": 3.8379, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702226796640116e-05, + "loss": 3.846, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693840849129596e-05, + "loss": 3.8433, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468547128042281e-05, + "loss": 3.8223, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677085332912285e-05, + "loss": 3.8286, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466869938540177e-05, + "loss": 3.8277, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466031343789125e-05, + "loss": 3.8316, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465194386918447e-05, + "loss": 3.8423, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464355792167394e-05, + "loss": 3.8332, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463517197416342e-05, + "loss": 3.8279, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.46267860266529e-05, + "loss": 3.8358, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461841645794611e-05, + "loss": 3.8293, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461003051043559e-05, + "loss": 3.8322, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460164456292507e-05, + "loss": 3.8246, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459325861541455e-05, + "loss": 3.8067, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458487266790403e-05, + "loss": 3.8514, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457650309919724e-05, + "loss": 3.837, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568117151686725e-05, + "loss": 3.8337, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559731204176205e-05, + "loss": 3.8281, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551361635469415e-05, + "loss": 3.8294, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542975687958895e-05, + "loss": 3.8167, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534589740448374e-05, + "loss": 3.8302, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526203792937854e-05, + "loss": 3.8228, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517817845427334e-05, + "loss": 3.8281, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509431897916814e-05, + "loss": 3.8432, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501045950406294e-05, + "loss": 3.8224, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492660002895774e-05, + "loss": 3.8139, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448429043418898e-05, + "loss": 3.8387, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447590448667846e-05, + "loss": 3.8075, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446751853916794e-05, + "loss": 3.82, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445913259165742e-05, + "loss": 3.8307, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445076302295064e-05, + "loss": 3.8277, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444237707544012e-05, + "loss": 3.8187, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.44339911279296e-05, + "loss": 3.8162, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442562155922281e-05, + "loss": 3.806, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441723561171229e-05, + "loss": 3.8156, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440884966420177e-05, + "loss": 3.8274, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440046371669125e-05, + "loss": 3.8183, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439209414798446e-05, + "loss": 3.8258, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438370820047394e-05, + "loss": 3.8259, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437532225296342e-05, + "loss": 3.8354, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669363054529e-05, + "loss": 3.8147, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435856673674611e-05, + "loss": 3.8166, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435018078923559e-05, + "loss": 3.826, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434179484172507e-05, + "loss": 3.8113, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433340889421455e-05, + "loss": 3.83, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432503932550776e-05, + "loss": 3.8182, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431665337799724e-05, + "loss": 3.8171, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430826743048672e-05, + "loss": 3.8245, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.42998814829762e-05, + "loss": 3.8049, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429149553546568e-05, + "loss": 3.8117, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428312596675889e-05, + "loss": 3.8155, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427474001924837e-05, + "loss": 3.8252, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426635407173785e-05, + "loss": 3.8093, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425796812422733e-05, + "loss": 3.8168, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249598555520546e-05, + "loss": 3.8111, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241212608010026e-05, + "loss": 3.8098, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232826660499506e-05, + "loss": 3.8032, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224440712988986e-05, + "loss": 3.8152, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216071144282195e-05, + "loss": 3.8244, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207685196771675e-05, + "loss": 3.8225, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199299249261155e-05, + "loss": 3.8212, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190913301750635e-05, + "loss": 3.804, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182543733043844e-05, + "loss": 3.8103, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174157785533324e-05, + "loss": 3.8115, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165771838022804e-05, + "loss": 3.82, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157385890512284e-05, + "loss": 3.8185, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41490163218055e-05, + "loss": 3.8125, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414063037429498e-05, + "loss": 3.8052, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413224442678446e-05, + "loss": 3.8253, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412385847927394e-05, + "loss": 3.7991, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411548891056715e-05, + "loss": 3.8115, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410710296305663e-05, + "loss": 3.8024, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409871701554611e-05, + "loss": 3.8135, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409033106803559e-05, + "loss": 3.8024, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.40819614993288e-05, + "loss": 3.8114, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407357555181828e-05, + "loss": 3.8035, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406518960430776e-05, + "loss": 3.8075, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405680365679724e-05, + "loss": 3.8093, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048434088090454e-05, + "loss": 3.8048, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040048140579934e-05, + "loss": 3.8173, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403167857187314e-05, + "loss": 3.8205, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402329262436262e-05, + "loss": 3.8118, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149066768521e-05, + "loss": 3.8107, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400652072934158e-05, + "loss": 3.801, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399813478183106e-05, + "loss": 3.8058, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398974883432054e-05, + "loss": 3.8023, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981362886810016e-05, + "loss": 3.8182, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972976939299496e-05, + "loss": 3.7888, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396460737059271e-05, + "loss": 3.8082, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395622142308219e-05, + "loss": 3.8069, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394783547557167e-05, + "loss": 3.8122, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393944952806115e-05, + "loss": 3.8012, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393107995935437e-05, + "loss": 3.8073, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392269401184384e-05, + "loss": 3.8008, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391430806433332e-05, + "loss": 3.8109, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.39059221168228e-05, + "loss": 3.8116, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897552548116016e-05, + "loss": 3.8137, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388916660060549e-05, + "loss": 3.7958, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388078065309497e-05, + "loss": 3.8085, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387239470558445e-05, + "loss": 3.8127, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864025136877665e-05, + "loss": 3.8015, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855639189367145e-05, + "loss": 3.8047, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847253241856625e-05, + "loss": 3.8129, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838867294346105e-05, + "loss": 3.8052, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830497725639314e-05, + "loss": 3.8257, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822111778128794e-05, + "loss": 3.7962, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813725830618274e-05, + "loss": 3.8079, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805339883107754e-05, + "loss": 3.7983, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379697031440096e-05, + "loss": 3.8015, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378858436689044e-05, + "loss": 3.8064, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378019841937992e-05, + "loss": 3.7971, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.37718124718694e-05, + "loss": 3.8009, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376344290316262e-05, + "loss": 3.7875, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.37550569556521e-05, + "loss": 3.8051, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8928475379943848, + "eval_runtime": 302.8902, + "eval_samples_per_second": 1259.833, + "eval_steps_per_second": 39.371, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.374667100814158e-05, + "loss": 3.7998, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373828506063106e-05, + "loss": 3.7915, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372989911312054e-05, + "loss": 3.8059, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372151316561002e-05, + "loss": 3.8032, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.37131272180995e-05, + "loss": 3.8136, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370474127058898e-05, + "loss": 3.7949, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369635532307846e-05, + "loss": 3.7975, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368796937556794e-05, + "loss": 3.7864, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367959980686115e-05, + "loss": 3.8005, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367121385935063e-05, + "loss": 3.7981, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366282791184011e-05, + "loss": 3.7974, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365444196432959e-05, + "loss": 3.7909, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.36460723956228e-05, + "loss": 3.7909, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363768644811228e-05, + "loss": 3.7933, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362930050060176e-05, + "loss": 3.787, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362091455309124e-05, + "loss": 3.7797, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361252860558072e-05, + "loss": 3.7859, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.36041426580702e-05, + "loss": 3.794, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.3595756710559676e-05, + "loss": 3.787, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.3587370763049156e-05, + "loss": 3.8049, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357900119434237e-05, + "loss": 3.7932, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.3570615246831845e-05, + "loss": 3.8024, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562229299321325e-05, + "loss": 3.7893, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553843351810805e-05, + "loss": 3.7921, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354547378310402e-05, + "loss": 3.787, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.35370878355935e-05, + "loss": 3.7993, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352870188808298e-05, + "loss": 3.7884, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.352031594057246e-05, + "loss": 3.7868, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351194637186568e-05, + "loss": 3.78, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350356042435515e-05, + "loss": 3.789, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349517447684463e-05, + "loss": 3.7927, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348678852933411e-05, + "loss": 3.7962, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347841896062732e-05, + "loss": 3.796, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.34700330131168e-05, + "loss": 3.7928, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346164706560628e-05, + "loss": 3.7877, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345326111809576e-05, + "loss": 3.7959, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.3444891549388975e-05, + "loss": 3.7919, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436505601878455e-05, + "loss": 3.7758, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3428119654367935e-05, + "loss": 3.779, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.3419733706857415e-05, + "loss": 3.7745, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411364138150624e-05, + "loss": 3.7782, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402978190640104e-05, + "loss": 3.7938, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394592243129584e-05, + "loss": 3.7857, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3386206295619064e-05, + "loss": 3.7755, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337783672691227e-05, + "loss": 3.7858, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336945077940175e-05, + "loss": 3.7779, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.336106483189123e-05, + "loss": 3.7839, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335267888438071e-05, + "loss": 3.7734, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334430931567393e-05, + "loss": 3.7568, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333592336816341e-05, + "loss": 3.8026, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332753742065289e-05, + "loss": 3.7843, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331915147314237e-05, + "loss": 3.7876, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331078190443558e-05, + "loss": 3.775, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330241233572879e-05, + "loss": 3.7844, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3294026388218266e-05, + "loss": 3.7685, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285640440707746e-05, + "loss": 3.7784, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3277254493197226e-05, + "loss": 3.7779, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.3268868545686706e-05, + "loss": 3.7782, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.3260482598176186e-05, + "loss": 3.797, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.3252096650665666e-05, + "loss": 3.7735, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.3243710703155146e-05, + "loss": 3.764, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323534113444836e-05, + "loss": 3.7907, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322695518693784e-05, + "loss": 3.7582, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321856923942732e-05, + "loss": 3.7678, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.32101832919168e-05, + "loss": 3.7852, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320181372321001e-05, + "loss": 3.7817, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319342777569949e-05, + "loss": 3.766, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318504182818897e-05, + "loss": 3.773, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317665588067845e-05, + "loss": 3.7558, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316828631197166e-05, + "loss": 3.7705, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315990036446114e-05, + "loss": 3.7786, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315151441695062e-05, + "loss": 3.7666, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3143144848243836e-05, + "loss": 3.7792, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.3134758900733316e-05, + "loss": 3.7771, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.3126372953222796e-05, + "loss": 3.7887, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.3117987005712276e-05, + "loss": 3.7657, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109617437005485e-05, + "loss": 3.7736, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101231489494965e-05, + "loss": 3.7784, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.3092845541984445e-05, + "loss": 3.7641, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.3084459594473925e-05, + "loss": 3.7786, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.3076090025767134e-05, + "loss": 3.7733, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067704078256614e-05, + "loss": 3.7698, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.3059318130746094e-05, + "loss": 3.7798, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.3050932183235574e-05, + "loss": 3.7597, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304256261452879e-05, + "loss": 3.7627, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303417666701827e-05, + "loss": 3.771, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302579071950775e-05, + "loss": 3.7747, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.301740477199723e-05, + "loss": 3.7649, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300903520329044e-05, + "loss": 3.7683, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300064925577992e-05, + "loss": 3.7598, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.29922633082694e-05, + "loss": 3.7661, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298387736075888e-05, + "loss": 3.7587, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297550779205209e-05, + "loss": 3.7669, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296712184454157e-05, + "loss": 3.7812, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295873589703105e-05, + "loss": 3.7724, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295034994952053e-05, + "loss": 3.774, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294198038081374e-05, + "loss": 3.76, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293359443330322e-05, + "loss": 3.7637, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.29252084857927e-05, + "loss": 3.7651, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291682253828218e-05, + "loss": 3.7767, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290845296957539e-05, + "loss": 3.7683, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290006702206487e-05, + "loss": 3.7726, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289168107455435e-05, + "loss": 3.7597, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288329512704383e-05, + "loss": 3.7765, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287492555833704e-05, + "loss": 3.7561, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286653961082652e-05, + "loss": 3.7673, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2858153663316e-05, + "loss": 3.7539, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284976771580548e-05, + "loss": 3.7721, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.28413981470987e-05, + "loss": 3.7607, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283301219958818e-05, + "loss": 3.7631, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282462625207766e-05, + "loss": 3.7592, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281624030456714e-05, + "loss": 3.7628, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.2807870735860346e-05, + "loss": 3.7633, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.2799484788349826e-05, + "loss": 3.7623, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.2791098840839306e-05, + "loss": 3.7706, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.2782729272132515e-05, + "loss": 3.774, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.2774343324621995e-05, + "loss": 3.7669, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2765957377111475e-05, + "loss": 3.7701, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.2757571429600955e-05, + "loss": 3.755, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.2749185482090435e-05, + "loss": 3.7593, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.2740799534579915e-05, + "loss": 3.7618, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2732413587069394e-05, + "loss": 3.7696, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272404401836261e-05, + "loss": 3.7455, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.271565807085209e-05, + "loss": 3.7638, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270727212334157e-05, + "loss": 3.7656, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269888617583105e-05, + "loss": 3.7628, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.269051660712426e-05, + "loss": 3.7591, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268213065961374e-05, + "loss": 3.7663, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267374471210322e-05, + "loss": 3.7567, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.26653587645927e-05, + "loss": 3.7689, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265698919588591e-05, + "loss": 3.766, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264860324837539e-05, + "loss": 3.7703, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264021730086487e-05, + "loss": 3.7483, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263183135335435e-05, + "loss": 3.7645, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.2623461784647564e-05, + "loss": 3.7675, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.2615075837137044e-05, + "loss": 3.7568, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.2606689889626524e-05, + "loss": 3.7614, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.2598303942116e-05, + "loss": 3.7678, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258993437340921e-05, + "loss": 3.7648, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258154842589869e-05, + "loss": 3.7768, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257316247838817e-05, + "loss": 3.7557, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.2564776530877646e-05, + "loss": 3.7604, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255640696217086e-05, + "loss": 3.7568, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254802101466034e-05, + "loss": 3.7599, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253963506714982e-05, + "loss": 3.7569, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.25312491196393e-05, + "loss": 3.7548, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252287955093252e-05, + "loss": 3.7608, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.2514493603422e-05, + "loss": 3.7444, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250610765591147e-05, + "loss": 3.7636, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8769750595092773, + "eval_runtime": 303.6628, + "eval_samples_per_second": 1256.627, + "eval_steps_per_second": 39.271, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.249772170840095e-05, + "loss": 3.7602, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.248935213969417e-05, + "loss": 3.7495, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.248096619218364e-05, + "loss": 3.7591, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.247258024467312e-05, + "loss": 3.758, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.24641942971626e-05, + "loss": 3.7721, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.2455824728455816e-05, + "loss": 3.7538, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.2447438780945296e-05, + "loss": 3.7574, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.2439052833434776e-05, + "loss": 3.7439, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.2430666885924255e-05, + "loss": 3.7588, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.242229731721747e-05, + "loss": 3.7555, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.2413911369706945e-05, + "loss": 3.7552, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.2405525422196424e-05, + "loss": 3.7494, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.239715585348964e-05, + "loss": 3.7483, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.2388769905979114e-05, + "loss": 3.7514, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.2380383958468593e-05, + "loss": 3.7493, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.2371998010958073e-05, + "loss": 3.7368, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.2363612063447553e-05, + "loss": 3.7433, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.235522611593703e-05, + "loss": 3.7509, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.234684016842651e-05, + "loss": 3.7469, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233845422091599e-05, + "loss": 3.7606, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.233008465220921e-05, + "loss": 3.7543, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.232169870469869e-05, + "loss": 3.7616, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.231331275718817e-05, + "loss": 3.7436, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.230492680967765e-05, + "loss": 3.7519, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.229655724097086e-05, + "loss": 3.7479, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.228817129346034e-05, + "loss": 3.7573, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.227978534594982e-05, + "loss": 3.7454, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.22713993984393e-05, + "loss": 3.7494, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.226302982973251e-05, + "loss": 3.7416, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.225464388222199e-05, + "loss": 3.7443, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.224625793471147e-05, + "loss": 3.7484, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.223787198720095e-05, + "loss": 3.7597, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.222950241849416e-05, + "loss": 3.7564, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.222111647098364e-05, + "loss": 3.7518, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.221273052347312e-05, + "loss": 3.7451, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.22043445759626e-05, + "loss": 3.7488, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.219597500725581e-05, + "loss": 3.7528, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.218758905974529e-05, + "loss": 3.7374, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.217920311223477e-05, + "loss": 3.7343, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.217081716472425e-05, + "loss": 3.732, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.216244759601746e-05, + "loss": 3.7409, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.215406164850694e-05, + "loss": 3.7477, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.214567570099642e-05, + "loss": 3.7472, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.21372897534859e-05, + "loss": 3.7372, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.2128920184779116e-05, + "loss": 3.7426, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.2120534237268596e-05, + "loss": 3.7389, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.2112148289758076e-05, + "loss": 3.7453, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.2103762342247556e-05, + "loss": 3.7331, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.2095392773540765e-05, + "loss": 3.718, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.2087006826030245e-05, + "loss": 3.7587, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.2078620878519725e-05, + "loss": 3.7441, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.2070234931009205e-05, + "loss": 3.7505, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.2061865362302414e-05, + "loss": 3.7383, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.2053495793595623e-05, + "loss": 3.7419, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.2045109846085103e-05, + "loss": 3.7314, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.203672389857459e-05, + "loss": 3.7373, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.202833795106407e-05, + "loss": 3.7412, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.201995200355355e-05, + "loss": 3.7351, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.201156605604303e-05, + "loss": 3.7573, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.200318010853251e-05, + "loss": 3.7356, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.199479416102199e-05, + "loss": 3.7254, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.19864245923152e-05, + "loss": 3.751, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.197803864480468e-05, + "loss": 3.7201, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.196965269729416e-05, + "loss": 3.7223, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.196126674978364e-05, + "loss": 3.7495, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.195289718107685e-05, + "loss": 3.7439, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.194451123356633e-05, + "loss": 3.7245, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193612528605581e-05, + "loss": 3.7354, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.192773933854529e-05, + "loss": 3.7193, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.1919369769838504e-05, + "loss": 3.7311, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.1910983822327984e-05, + "loss": 3.7354, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.1902597874817464e-05, + "loss": 3.7307, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.1894211927306944e-05, + "loss": 3.7395, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188584235860015e-05, + "loss": 3.7381, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.187745641108963e-05, + "loss": 3.747, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186907046357911e-05, + "loss": 3.7297, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.186070089487232e-05, + "loss": 3.7351, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.18523149473618e-05, + "loss": 3.7382, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.184392899985128e-05, + "loss": 3.7273, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.183554305234076e-05, + "loss": 3.7397, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.182717348363398e-05, + "loss": 3.7368, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.181878753612346e-05, + "loss": 3.7273, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.181040158861294e-05, + "loss": 3.7461, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.180201564110242e-05, + "loss": 3.7199, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.1793646072395626e-05, + "loss": 3.7231, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.1785260124885106e-05, + "loss": 3.7345, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.1776874177374586e-05, + "loss": 3.7359, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.1768488229864066e-05, + "loss": 3.7281, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.1760118661157275e-05, + "loss": 3.7324, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.1751732713646755e-05, + "loss": 3.7178, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.1743346766136235e-05, + "loss": 3.7282, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.1734960818625715e-05, + "loss": 3.7217, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.1726574871115195e-05, + "loss": 3.7323, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.1718188923604675e-05, + "loss": 3.7407, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.1709802976094155e-05, + "loss": 3.7344, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.1701417028583635e-05, + "loss": 3.7368, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.1693047459876844e-05, + "loss": 3.7227, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.1684661512366324e-05, + "loss": 3.7268, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.1676275564855804e-05, + "loss": 3.7245, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.1667889617345284e-05, + "loss": 3.7402, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.165952004863849e-05, + "loss": 3.7312, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.165113410112797e-05, + "loss": 3.7366, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.164274815361745e-05, + "loss": 3.7201, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.163437858491067e-05, + "loss": 3.736, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.162599263740015e-05, + "loss": 3.7238, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.161760668988963e-05, + "loss": 3.7292, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.160922074237911e-05, + "loss": 3.7156, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160085117367232e-05, + "loss": 3.7337, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.15924652261618e-05, + "loss": 3.7215, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.158407927865128e-05, + "loss": 3.7287, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.157569333114076e-05, + "loss": 3.7172, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.156732376243397e-05, + "loss": 3.7305, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.155893781492345e-05, + "loss": 3.724, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.155055186741293e-05, + "loss": 3.7223, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.154216591990241e-05, + "loss": 3.737, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.153379635119562e-05, + "loss": 3.7367, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.15254104036851e-05, + "loss": 3.7317, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.151702445617458e-05, + "loss": 3.7282, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.150863850866406e-05, + "loss": 3.7214, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.150026893995727e-05, + "loss": 3.7227, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.149188299244675e-05, + "loss": 3.7246, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.148349704493623e-05, + "loss": 3.7288, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.147511109742571e-05, + "loss": 3.7123, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.146674152871892e-05, + "loss": 3.7269, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.14583555812084e-05, + "loss": 3.7277, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.144996963369788e-05, + "loss": 3.7277, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.144158368618736e-05, + "loss": 3.7245, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.1433214117480576e-05, + "loss": 3.7259, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.1424828169970056e-05, + "loss": 3.7212, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.1416442222459536e-05, + "loss": 3.7345, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.1408056274949016e-05, + "loss": 3.7317, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.1399686706242225e-05, + "loss": 3.7304, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.1391300758731705e-05, + "loss": 3.7137, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.1382914811221185e-05, + "loss": 3.7294, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.1374528863710665e-05, + "loss": 3.7289, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.1366159295003874e-05, + "loss": 3.7198, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.1357773347493354e-05, + "loss": 3.7281, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.1349387399982834e-05, + "loss": 3.7292, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.1341001452472314e-05, + "loss": 3.7274, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.133263188376553e-05, + "loss": 3.7432, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.132424593625501e-05, + "loss": 3.7198, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.131585998874449e-05, + "loss": 3.7279, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.130747404123397e-05, + "loss": 3.7248, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.129910447252718e-05, + "loss": 3.7245, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.129073490382039e-05, + "loss": 3.7185, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.128234895630987e-05, + "loss": 3.716, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.127396300879935e-05, + "loss": 3.7236, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.126557706128883e-05, + "loss": 3.71, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.125719111377831e-05, + "loss": 3.7283, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 3.8663697242736816, + "eval_runtime": 304.6221, + "eval_samples_per_second": 1252.67, + "eval_steps_per_second": 39.147, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.124880516626779e-05, + "loss": 3.7272, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.124041921875727e-05, + "loss": 3.713, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123203327124675e-05, + "loss": 3.7245, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122364732373623e-05, + "loss": 3.724, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215261376225714e-05, + "loss": 3.7345, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206891807518923e-05, + "loss": 3.7185, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1198505860008403e-05, + "loss": 3.7259, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119011991249788e-05, + "loss": 3.7133, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118173396498736e-05, + "loss": 3.7145, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117334801747684e-05, + "loss": 3.7263, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116496206996632e-05, + "loss": 3.719, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156576122455796e-05, + "loss": 3.7123, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114820655374901e-05, + "loss": 3.7208, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113982060623849e-05, + "loss": 3.7101, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113143465872797e-05, + "loss": 3.7091, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112304871121745e-05, + "loss": 3.7061, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111466276370693e-05, + "loss": 3.7071, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110627681619641e-05, + "loss": 3.717, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109789086868589e-05, + "loss": 3.7066, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108950492117537e-05, + "loss": 3.7298, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108113535246858e-05, + "loss": 3.7173, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107274940495806e-05, + "loss": 3.7269, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106436345744754e-05, + "loss": 3.7127, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105597750993702e-05, + "loss": 3.7143, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104760794123023e-05, + "loss": 3.7183, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103922199371971e-05, + "loss": 3.7188, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103083604620919e-05, + "loss": 3.7115, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102245009869867e-05, + "loss": 3.7168, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1014080529991886e-05, + "loss": 3.7043, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005694582481366e-05, + "loss": 3.7108, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997308634970846e-05, + "loss": 3.7138, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0988922687460326e-05, + "loss": 3.7221, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.0980553118753535e-05, + "loss": 3.7223, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0972167171243015e-05, + "loss": 3.7192, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963781223732495e-05, + "loss": 3.7121, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0955395276221975e-05, + "loss": 3.714, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.0947025707515184e-05, + "loss": 3.7201, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.0938639760004664e-05, + "loss": 3.705, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930253812494144e-05, + "loss": 3.7028, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921867864983624e-05, + "loss": 3.6989, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091349829627684e-05, + "loss": 3.7063, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090511234876632e-05, + "loss": 3.7087, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.08967264012558e-05, + "loss": 3.7152, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088834045374528e-05, + "loss": 3.7082, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087997088503849e-05, + "loss": 3.7063, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087158493752797e-05, + "loss": 3.7086, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086319899001745e-05, + "loss": 3.7135, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085482942131066e-05, + "loss": 3.6987, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084644347380014e-05, + "loss": 3.6846, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083805752628962e-05, + "loss": 3.7192, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.08296715787791e-05, + "loss": 3.7118, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082130201007231e-05, + "loss": 3.7185, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081291606256179e-05, + "loss": 3.7048, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.0804546493855e-05, + "loss": 3.7069, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079616054634448e-05, + "loss": 3.6982, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078777459883396e-05, + "loss": 3.7015, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077938865132344e-05, + "loss": 3.7116, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077100270381292e-05, + "loss": 3.697, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.07626167563024e-05, + "loss": 3.7255, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075423080879188e-05, + "loss": 3.7071, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074584486128136e-05, + "loss": 3.6858, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073747529257457e-05, + "loss": 3.7179, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072908934506405e-05, + "loss": 3.6899, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072070339755353e-05, + "loss": 3.6899, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071233382884675e-05, + "loss": 3.7168, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070394788133623e-05, + "loss": 3.7073, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069556193382571e-05, + "loss": 3.6923, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068717598631519e-05, + "loss": 3.7005, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678790038804667e-05, + "loss": 3.6878, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6994, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.7043, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653632196273106e-05, + "loss": 3.6983, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.0645262627566316e-05, + "loss": 3.7089, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636876680055796e-05, + "loss": 3.703, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0628490732545275e-05, + "loss": 3.7143, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620104785034755e-05, + "loss": 3.697, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.0611735216327965e-05, + "loss": 3.7049, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0603349268817444e-05, + "loss": 3.7031, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059496332130693e-05, + "loss": 3.6954, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0586577373796404e-05, + "loss": 3.7077, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057820780508962e-05, + "loss": 3.7043, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.05698218575791e-05, + "loss": 3.6926, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056145228887231e-05, + "loss": 3.7127, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055306634136179e-05, + "loss": 3.6867, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054468039385127e-05, + "loss": 3.6884, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053629444634075e-05, + "loss": 3.7035, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052790849883023e-05, + "loss": 3.701, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.05195225513197e-05, + "loss": 3.696, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051115298261292e-05, + "loss": 3.7041, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.05027670351024e-05, + "loss": 3.6876, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049438108759188e-05, + "loss": 3.6942, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048599514008136e-05, + "loss": 3.6923, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047760919257084e-05, + "loss": 3.6963, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046922324506032e-05, + "loss": 3.711, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.04608372975498e-05, + "loss": 3.7015, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045245135003928e-05, + "loss": 3.7077, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044408178133249e-05, + "loss": 3.6901, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043569583382197e-05, + "loss": 3.6937, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042730988631145e-05, + "loss": 3.6938, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041892393880093e-05, + "loss": 3.7052, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.0410554370094136e-05, + "loss": 3.6997, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040216842258362e-05, + "loss": 3.7045, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.03937824750731e-05, + "loss": 3.6934, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038539652756258e-05, + "loss": 3.6992, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037701058005206e-05, + "loss": 3.6962, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036862463254154e-05, + "loss": 3.6942, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036023868503102e-05, + "loss": 3.6844, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035186911632423e-05, + "loss": 3.7041, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034348316881371e-05, + "loss": 3.6894, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033509722130319e-05, + "loss": 3.6943, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032671127379267e-05, + "loss": 3.686, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031834170508588e-05, + "loss": 3.6996, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030997213637909e-05, + "loss": 3.693, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301586188868576e-05, + "loss": 3.6918, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293200241358056e-05, + "loss": 3.7029, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.7079, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.0276428346337016e-05, + "loss": 3.7038, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.0268042398826496e-05, + "loss": 3.6951, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.0259656451315976e-05, + "loss": 3.6888, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251270503805456e-05, + "loss": 3.6903, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242900935098665e-05, + "loss": 3.6929, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234514987588145e-05, + "loss": 3.6959, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0226129040077625e-05, + "loss": 3.6819, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217743092567105e-05, + "loss": 3.6955, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209373523860314e-05, + "loss": 3.7009, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0200987576349794e-05, + "loss": 3.6913, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0192601628839274e-05, + "loss": 3.6928, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.0184215681328754e-05, + "loss": 3.6995, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017584611262197e-05, + "loss": 3.6892, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016746016511145e-05, + "loss": 3.7003, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015907421760093e-05, + "loss": 3.6994, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015068827009041e-05, + "loss": 3.7019, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014231870138362e-05, + "loss": 3.6837, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.01339327538731e-05, + "loss": 3.6974, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012554680636258e-05, + "loss": 3.6984, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011716085885206e-05, + "loss": 3.6917, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010877491134154e-05, + "loss": 3.6961, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010038896383101e-05, + "loss": 3.6952, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009200301632049e-05, + "loss": 3.6981, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008361706880998e-05, + "loss": 3.7159, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007524750010319e-05, + "loss": 3.6858, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006686155259267e-05, + "loss": 3.6988, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005847560508215e-05, + "loss": 3.6941, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.005008965757163e-05, + "loss": 3.6936, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004173646766857e-05, + "loss": 3.6896, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003335052015805e-05, + "loss": 3.6855, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002496457264753e-05, + "loss": 3.6954, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0016578625137006e-05, + "loss": 3.6771, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0008192677626486e-05, + "loss": 3.6974, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.8597612380981445, + "eval_runtime": 317.2677, + "eval_samples_per_second": 1202.742, + "eval_steps_per_second": 37.587, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.9999806730115966e-05, + "loss": 3.6901, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.9991420782605445e-05, + "loss": 3.6847, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998303483509493e-05, + "loss": 3.6931, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997466526638814e-05, + "loss": 3.6936, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996627931887762e-05, + "loss": 3.7037, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995790975017084e-05, + "loss": 3.69, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994952380266031e-05, + "loss": 3.6977, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.994113785514979e-05, + "loss": 3.6821, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.993275190763927e-05, + "loss": 3.6846, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992436596012875e-05, + "loss": 3.6975, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991598001261823e-05, + "loss": 3.6877, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990759406510771e-05, + "loss": 3.6812, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989922449640092e-05, + "loss": 3.6941, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.98908385488904e-05, + "loss": 3.679, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.9882452601379886e-05, + "loss": 3.6825, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.9874066653869366e-05, + "loss": 3.6704, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.9865680706358846e-05, + "loss": 3.6817, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.9857294758848326e-05, + "loss": 3.6905, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.9848908811337806e-05, + "loss": 3.6762, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.9840539242631015e-05, + "loss": 3.6963, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.9832153295120495e-05, + "loss": 3.6917, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.9823767347609975e-05, + "loss": 3.6958, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.9815381400099455e-05, + "loss": 3.6849, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.9806995452588935e-05, + "loss": 3.6873, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.9798609505078415e-05, + "loss": 3.6881, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.9790223557567895e-05, + "loss": 3.6891, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.978183761005737e-05, + "loss": 3.6796, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.9773468041350584e-05, + "loss": 3.6887, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976508209384007e-05, + "loss": 3.6748, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.975669614632955e-05, + "loss": 3.6821, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.9748310198819023e-05, + "loss": 3.6835, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.973994063011224e-05, + "loss": 3.6897, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973155468260172e-05, + "loss": 3.695, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.97231687350912e-05, + "loss": 3.6942, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971478278758067e-05, + "loss": 3.6777, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970641321887389e-05, + "loss": 3.687, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.969802727136337e-05, + "loss": 3.6924, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.968964132385284e-05, + "loss": 3.6714, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968125537634232e-05, + "loss": 3.676, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967288580763554e-05, + "loss": 3.6713, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.9664499860125024e-05, + "loss": 3.6728, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.96561139126145e-05, + "loss": 3.6817, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964772796510398e-05, + "loss": 3.687, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.963935839639719e-05, + "loss": 3.6785, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963097244888667e-05, + "loss": 3.6777, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.9622586501376146e-05, + "loss": 3.6772, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.9614200553865626e-05, + "loss": 3.688, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.960583098515884e-05, + "loss": 3.6685, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.9597445037648315e-05, + "loss": 3.6593, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.9589059090137795e-05, + "loss": 3.6896, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.958068952143101e-05, + "loss": 3.6816, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957230357392049e-05, + "loss": 3.6886, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956391762640997e-05, + "loss": 3.6765, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955554805770319e-05, + "loss": 3.6775, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954716211019267e-05, + "loss": 3.672, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953877616268215e-05, + "loss": 3.6752, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953039021517162e-05, + "loss": 3.6852, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.95220042676611e-05, + "loss": 3.6674, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951361832015058e-05, + "loss": 3.6981, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950523237264006e-05, + "loss": 3.6768, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949686280393327e-05, + "loss": 3.6578, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948847685642275e-05, + "loss": 3.6888, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.948009090891223e-05, + "loss": 3.6697, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947170496140171e-05, + "loss": 3.6579, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.9463335392694925e-05, + "loss": 3.6845, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.9454949445184404e-05, + "loss": 3.6812, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.9446563497673884e-05, + "loss": 3.6675, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.9438177550163364e-05, + "loss": 3.6703, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.9429791602652844e-05, + "loss": 3.6573, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.9421405655142324e-05, + "loss": 3.669, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.9413019707631804e-05, + "loss": 3.6785, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.9404633760121284e-05, + "loss": 3.6702, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939626419141449e-05, + "loss": 3.6761, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.938787824390397e-05, + "loss": 3.6727, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937949229639345e-05, + "loss": 3.6869, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937110634888293e-05, + "loss": 3.6707, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936273678017615e-05, + "loss": 3.6783, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935435083266563e-05, + "loss": 3.6728, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934596488515511e-05, + "loss": 3.6671, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933757893764459e-05, + "loss": 3.6828, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.93292093689378e-05, + "loss": 3.6746, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932083980023101e-05, + "loss": 3.6688, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.931245385272049e-05, + "loss": 3.6822, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930406790520997e-05, + "loss": 3.6593, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.929568195769945e-05, + "loss": 3.6639, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.928729601018893e-05, + "loss": 3.6738, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.9278926441482136e-05, + "loss": 3.6772, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.9270540493971616e-05, + "loss": 3.6621, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.92621545464611e-05, + "loss": 3.6771, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925376859895058e-05, + "loss": 3.6626, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924538265144006e-05, + "loss": 3.6653, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923699670392954e-05, + "loss": 3.6598, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922861075641902e-05, + "loss": 3.6699, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.6841, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.921185524020171e-05, + "loss": 3.6722, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.920346929269119e-05, + "loss": 3.6784, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919508334518067e-05, + "loss": 3.666, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918671377647388e-05, + "loss": 3.6658, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.917832782896336e-05, + "loss": 3.666, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.916994188145284e-05, + "loss": 3.6773, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.916155593394232e-05, + "loss": 3.6721, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.9153186365235536e-05, + "loss": 3.6742, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.9144800417725016e-05, + "loss": 3.6714, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.9136414470214496e-05, + "loss": 3.6707, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.9128028522703976e-05, + "loss": 3.6704, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.9119658953997185e-05, + "loss": 3.666, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.9111273006486665e-05, + "loss": 3.6585, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.9102887058976145e-05, + "loss": 3.6756, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.9094517490269354e-05, + "loss": 3.6641, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.9086131542758834e-05, + "loss": 3.6668, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.9077745595248314e-05, + "loss": 3.6652, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.9069359647737794e-05, + "loss": 3.6656, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.9060973700227274e-05, + "loss": 3.6686, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.9052587752716754e-05, + "loss": 3.6629, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.9044201805206234e-05, + "loss": 3.6778, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903583223649945e-05, + "loss": 3.6776, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.902744628898892e-05, + "loss": 3.675, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.90190603414784e-05, + "loss": 3.6673, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.901067439396788e-05, + "loss": 3.6675, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.900228844645736e-05, + "loss": 3.6624, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899390249894684e-05, + "loss": 3.6679, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898551655143632e-05, + "loss": 3.6717, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.89771306039258e-05, + "loss": 3.6557, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896876103521901e-05, + "loss": 3.6672, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.896037508770849e-05, + "loss": 3.6705, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.895198914019798e-05, + "loss": 3.6692, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.894360319268746e-05, + "loss": 3.6639, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.89352500027844e-05, + "loss": 3.6692, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892686405527388e-05, + "loss": 3.6614, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891847810776336e-05, + "loss": 3.6752, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.891009216025284e-05, + "loss": 3.6699, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890170621274232e-05, + "loss": 3.6799, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.8893336644035526e-05, + "loss": 3.6577, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.8884950696525006e-05, + "loss": 3.6684, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.8876564749014486e-05, + "loss": 3.6737, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.8868178801503966e-05, + "loss": 3.6657, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.8859792853993446e-05, + "loss": 3.6663, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885142328528666e-05, + "loss": 3.6699, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884303733777614e-05, + "loss": 3.6711, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.883465139026562e-05, + "loss": 3.6872, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.88262654427551e-05, + "loss": 3.6628, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881787949524458e-05, + "loss": 3.6724, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880949354773406e-05, + "loss": 3.6706, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880110760022354e-05, + "loss": 3.6642, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879273803151675e-05, + "loss": 3.6633, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878435208400623e-05, + "loss": 3.6599, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877596613649571e-05, + "loss": 3.6652, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876758018898519e-05, + "loss": 3.658, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.875919424147467e-05, + "loss": 3.6665, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.8546080589294434, + "eval_runtime": 306.281, + "eval_samples_per_second": 1245.885, + "eval_steps_per_second": 38.935, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.875080829396415e-05, + "loss": 3.6662, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874242234645363e-05, + "loss": 3.6574, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873403639894311e-05, + "loss": 3.6641, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872565045143259e-05, + "loss": 3.6715, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871726450392207e-05, + "loss": 3.6807, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.8708894935215286e-05, + "loss": 3.6634, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870050898770476e-05, + "loss": 3.6679, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869212304019424e-05, + "loss": 3.6585, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868373709268372e-05, + "loss": 3.6599, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.86753511451732e-05, + "loss": 3.6687, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866696519766268e-05, + "loss": 3.6657, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865857925015216e-05, + "loss": 3.6565, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6691, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.651, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.6542, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8625051838913814e-05, + "loss": 3.6428, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.8616665891403294e-05, + "loss": 3.6595, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8608279943892774e-05, + "loss": 3.6648, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.8599893996382254e-05, + "loss": 3.6502, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8591524427675463e-05, + "loss": 3.6692, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858313848016494e-05, + "loss": 3.6636, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857475253265442e-05, + "loss": 3.6703, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.85663665851439e-05, + "loss": 3.6605, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855798063763338e-05, + "loss": 3.6613, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854959469012286e-05, + "loss": 3.661, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854120874261234e-05, + "loss": 3.668, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853282279510182e-05, + "loss": 3.6485, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852445322639503e-05, + "loss": 3.6633, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851608365768825e-05, + "loss": 3.6486, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850769771017773e-05, + "loss": 3.6549, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849931176266721e-05, + "loss": 3.6605, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849092581515669e-05, + "loss": 3.6658, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848253986764617e-05, + "loss": 3.6604, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847415392013565e-05, + "loss": 3.6707, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846576797262512e-05, + "loss": 3.6541, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.84573820251146e-05, + "loss": 3.6606, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844901245640782e-05, + "loss": 3.6652, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.84406265088973e-05, + "loss": 3.6457, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843224056138677e-05, + "loss": 3.6493, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842385461387626e-05, + "loss": 3.65, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841548504516947e-05, + "loss": 3.6448, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.8407099097658946e-05, + "loss": 3.6546, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.8398713150148426e-05, + "loss": 3.6662, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.8390327202637906e-05, + "loss": 3.6508, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838195763393112e-05, + "loss": 3.6537, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.8373571686420595e-05, + "loss": 3.6521, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.8365185738910075e-05, + "loss": 3.6589, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835681617020329e-05, + "loss": 3.6427, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834843022269277e-05, + "loss": 3.6364, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.8340044275182244e-05, + "loss": 3.6647, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331658327671724e-05, + "loss": 3.6578, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832328875896494e-05, + "loss": 3.6667, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831490281145442e-05, + "loss": 3.6489, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8306533242747635e-05, + "loss": 3.6513, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.8298147295237115e-05, + "loss": 3.6466, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.8289761347726595e-05, + "loss": 3.6502, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828137540021607e-05, + "loss": 3.6648, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827298945270555e-05, + "loss": 3.636, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826460350519503e-05, + "loss": 3.6774, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825621755768451e-05, + "loss": 3.6546, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824783161017399e-05, + "loss": 3.6328, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.82394620414672e-05, + "loss": 3.6603, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823107609395668e-05, + "loss": 3.6451, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822269014644616e-05, + "loss": 3.6332, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821432057773937e-05, + "loss": 3.6581, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820593463022885e-05, + "loss": 3.6609, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819754868271833e-05, + "loss": 3.6396, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818916273520781e-05, + "loss": 3.6482, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818077678769729e-05, + "loss": 3.6305, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817239084018677e-05, + "loss": 3.6457, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816400489267625e-05, + "loss": 3.6522, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815563532396946e-05, + "loss": 3.6421, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814724937645894e-05, + "loss": 3.6573, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813886342894842e-05, + "loss": 3.6427, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.81304774814379e-05, + "loss": 3.6638, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812209153392738e-05, + "loss": 3.6447, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811370558641686e-05, + "loss": 3.6546, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810531963890634e-05, + "loss": 3.6481, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809693369139583e-05, + "loss": 3.6428, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808856412268904e-05, + "loss": 3.6556, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808017817517852e-05, + "loss": 3.6462, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071792227668e-05, + "loss": 3.6505, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.8063422658961207e-05, + "loss": 3.6541, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.8055036711450686e-05, + "loss": 3.6428, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8046650763940166e-05, + "loss": 3.6327, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8038264816429646e-05, + "loss": 3.6475, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029878868919126e-05, + "loss": 3.6556, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.80214929214086e-05, + "loss": 3.6374, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.8013123352701815e-05, + "loss": 3.6501, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.8004737405191295e-05, + "loss": 3.6394, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799635145768078e-05, + "loss": 3.6433, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.7987965510170255e-05, + "loss": 3.6378, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.7979579562659735e-05, + "loss": 3.6462, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.7971193615149215e-05, + "loss": 3.6545, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.7962807667638695e-05, + "loss": 3.6499, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7954421720128175e-05, + "loss": 3.6545, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.7946052151421384e-05, + "loss": 3.6418, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.7937666203910864e-05, + "loss": 3.6425, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792929663520407e-05, + "loss": 3.6432, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792091068769355e-05, + "loss": 3.6522, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791252474018303e-05, + "loss": 3.6478, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790413879267252e-05, + "loss": 3.6531, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.7895752845162e-05, + "loss": 3.6453, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788736689765148e-05, + "loss": 3.6431, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787899732894469e-05, + "loss": 3.6523, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787061138143417e-05, + "loss": 3.6412, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786222543392365e-05, + "loss": 3.6391, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785383948641313e-05, + "loss": 3.6497, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784545353890261e-05, + "loss": 3.6403, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783708397019582e-05, + "loss": 3.6423, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.78286980226853e-05, + "loss": 3.6372, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782031207517478e-05, + "loss": 3.6391, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781192612766426e-05, + "loss": 3.6479, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780354018015374e-05, + "loss": 3.639, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779515423264322e-05, + "loss": 3.6501, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.7786784663936433e-05, + "loss": 3.6535, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.7778398716425913e-05, + "loss": 3.6546, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777001276891539e-05, + "loss": 3.6434, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776162682140487e-05, + "loss": 3.6443, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775324087389435e-05, + "loss": 3.6378, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774487130518756e-05, + "loss": 3.6488, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773648535767704e-05, + "loss": 3.643, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772809941016652e-05, + "loss": 3.6334, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7719713462656e-05, + "loss": 3.6427, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771132751514548e-05, + "loss": 3.6446, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770295794643869e-05, + "loss": 3.648, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769457199892817e-05, + "loss": 3.6402, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768618605141765e-05, + "loss": 3.6432, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767780010390714e-05, + "loss": 3.6375, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766943053520035e-05, + "loss": 3.6534, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766104458768983e-05, + "loss": 3.6456, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765265864017931e-05, + "loss": 3.6529, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764427269266879e-05, + "loss": 3.636, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763588674515827e-05, + "loss": 3.6448, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762750079764774e-05, + "loss": 3.6517, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7619131228940956e-05, + "loss": 3.6421, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7610745281430436e-05, + "loss": 3.644, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760235933391991e-05, + "loss": 3.643, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759397338640939e-05, + "loss": 3.6509, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.7585587438898876e-05, + "loss": 3.6585, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.7577201491388356e-05, + "loss": 3.6439, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7568815543877836e-05, + "loss": 3.6445, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.7560429596367316e-05, + "loss": 3.6461, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.7552060027660525e-05, + "loss": 3.641, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7543674080150005e-05, + "loss": 3.6394, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7535288132639485e-05, + "loss": 3.6389, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.7526918563932694e-05, + "loss": 3.6391, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.7518532616422174e-05, + "loss": 3.6349, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.7510146668911654e-05, + "loss": 3.6435, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8529796600341797, + "eval_runtime": 307.004, + "eval_samples_per_second": 1242.951, + "eval_steps_per_second": 38.843, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.7501760721401134e-05, + "loss": 3.6409, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749339115269434e-05, + "loss": 3.6351, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748500520518383e-05, + "loss": 3.6427, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747661925767331e-05, + "loss": 3.6488, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746823331016279e-05, + "loss": 3.6564, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7459863741456e-05, + "loss": 3.6395, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745147779394548e-05, + "loss": 3.6481, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744309184643496e-05, + "loss": 3.6357, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743470589892444e-05, + "loss": 3.6358, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742631995141392e-05, + "loss": 3.6425, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741795038270713e-05, + "loss": 3.6453, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740956443519661e-05, + "loss": 3.6353, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.7401194866489816e-05, + "loss": 3.6432, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.7392808918979296e-05, + "loss": 3.6289, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738442297146878e-05, + "loss": 3.6333, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737603702395826e-05, + "loss": 3.6192, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736765107644774e-05, + "loss": 3.6387, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735926512893722e-05, + "loss": 3.6395, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.73508791814267e-05, + "loss": 3.6287, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734249323391618e-05, + "loss": 3.6437, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733412366520939e-05, + "loss": 3.6442, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732573771769887e-05, + "loss": 3.6486, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731735177018835e-05, + "loss": 3.6361, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.730896582267783e-05, + "loss": 3.6367, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.730057987516731e-05, + "loss": 3.6408, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729219392765679e-05, + "loss": 3.644, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728380798014627e-05, + "loss": 3.6267, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727542203263575e-05, + "loss": 3.6395, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726705246392897e-05, + "loss": 3.631, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725866651641845e-05, + "loss": 3.6281, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.725028056890793e-05, + "loss": 3.6372, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.72418946213974e-05, + "loss": 3.6414, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723350867388688e-05, + "loss": 3.6406, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722512272637636e-05, + "loss": 3.6463, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721675315766957e-05, + "loss": 3.6335, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720836721015905e-05, + "loss": 3.637, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719998126264853e-05, + "loss": 3.6448, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719159531513801e-05, + "loss": 3.6233, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718320936762749e-05, + "loss": 3.6262, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.717482342011697e-05, + "loss": 3.6308, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.7166453851410185e-05, + "loss": 3.6199, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.7158067903899665e-05, + "loss": 3.63, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.7149681956389145e-05, + "loss": 3.6458, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.7141296008878625e-05, + "loss": 3.6279, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.7132910061368105e-05, + "loss": 3.6309, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.7124524113857585e-05, + "loss": 3.6328, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.7116138166347065e-05, + "loss": 3.6368, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.7107752218836545e-05, + "loss": 3.619, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.7099382650129754e-05, + "loss": 3.6139, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.7090996702619234e-05, + "loss": 3.6383, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.7082610755108714e-05, + "loss": 3.6369, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.7074224807598194e-05, + "loss": 3.6469, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.7065838860087674e-05, + "loss": 3.6248, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705746929138088e-05, + "loss": 3.6271, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704908334387037e-05, + "loss": 3.6267, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704069739635985e-05, + "loss": 3.6248, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703231144884933e-05, + "loss": 3.6409, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702392550133881e-05, + "loss": 3.6118, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701555593263202e-05, + "loss": 3.6542, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.70071699851215e-05, + "loss": 3.6347, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699878403761098e-05, + "loss": 3.6135, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699039809010046e-05, + "loss": 3.6354, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698201214258993e-05, + "loss": 3.6217, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697362619507941e-05, + "loss": 3.6114, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696525662637263e-05, + "loss": 3.6365, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695687067886211e-05, + "loss": 3.6354, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694848473135159e-05, + "loss": 3.6177, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694009878384107e-05, + "loss": 3.6294, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693171283633055e-05, + "loss": 3.6081, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692332688882003e-05, + "loss": 3.6226, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691494094130951e-05, + "loss": 3.6249, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6906571372602716e-05, + "loss": 3.6254, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.6898185425092196e-05, + "loss": 3.6311, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.6889799477581676e-05, + "loss": 3.6227, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.6881413530071156e-05, + "loss": 3.6428, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.6873027582560636e-05, + "loss": 3.6229, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.6864658013853845e-05, + "loss": 3.6339, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6856272066343325e-05, + "loss": 3.6237, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.6847886118832805e-05, + "loss": 3.6197, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683950017132229e-05, + "loss": 3.6343, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.68311306026155e-05, + "loss": 3.625, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682274465510498e-05, + "loss": 3.6267, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.681435870759446e-05, + "loss": 3.6365, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680597276008394e-05, + "loss": 3.6213, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679760319137715e-05, + "loss": 3.6087, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678921724386663e-05, + "loss": 3.6232, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678083129635611e-05, + "loss": 3.6336, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677244534884559e-05, + "loss": 3.6156, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676405940133507e-05, + "loss": 3.6299, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675567345382455e-05, + "loss": 3.6204, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674728750631403e-05, + "loss": 3.6168, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673890155880351e-05, + "loss": 3.6166, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.6730531990096726e-05, + "loss": 3.6229, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.6722146042586206e-05, + "loss": 3.6377, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.6713760095075685e-05, + "loss": 3.625, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.6705374147565165e-05, + "loss": 3.6322, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.6696988200054645e-05, + "loss": 3.6218, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668860225254412e-05, + "loss": 3.6178, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.6680232683837334e-05, + "loss": 3.619, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.6671846736326814e-05, + "loss": 3.6299, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.6663460788816294e-05, + "loss": 3.6278, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665507484130577e-05, + "loss": 3.6297, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664668889379525e-05, + "loss": 3.625, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663830294628473e-05, + "loss": 3.6172, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.6629916998774214e-05, + "loss": 3.6315, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662154743006742e-05, + "loss": 3.6202, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.66131614825569e-05, + "loss": 3.6151, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660477553504638e-05, + "loss": 3.6256, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659638958753586e-05, + "loss": 3.6208, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658802001882907e-05, + "loss": 3.6207, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657963407131855e-05, + "loss": 3.6171, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657124812380803e-05, + "loss": 3.6198, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656286217629751e-05, + "loss": 3.6249, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655447622878699e-05, + "loss": 3.6223, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.65461066600802e-05, + "loss": 3.6256, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653772071256968e-05, + "loss": 3.6306, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652933476505916e-05, + "loss": 3.6331, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652094881754865e-05, + "loss": 3.6215, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651256287003813e-05, + "loss": 3.6227, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650419330133134e-05, + "loss": 3.6157, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649580735382082e-05, + "loss": 3.6233, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.64874214063103e-05, + "loss": 3.6225, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647903545879978e-05, + "loss": 3.6153, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.647064951128926e-05, + "loss": 3.6155, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.6462279942582466e-05, + "loss": 3.6257, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.6453893995071946e-05, + "loss": 3.6277, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.6445508047561426e-05, + "loss": 3.6155, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.6437122100050906e-05, + "loss": 3.6226, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.6428752531344115e-05, + "loss": 3.6199, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.64203665838336e-05, + "loss": 3.6268, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641198063632308e-05, + "loss": 3.6248, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640359468881256e-05, + "loss": 3.6327, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639522512010577e-05, + "loss": 3.6122, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638683917259525e-05, + "loss": 3.6234, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637845322508473e-05, + "loss": 3.6285, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637006727757421e-05, + "loss": 3.615, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636168133006369e-05, + "loss": 3.6231, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.63533117613569e-05, + "loss": 3.6261, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634492581384638e-05, + "loss": 3.6321, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633653986633586e-05, + "loss": 3.6354, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632815391882534e-05, + "loss": 3.6213, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631976797131482e-05, + "loss": 3.6234, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.6311398402608035e-05, + "loss": 3.6253, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.6303012455097515e-05, + "loss": 3.6189, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6294626507586995e-05, + "loss": 3.6187, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.6286240560076475e-05, + "loss": 3.6179, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277854612565955e-05, + "loss": 3.6143, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626946866505543e-05, + "loss": 3.6189, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6261099096348644e-05, + "loss": 3.6178, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.850759506225586, + "eval_runtime": 314.7366, + "eval_samples_per_second": 1212.414, + "eval_steps_per_second": 37.889, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.6252713148838124e-05, + "loss": 3.6177, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.6244327201327604e-05, + "loss": 3.6144, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623594125381708e-05, + "loss": 3.6228, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622755530630656e-05, + "loss": 3.6242, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621918573759977e-05, + "loss": 3.6335, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621079979008925e-05, + "loss": 3.6198, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620241384257873e-05, + "loss": 3.6253, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619402789506821e-05, + "loss": 3.6175, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618564194755769e-05, + "loss": 3.6122, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617725600004717e-05, + "loss": 3.6189, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616888643134038e-05, + "loss": 3.6282, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.616050048382986e-05, + "loss": 3.6098, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615213091512308e-05, + "loss": 3.6241, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614374496761255e-05, + "loss": 3.6062, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.613535902010203e-05, + "loss": 3.6095, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612697307259151e-05, + "loss": 3.6005, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611858712508099e-05, + "loss": 3.6172, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.611020117757048e-05, + "loss": 3.6153, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610181523005996e-05, + "loss": 3.6124, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609342928254944e-05, + "loss": 3.6148, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608504333503892e-05, + "loss": 3.6292, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.6076673766332126e-05, + "loss": 3.6226, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.6068287818821606e-05, + "loss": 3.6177, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.6059901871311086e-05, + "loss": 3.6139, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.6051515923800566e-05, + "loss": 3.6242, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.6043129976290046e-05, + "loss": 3.6189, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.6034744028779526e-05, + "loss": 3.6093, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.6026374460072735e-05, + "loss": 3.6199, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.6017988512562215e-05, + "loss": 3.6087, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6009602565051695e-05, + "loss": 3.606, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.6001216617541175e-05, + "loss": 3.6186, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5992830670030655e-05, + "loss": 3.6157, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598446110132387e-05, + "loss": 3.6251, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597607515381335e-05, + "loss": 3.6238, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596768920630283e-05, + "loss": 3.6092, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595930325879231e-05, + "loss": 3.6189, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595091731128179e-05, + "loss": 3.6217, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.5942547742575e-05, + "loss": 3.6051, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593416179506448e-05, + "loss": 3.6078, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592577584755396e-05, + "loss": 3.6022, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591738990004344e-05, + "loss": 3.601, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590900395253291e-05, + "loss": 3.6104, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590061800502239e-05, + "loss": 3.6255, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589224843631561e-05, + "loss": 3.6093, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588386248880509e-05, + "loss": 3.607, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587547654129457e-05, + "loss": 3.6152, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586709059378405e-05, + "loss": 3.613, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585870464627353e-05, + "loss": 3.6021, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.585033507756674e-05, + "loss": 3.5938, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584194913005622e-05, + "loss": 3.616, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.58335631825457e-05, + "loss": 3.6197, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582517723503518e-05, + "loss": 3.6209, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.5816807666328387e-05, + "loss": 3.6085, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.5808421718817867e-05, + "loss": 3.6058, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.5800035771307346e-05, + "loss": 3.6037, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579164982379683e-05, + "loss": 3.6046, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578326387628631e-05, + "loss": 3.6205, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577489430757952e-05, + "loss": 3.5957, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.5766508360069e-05, + "loss": 3.6289, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575812241255848e-05, + "loss": 3.6127, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574973646504796e-05, + "loss": 3.595, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574135051753744e-05, + "loss": 3.6117, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573298094883065e-05, + "loss": 3.6036, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572459500132013e-05, + "loss": 3.5919, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571620905380961e-05, + "loss": 3.6126, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570782310629909e-05, + "loss": 3.6152, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569943715878857e-05, + "loss": 3.5982, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569106759008179e-05, + "loss": 3.6096, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568268164257127e-05, + "loss": 3.5882, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567429569506075e-05, + "loss": 3.6036, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566590974755023e-05, + "loss": 3.6061, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.5657540178843436e-05, + "loss": 3.6063, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.5649154231332916e-05, + "loss": 3.6068, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.5640768283822396e-05, + "loss": 3.6041, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5632382336311876e-05, + "loss": 3.6205, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.5624012767605085e-05, + "loss": 3.6038, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.5615626820094565e-05, + "loss": 3.613, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.5607240872584045e-05, + "loss": 3.6049, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.5598854925073525e-05, + "loss": 3.6029, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.5590468977563005e-05, + "loss": 3.6156, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558209940885622e-05, + "loss": 3.6069, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.55737134613457e-05, + "loss": 3.6026, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556532751383518e-05, + "loss": 3.6144, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555694156632466e-05, + "loss": 3.6067, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554857199761787e-05, + "loss": 3.587, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.554018605010735e-05, + "loss": 3.6046, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553180010259683e-05, + "loss": 3.6089, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552341415508631e-05, + "loss": 3.599, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551504458637952e-05, + "loss": 3.6071, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.5506658638869e-05, + "loss": 3.6027, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549827269135848e-05, + "loss": 3.5954, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.548988674384796e-05, + "loss": 3.5998, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.5481517175141174e-05, + "loss": 3.6009, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5473131227630654e-05, + "loss": 3.6142, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5464745280120134e-05, + "loss": 3.6082, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5456359332609614e-05, + "loss": 3.6133, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5447973385099094e-05, + "loss": 3.5977, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5439587437588574e-05, + "loss": 3.6001, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543120149007805e-05, + "loss": 3.6031, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542283192137126e-05, + "loss": 3.6099, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541444597386074e-05, + "loss": 3.6069, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.5406060026350216e-05, + "loss": 3.6087, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5397674078839696e-05, + "loss": 3.602, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538930451013291e-05, + "loss": 3.5998, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538091856262239e-05, + "loss": 3.6106, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537253261511187e-05, + "loss": 3.6002, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536414666760135e-05, + "loss": 3.6018, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535577709889457e-05, + "loss": 3.6022, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534739115138405e-05, + "loss": 3.6011, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533900520387352e-05, + "loss": 3.603, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.5330619256363e-05, + "loss": 3.5944, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532223330885248e-05, + "loss": 3.597, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531386374014569e-05, + "loss": 3.6082, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530547779263517e-05, + "loss": 3.6026, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529709184512465e-05, + "loss": 3.6008, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528870589761413e-05, + "loss": 3.6101, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528031995010361e-05, + "loss": 3.6171, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5271950381396826e-05, + "loss": 3.6008, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.5263564433886305e-05, + "loss": 3.6002, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.5255178486375785e-05, + "loss": 3.6002, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.5246792538865265e-05, + "loss": 3.6052, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.5238422970158474e-05, + "loss": 3.5995, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5230037022647954e-05, + "loss": 3.5978, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.5221651075137434e-05, + "loss": 3.5965, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.5213265127626914e-05, + "loss": 3.608, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5204879180116394e-05, + "loss": 3.6006, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.5196509611409603e-05, + "loss": 3.5991, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518812366389908e-05, + "loss": 3.6064, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517973771638856e-05, + "loss": 3.6023, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517135176887805e-05, + "loss": 3.6029, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516298220017126e-05, + "loss": 3.6081, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515459625266074e-05, + "loss": 3.6107, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514621030515022e-05, + "loss": 3.5965, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.51378243576397e-05, + "loss": 3.6036, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512943841012918e-05, + "loss": 3.6082, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512106884142239e-05, + "loss": 3.5993, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511268289391187e-05, + "loss": 3.5977, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510429694640135e-05, + "loss": 3.6055, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509591099889083e-05, + "loss": 3.614, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508752505138031e-05, + "loss": 3.6148, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507915548267352e-05, + "loss": 3.6052, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5070769535163004e-05, + "loss": 3.6029, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062383587652484e-05, + "loss": 3.6062, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5053997640141964e-05, + "loss": 3.6035, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504562807143517e-05, + "loss": 3.5968, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503724212392465e-05, + "loss": 3.6027, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502885617641413e-05, + "loss": 3.5916, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502047022890361e-05, + "loss": 3.6012, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501210066019682e-05, + "loss": 3.5986, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8513965606689453, + "eval_runtime": 303.001, + "eval_samples_per_second": 1259.372, + "eval_steps_per_second": 39.356, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.50037147126863e-05, + "loss": 3.6051, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499532876517578e-05, + "loss": 3.589, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498694281766526e-05, + "loss": 3.6014, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497857324895847e-05, + "loss": 3.6092, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497018730144796e-05, + "loss": 3.6092, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496180135393744e-05, + "loss": 3.6082, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495341540642692e-05, + "loss": 3.6047, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.49450294589164e-05, + "loss": 3.5948, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4936659890209606e-05, + "loss": 3.5916, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.4928273942699086e-05, + "loss": 3.6041, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.4919887995188566e-05, + "loss": 3.5997, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.4911502047678046e-05, + "loss": 3.596, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.4903132478971255e-05, + "loss": 3.6058, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.4894746531460735e-05, + "loss": 3.5853, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.4886360583950215e-05, + "loss": 3.5917, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.4877974636439695e-05, + "loss": 3.5793, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.4869588688929175e-05, + "loss": 3.6001, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4861202741418655e-05, + "loss": 3.593, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4852816793908135e-05, + "loss": 3.5956, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.4844430846397615e-05, + "loss": 3.5978, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.4836044898887095e-05, + "loss": 3.6063, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.4827675330180304e-05, + "loss": 3.6038, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.4819289382669784e-05, + "loss": 3.5973, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.4810903435159264e-05, + "loss": 3.5976, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.4802517487648744e-05, + "loss": 3.6069, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.4794131540138224e-05, + "loss": 3.5987, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.4785745592627704e-05, + "loss": 3.5884, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477737602392091e-05, + "loss": 3.6009, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476899007641039e-05, + "loss": 3.5854, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476060412889988e-05, + "loss": 3.5922, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475221818138936e-05, + "loss": 3.5996, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.474384861268257e-05, + "loss": 3.5979, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473546266517205e-05, + "loss": 3.6017, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.472707671766153e-05, + "loss": 3.6056, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.471869077015101e-05, + "loss": 3.5914, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.471030482264049e-05, + "loss": 3.601, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.47019352539337e-05, + "loss": 3.6038, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469354930642318e-05, + "loss": 3.5865, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.468516335891266e-05, + "loss": 3.5906, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467677741140214e-05, + "loss": 3.5842, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.4668407842695347e-05, + "loss": 3.5862, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.466002189518483e-05, + "loss": 3.5924, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465163594767431e-05, + "loss": 3.6032, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464325000016379e-05, + "loss": 3.5881, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.4634880431457e-05, + "loss": 3.5911, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462649448394648e-05, + "loss": 3.596, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461810853643596e-05, + "loss": 3.5951, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460972258892544e-05, + "loss": 3.5838, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460135302021865e-05, + "loss": 3.573, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459296707270813e-05, + "loss": 3.593, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458458112519761e-05, + "loss": 3.6046, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457619517768709e-05, + "loss": 3.6028, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456780923017657e-05, + "loss": 3.5861, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455943966146978e-05, + "loss": 3.5866, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455105371395927e-05, + "loss": 3.5891, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454266776644875e-05, + "loss": 3.5791, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.453428181893823e-05, + "loss": 3.6084, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.4525912250231436e-05, + "loss": 3.5754, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.4517526302720916e-05, + "loss": 3.6096, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.4509140355210396e-05, + "loss": 3.5926, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.4500754407699876e-05, + "loss": 3.5784, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.4492368460189356e-05, + "loss": 3.5926, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.4483998891482565e-05, + "loss": 3.5881, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.4475612943972045e-05, + "loss": 3.5729, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.4467226996461525e-05, + "loss": 3.5945, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.4458841048951005e-05, + "loss": 3.5974, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445047148024422e-05, + "loss": 3.5815, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.44420855327337e-05, + "loss": 3.589, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443369958522318e-05, + "loss": 3.569, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442531363771266e-05, + "loss": 3.5863, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.441694406900587e-05, + "loss": 3.5842, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.440855812149535e-05, + "loss": 3.5903, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.440017217398483e-05, + "loss": 3.5862, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439178622647431e-05, + "loss": 3.5871, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438341665776752e-05, + "loss": 3.6022, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.4375030710257e-05, + "loss": 3.5855, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436664476274648e-05, + "loss": 3.5931, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435825881523596e-05, + "loss": 3.5871, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.4349889246529174e-05, + "loss": 3.5846, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.4341503299018654e-05, + "loss": 3.5951, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.4333117351508134e-05, + "loss": 3.5873, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432473140399761e-05, + "loss": 3.5911, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.431636183529082e-05, + "loss": 3.5916, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.43079758877803e-05, + "loss": 3.5912, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429958994026978e-05, + "loss": 3.566, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4291203992759256e-05, + "loss": 3.5897, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.4282818045248736e-05, + "loss": 3.5874, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427444847654195e-05, + "loss": 3.5805, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4266062529031425e-05, + "loss": 3.5891, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425767658152091e-05, + "loss": 3.5822, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424929063401039e-05, + "loss": 3.5795, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424090468649987e-05, + "loss": 3.5794, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.423253511779308e-05, + "loss": 3.5865, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.422414917028256e-05, + "loss": 3.5907, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421576322277204e-05, + "loss": 3.5915, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420737727526152e-05, + "loss": 3.594, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419900770655473e-05, + "loss": 3.5836, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419062175904421e-05, + "loss": 3.5822, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418223581153369e-05, + "loss": 3.5848, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417384986402317e-05, + "loss": 3.5927, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416548029531638e-05, + "loss": 3.587, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.4157094347805866e-05, + "loss": 3.5906, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.4148708400295346e-05, + "loss": 3.5839, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.4140322452784826e-05, + "loss": 3.5804, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.4131936505274306e-05, + "loss": 3.5928, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.4123566936567515e-05, + "loss": 3.5825, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.4115180989056995e-05, + "loss": 3.5806, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.4106795041546475e-05, + "loss": 3.5842, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.4098409094035955e-05, + "loss": 3.5841, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.4090039525329164e-05, + "loss": 3.5815, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.4081653577818644e-05, + "loss": 3.5807, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4073267630308124e-05, + "loss": 3.5769, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4064881682797603e-05, + "loss": 3.5879, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405651211409082e-05, + "loss": 3.5919, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.40481261665803e-05, + "loss": 3.5793, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403974021906978e-05, + "loss": 3.5928, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403135427155926e-05, + "loss": 3.596, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402298470285247e-05, + "loss": 3.5844, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401459875534195e-05, + "loss": 3.5832, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400621280783143e-05, + "loss": 3.582, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399782686032091e-05, + "loss": 3.5852, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398944091281039e-05, + "loss": 3.5805, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.39810713441036e-05, + "loss": 3.5795, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397268539659308e-05, + "loss": 3.5799, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396429944908256e-05, + "loss": 3.5884, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395591350157204e-05, + "loss": 3.5822, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394754393286525e-05, + "loss": 3.5865, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393915798535473e-05, + "loss": 3.5865, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.393077203784421e-05, + "loss": 3.5845, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392238609033369e-05, + "loss": 3.581, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.39140165216269e-05, + "loss": 3.5939, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390563057411638e-05, + "loss": 3.5906, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389724462660586e-05, + "loss": 3.5813, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388885867909534e-05, + "loss": 3.5808, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388047273158482e-05, + "loss": 3.5932, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387210316287803e-05, + "loss": 3.5795, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386371721536751e-05, + "loss": 3.5847, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.385533126785699e-05, + "loss": 3.5881, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384694532034647e-05, + "loss": 3.5985, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3838575751639687e-05, + "loss": 3.5921, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3830189804129167e-05, + "loss": 3.5935, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.3821803856618647e-05, + "loss": 3.5802, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.3813417909108126e-05, + "loss": 3.593, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.3805031961597606e-05, + "loss": 3.5825, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.3796662392890816e-05, + "loss": 3.5779, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.3788276445380295e-05, + "loss": 3.5844, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3779890497869775e-05, + "loss": 3.5748, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.3771504550359255e-05, + "loss": 3.5844, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.3763134981652464e-05, + "loss": 3.5791, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8508660793304443, + "eval_runtime": 304.5509, + "eval_samples_per_second": 1252.963, + "eval_steps_per_second": 39.156, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3754749034141944e-05, + "loss": 3.5929, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3746363086631424e-05, + "loss": 3.5752, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3737977139120904e-05, + "loss": 3.5827, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372959119161039e-05, + "loss": 3.5929, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.37212216229036e-05, + "loss": 3.5879, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371283567539308e-05, + "loss": 3.5946, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370444972788256e-05, + "loss": 3.5824, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369606378037203e-05, + "loss": 3.5804, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368767783286151e-05, + "loss": 3.5707, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367930826415473e-05, + "loss": 3.5886, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367092231664421e-05, + "loss": 3.5827, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366253636913368e-05, + "loss": 3.5776, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.36541668004269e-05, + "loss": 3.5908, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364578085291638e-05, + "loss": 3.5641, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363739490540586e-05, + "loss": 3.5723, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362900895789534e-05, + "loss": 3.5691, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362062301038482e-05, + "loss": 3.5776, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.36122370628743e-05, + "loss": 3.5775, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360385111536378e-05, + "loss": 3.5768, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359546516785326e-05, + "loss": 3.5812, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358707922034274e-05, + "loss": 3.5862, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357870965163595e-05, + "loss": 3.5859, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357032370412543e-05, + "loss": 3.582, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356193775661491e-05, + "loss": 3.5768, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355355180910439e-05, + "loss": 3.5907, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3545182240397596e-05, + "loss": 3.5774, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353679629288708e-05, + "loss": 3.5757, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352841034537656e-05, + "loss": 3.5825, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352002439786604e-05, + "loss": 3.5692, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351165482915925e-05, + "loss": 3.5743, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350326888164873e-05, + "loss": 3.5784, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349488293413821e-05, + "loss": 3.5802, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348649698662769e-05, + "loss": 3.5854, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.34781274179209e-05, + "loss": 3.5867, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346974147041038e-05, + "loss": 3.5749, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346135552289986e-05, + "loss": 3.583, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345296957538934e-05, + "loss": 3.5875, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344460000668255e-05, + "loss": 3.5682, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.3436214059172036e-05, + "loss": 3.574, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3427828111661516e-05, + "loss": 3.563, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3419442164150996e-05, + "loss": 3.5705, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411072595444205e-05, + "loss": 3.5712, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3402686647933685e-05, + "loss": 3.5922, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394300700423165e-05, + "loss": 3.5689, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3385914752912645e-05, + "loss": 3.5714, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3377545184205854e-05, + "loss": 3.5756, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369159236695334e-05, + "loss": 3.5772, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3360773289184814e-05, + "loss": 3.5688, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3352387341674294e-05, + "loss": 3.5576, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3344001394163774e-05, + "loss": 3.5785, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333563182545699e-05, + "loss": 3.5846, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332724587794647e-05, + "loss": 3.5836, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331885993043595e-05, + "loss": 3.5718, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331047398292543e-05, + "loss": 3.567, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330210441421864e-05, + "loss": 3.5763, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329371846670812e-05, + "loss": 3.5622, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.32853325191976e-05, + "loss": 3.5894, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327694657168708e-05, + "loss": 3.5606, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326857700298029e-05, + "loss": 3.5908, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326019105546977e-05, + "loss": 3.5785, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325180510795925e-05, + "loss": 3.5581, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324341916044873e-05, + "loss": 3.5758, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3235049591741944e-05, + "loss": 3.5742, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226663644231424e-05, + "loss": 3.5577, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218277696720903e-05, + "loss": 3.5665, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3209891749210383e-05, + "loss": 3.5834, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320152218050359e-05, + "loss": 3.5644, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319313623299307e-05, + "loss": 3.568, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318475028548255e-05, + "loss": 3.556, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317636433797203e-05, + "loss": 3.5708, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316799476926524e-05, + "loss": 3.5643, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315960882175472e-05, + "loss": 3.5738, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.31512228742442e-05, + "loss": 3.5687, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314283692673368e-05, + "loss": 3.5716, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.31344673580269e-05, + "loss": 3.5826, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312608141051638e-05, + "loss": 3.568, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311769546300586e-05, + "loss": 3.5732, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310930951549534e-05, + "loss": 3.5732, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.3100939946788546e-05, + "loss": 3.5703, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.3092553999278026e-05, + "loss": 3.5761, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.3084168051767506e-05, + "loss": 3.571, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.3075782104256986e-05, + "loss": 3.5703, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3067412535550195e-05, + "loss": 3.5773, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3059026588039675e-05, + "loss": 3.5721, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3050640640529155e-05, + "loss": 3.5512, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3042254693018635e-05, + "loss": 3.572, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3033885124311844e-05, + "loss": 3.568, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302549917680133e-05, + "loss": 3.5695, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301711322929081e-05, + "loss": 3.5674, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300872728178029e-05, + "loss": 3.5718, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.30003577130735e-05, + "loss": 3.559, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299197176556298e-05, + "loss": 3.561, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298358581805246e-05, + "loss": 3.5673, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297519987054194e-05, + "loss": 3.5765, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296683030183515e-05, + "loss": 3.5697, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295844435432463e-05, + "loss": 3.5808, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295005840681411e-05, + "loss": 3.5608, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294167245930358e-05, + "loss": 3.5676, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.29333028905968e-05, + "loss": 3.5684, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.2924916943086285e-05, + "loss": 3.5763, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.2916530995575764e-05, + "loss": 3.5693, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290814504806524e-05, + "loss": 3.5753, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.2899775479358454e-05, + "loss": 3.5676, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2891389531847933e-05, + "loss": 3.5649, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.2883003584337413e-05, + "loss": 3.5798, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.2874617636826887e-05, + "loss": 3.5609, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.2866231689316367e-05, + "loss": 3.5655, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285786212060958e-05, + "loss": 3.5694, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2849476173099056e-05, + "loss": 3.566, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2841090225588536e-05, + "loss": 3.5644, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283270427807802e-05, + "loss": 3.5662, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282433470937124e-05, + "loss": 3.5575, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281594876186071e-05, + "loss": 3.5711, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280756281435019e-05, + "loss": 3.5715, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279917686683967e-05, + "loss": 3.5629, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279080729813289e-05, + "loss": 3.5784, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278242135062236e-05, + "loss": 3.5811, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277403540311184e-05, + "loss": 3.5679, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276564945560132e-05, + "loss": 3.5659, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275727988689453e-05, + "loss": 3.5652, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274889393938401e-05, + "loss": 3.5666, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274050799187349e-05, + "loss": 3.5625, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.2732122044362976e-05, + "loss": 3.5656, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2723752475656185e-05, + "loss": 3.5604, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.2715366528145665e-05, + "loss": 3.5741, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.2706980580635145e-05, + "loss": 3.5678, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2698594633124625e-05, + "loss": 3.5641, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690225064417834e-05, + "loss": 3.5677, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2681839116907314e-05, + "loss": 3.5663, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2673453169396794e-05, + "loss": 3.5626, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.2665067221886274e-05, + "loss": 3.5783, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265669765317948e-05, + "loss": 3.5772, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264831170566896e-05, + "loss": 3.5662, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.263992575815844e-05, + "loss": 3.5617, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263153981064793e-05, + "loss": 3.5721, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262317024194114e-05, + "loss": 3.5659, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261478429443062e-05, + "loss": 3.567, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.26063983469201e-05, + "loss": 3.5696, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259801239940958e-05, + "loss": 3.5875, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258964283070279e-05, + "loss": 3.5676, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258125688319227e-05, + "loss": 3.5767, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257287093568175e-05, + "loss": 3.5659, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256448498817123e-05, + "loss": 3.5764, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255611541946444e-05, + "loss": 3.565, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.2547729471953917e-05, + "loss": 3.5596, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.2539343524443397e-05, + "loss": 3.5707, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253095757693288e-05, + "loss": 3.5555, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252258800822609e-05, + "loss": 3.5694, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251420206071557e-05, + "loss": 3.5621, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.851832151412964, + "eval_runtime": 304.5482, + "eval_samples_per_second": 1252.974, + "eval_steps_per_second": 39.156, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250581611320505e-05, + "loss": 3.5691, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249743016569453e-05, + "loss": 3.5614, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248906059698774e-05, + "loss": 3.5623, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248067464947722e-05, + "loss": 3.577, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.24722887019667e-05, + "loss": 3.5713, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246390275445618e-05, + "loss": 3.5781, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245553318574939e-05, + "loss": 3.5626, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244714723823887e-05, + "loss": 3.5624, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243876129072835e-05, + "loss": 3.5588, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243037534321784e-05, + "loss": 3.5713, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.2422005774511046e-05, + "loss": 3.564, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2413619827000526e-05, + "loss": 3.5621, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.2405250258293735e-05, + "loss": 3.5763, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.2396864310783215e-05, + "loss": 3.5504, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.2388478363272695e-05, + "loss": 3.5517, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.2380092415762175e-05, + "loss": 3.5524, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.2371706468251655e-05, + "loss": 3.5597, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.2363320520741135e-05, + "loss": 3.5624, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.2354934573230615e-05, + "loss": 3.5626, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.2346548625720095e-05, + "loss": 3.5617, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.2338162678209575e-05, + "loss": 3.5707, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.232979310950279e-05, + "loss": 3.5667, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232140716199227e-05, + "loss": 3.5682, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231302121448175e-05, + "loss": 3.5601, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230463526697123e-05, + "loss": 3.5755, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229626569826444e-05, + "loss": 3.5623, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228787975075392e-05, + "loss": 3.5602, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.22794938032434e-05, + "loss": 3.5617, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.227110785573288e-05, + "loss": 3.5559, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226273828702609e-05, + "loss": 3.5579, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225435233951557e-05, + "loss": 3.5609, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224596639200505e-05, + "loss": 3.5646, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223758044449453e-05, + "loss": 3.5722, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222921087578774e-05, + "loss": 3.5706, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2220824928277224e-05, + "loss": 3.5578, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.2212438980766704e-05, + "loss": 3.567, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.2204053033256184e-05, + "loss": 3.5664, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219568346454939e-05, + "loss": 3.5538, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218729751703887e-05, + "loss": 3.5563, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217891156952835e-05, + "loss": 3.547, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217052562201783e-05, + "loss": 3.5564, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216215605331104e-05, + "loss": 3.5548, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215377010580052e-05, + "loss": 3.5731, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214538415829e-05, + "loss": 3.5534, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213699821077948e-05, + "loss": 3.5566, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212862864207269e-05, + "loss": 3.564, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212024269456218e-05, + "loss": 3.5595, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211185674705166e-05, + "loss": 3.5564, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210347079954114e-05, + "loss": 3.5367, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209510123083435e-05, + "loss": 3.56, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208671528332383e-05, + "loss": 3.5671, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207832933581331e-05, + "loss": 3.5684, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.206994338830279e-05, + "loss": 3.554, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.2061573819595996e-05, + "loss": 3.5484, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.2053187872085476e-05, + "loss": 3.5611, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.2044801924574956e-05, + "loss": 3.5495, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.2036415977064436e-05, + "loss": 3.5698, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.2028046408357645e-05, + "loss": 3.5439, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201966046084713e-05, + "loss": 3.5774, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201127451333661e-05, + "loss": 3.5629, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2002888565826085e-05, + "loss": 3.5431, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.19945189971193e-05, + "loss": 3.5572, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198613304960878e-05, + "loss": 3.565, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197774710209826e-05, + "loss": 3.5407, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1969361154587734e-05, + "loss": 3.5492, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.196099158588095e-05, + "loss": 3.5708, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195260563837043e-05, + "loss": 3.5534, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.19442196908599e-05, + "loss": 3.5506, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193583374334938e-05, + "loss": 3.5351, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192744779583887e-05, + "loss": 3.5533, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1919078227132085e-05, + "loss": 3.5487, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191069227962156e-05, + "loss": 3.5618, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190230633211104e-05, + "loss": 3.5488, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189392038460052e-05, + "loss": 3.5587, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.1885550815893734e-05, + "loss": 3.5633, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187716486838321e-05, + "loss": 3.5572, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186877892087269e-05, + "loss": 3.5541, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186039297336217e-05, + "loss": 3.5529, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.1852023404655376e-05, + "loss": 3.5577, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.1843637457144856e-05, + "loss": 3.5607, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.1835251509634336e-05, + "loss": 3.5551, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182686556212382e-05, + "loss": 3.5554, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181849599341703e-05, + "loss": 3.5569, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.181011004590651e-05, + "loss": 3.5559, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180172409839599e-05, + "loss": 3.5378, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.179333815088547e-05, + "loss": 3.5547, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178496858217868e-05, + "loss": 3.55, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177658263466816e-05, + "loss": 3.554, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176819668715764e-05, + "loss": 3.5553, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.175981073964712e-05, + "loss": 3.5539, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175144117094033e-05, + "loss": 3.5481, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174305522342981e-05, + "loss": 3.5435, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173466927591929e-05, + "loss": 3.5473, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172628332840878e-05, + "loss": 3.5609, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.1717913759701986e-05, + "loss": 3.5555, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.1709527812191466e-05, + "loss": 3.5633, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.1701141864680946e-05, + "loss": 3.5486, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.1692755917170426e-05, + "loss": 3.5537, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.1684386348463635e-05, + "loss": 3.5493, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.1676000400953115e-05, + "loss": 3.5608, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.1667614453442595e-05, + "loss": 3.5509, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.1659228505932075e-05, + "loss": 3.5613, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.1650858937225284e-05, + "loss": 3.5488, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.1642472989714764e-05, + "loss": 3.547, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634087042204244e-05, + "loss": 3.565, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162570109469373e-05, + "loss": 3.5417, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161733152598694e-05, + "loss": 3.5494, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160894557847642e-05, + "loss": 3.5564, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.16005596309659e-05, + "loss": 3.5486, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159217368345538e-05, + "loss": 3.5491, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158380411474859e-05, + "loss": 3.5525, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157541816723807e-05, + "loss": 3.5442, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156703221972755e-05, + "loss": 3.5566, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155864627221703e-05, + "loss": 3.5524, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155027670351024e-05, + "loss": 3.5509, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154189075599972e-05, + "loss": 3.5616, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.15335048084892e-05, + "loss": 3.5641, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.1525118860978684e-05, + "loss": 3.5542, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151674929227189e-05, + "loss": 3.5504, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150836334476137e-05, + "loss": 3.5478, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.149997739725085e-05, + "loss": 3.5505, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149159144974033e-05, + "loss": 3.5431, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148322188103354e-05, + "loss": 3.5533, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147483593352302e-05, + "loss": 3.5413, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.14664499860125e-05, + "loss": 3.5592, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145806403850198e-05, + "loss": 3.5502, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.144969446979519e-05, + "loss": 3.5506, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144130852228467e-05, + "loss": 3.5531, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143292257477415e-05, + "loss": 3.5484, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142453662726364e-05, + "loss": 3.546, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141616705855685e-05, + "loss": 3.5638, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140778111104633e-05, + "loss": 3.5596, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139939516353581e-05, + "loss": 3.5556, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.139100921602529e-05, + "loss": 3.5423, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1382639647318496e-05, + "loss": 3.5549, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.1374253699807976e-05, + "loss": 3.5525, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.1365867752297456e-05, + "loss": 3.5516, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.1357481804786936e-05, + "loss": 3.5565, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.1349112236080145e-05, + "loss": 3.5687, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.1340726288569625e-05, + "loss": 3.5519, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.1332340341059105e-05, + "loss": 3.5621, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.1323954393548585e-05, + "loss": 3.5514, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.13155848248418e-05, + "loss": 3.5575, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130719887733128e-05, + "loss": 3.5464, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129881292982076e-05, + "loss": 3.549, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.129042698231024e-05, + "loss": 3.5552, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128205741360345e-05, + "loss": 3.5377, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127367146609293e-05, + "loss": 3.5537, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126528551858241e-05, + "loss": 3.5498, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.852745532989502, + "eval_runtime": 303.314, + "eval_samples_per_second": 1258.072, + "eval_steps_per_second": 39.316, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125689957107189e-05, + "loss": 3.5563, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124851362356137e-05, + "loss": 3.5469, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.124012767605085e-05, + "loss": 3.547, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123174172854033e-05, + "loss": 3.5597, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122337215983354e-05, + "loss": 3.5574, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.1214986212323025e-05, + "loss": 3.565, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.1206600264812505e-05, + "loss": 3.5449, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.1198214317301985e-05, + "loss": 3.5494, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118982836979146e-05, + "loss": 3.5403, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.1181458801084674e-05, + "loss": 3.5579, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.1173072853574154e-05, + "loss": 3.5499, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.1164686906063634e-05, + "loss": 3.5491, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115630095855311e-05, + "loss": 3.5507, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114793138984632e-05, + "loss": 3.5406, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.11395454423358e-05, + "loss": 3.5404, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113115949482528e-05, + "loss": 3.5402, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112277354731476e-05, + "loss": 3.5375, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111438759980424e-05, + "loss": 3.5466, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110600165229372e-05, + "loss": 3.5482, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.10976157047832e-05, + "loss": 3.543, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108922975727268e-05, + "loss": 3.5587, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108086018856589e-05, + "loss": 3.5501, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107247424105537e-05, + "loss": 3.5513, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106408829354485e-05, + "loss": 3.5471, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105570234603433e-05, + "loss": 3.5586, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104733277732754e-05, + "loss": 3.5441, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103894682981702e-05, + "loss": 3.5481, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.10305608823065e-05, + "loss": 3.5415, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102217493479598e-05, + "loss": 3.5458, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.1013805366089196e-05, + "loss": 3.5433, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.1005419418578676e-05, + "loss": 3.5414, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.0997033471068156e-05, + "loss": 3.5529, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.0988647523557636e-05, + "loss": 3.5547, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0980277954850845e-05, + "loss": 3.5502, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0971892007340325e-05, + "loss": 3.546, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0963506059829805e-05, + "loss": 3.5508, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.0955120112319285e-05, + "loss": 3.5524, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.0946750543612494e-05, + "loss": 3.5368, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.0938364596101974e-05, + "loss": 3.5455, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0929978648591454e-05, + "loss": 3.5307, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0921592701080934e-05, + "loss": 3.5419, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.0913206753570414e-05, + "loss": 3.539, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090483718486363e-05, + "loss": 3.5599, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089645123735311e-05, + "loss": 3.5402, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088806528984259e-05, + "loss": 3.5373, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087967934233207e-05, + "loss": 3.5459, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087130977362528e-05, + "loss": 3.5463, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086292382611476e-05, + "loss": 3.5396, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085453787860424e-05, + "loss": 3.5227, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084615193109372e-05, + "loss": 3.5412, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083778236238693e-05, + "loss": 3.5534, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082939641487641e-05, + "loss": 3.5522, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082101046736589e-05, + "loss": 3.5432, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081262451985537e-05, + "loss": 3.5334, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0804254951148584e-05, + "loss": 3.5481, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0795869003638064e-05, + "loss": 3.5306, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0787483056127544e-05, + "loss": 3.5564, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.0779097108617024e-05, + "loss": 3.5276, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077072753991023e-05, + "loss": 3.5563, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076234159239971e-05, + "loss": 3.5499, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075395564488919e-05, + "loss": 3.5279, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074556969737867e-05, + "loss": 3.5436, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073720012867188e-05, + "loss": 3.549, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072881418116136e-05, + "loss": 3.5219, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072042823365084e-05, + "loss": 3.5346, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071204228614032e-05, + "loss": 3.5551, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070367271743354e-05, + "loss": 3.5401, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069528676992302e-05, + "loss": 3.5346, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.06869008224125e-05, + "loss": 3.5256, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067851487490198e-05, + "loss": 3.5376, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.0670145306195186e-05, + "loss": 3.5282, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.0661759358684666e-05, + "loss": 3.5464, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.0653373411174146e-05, + "loss": 3.5325, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.0644987463663626e-05, + "loss": 3.5441, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.0636617894956835e-05, + "loss": 3.5454, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.0628231947446315e-05, + "loss": 3.5402, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.0619845999935795e-05, + "loss": 3.5381, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.0611460052425275e-05, + "loss": 3.5386, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060309048371849e-05, + "loss": 3.5441, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059470453620797e-05, + "loss": 3.543, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058631858869745e-05, + "loss": 3.5417, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057793264118693e-05, + "loss": 3.5403, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056956307248014e-05, + "loss": 3.5412, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056117712496962e-05, + "loss": 3.5404, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.05527911774591e-05, + "loss": 3.5241, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054440522994858e-05, + "loss": 3.5365, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053603566124179e-05, + "loss": 3.5371, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052764971373127e-05, + "loss": 3.538, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051926376622075e-05, + "loss": 3.5424, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0510877818710232e-05, + "loss": 3.5376, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.050250825000344e-05, + "loss": 3.534, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.049412230249292e-05, + "loss": 3.5259, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.04857363549824e-05, + "loss": 3.5344, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477350407471885e-05, + "loss": 3.5449, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0468980838765094e-05, + "loss": 3.5418, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460594891254574e-05, + "loss": 3.5482, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452208943744054e-05, + "loss": 3.5369, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0443822996233534e-05, + "loss": 3.5372, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435453427526746e-05, + "loss": 3.5331, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427067480016226e-05, + "loss": 3.5458, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0418681532505706e-05, + "loss": 3.5359, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410295584995186e-05, + "loss": 3.5469, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0401926016288395e-05, + "loss": 3.5334, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393540068777875e-05, + "loss": 3.5306, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385154121267355e-05, + "loss": 3.5523, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0376768173756838e-05, + "loss": 3.5304, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0368398605050047e-05, + "loss": 3.5302, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360012657539527e-05, + "loss": 3.5396, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0351626710029007e-05, + "loss": 3.5397, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343240762518484e-05, + "loss": 3.5295, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.03348711938117e-05, + "loss": 3.5358, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.032648524630118e-05, + "loss": 3.5306, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.031809929879066e-05, + "loss": 3.5372, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0309713351280133e-05, + "loss": 3.5374, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.030134378257335e-05, + "loss": 3.5374, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029295783506283e-05, + "loss": 3.5442, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.028457188755231e-05, + "loss": 3.551, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276185940041785e-05, + "loss": 3.5395, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0267816371335e-05, + "loss": 3.5368, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.025943042382448e-05, + "loss": 3.5324, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251044476313954e-05, + "loss": 3.5349, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0242658528803437e-05, + "loss": 3.5295, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234288960096653e-05, + "loss": 3.538, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0225903012586133e-05, + "loss": 3.5295, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217517065075606e-05, + "loss": 3.5414, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209131117565086e-05, + "loss": 3.5358, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200761548858302e-05, + "loss": 3.5395, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192375601347782e-05, + "loss": 3.5362, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.018398965383726e-05, + "loss": 3.5344, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.017560370632674e-05, + "loss": 3.5295, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167234137619955e-05, + "loss": 3.5468, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0158848190109428e-05, + "loss": 3.5491, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150462242598908e-05, + "loss": 3.5421, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.014207629508839e-05, + "loss": 3.5294, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0133706726381604e-05, + "loss": 3.5365, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.012532077887108e-05, + "loss": 3.5386, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.011693483136056e-05, + "loss": 3.5373, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.010854888385004e-05, + "loss": 3.5418, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100179315143256e-05, + "loss": 3.5511, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0091793367632733e-05, + "loss": 3.5354, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083407420122213e-05, + "loss": 3.5513, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0075021472611692e-05, + "loss": 3.5334, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.00666519039049e-05, + "loss": 3.5411, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.005826595639438e-05, + "loss": 3.5359, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.004988000888386e-05, + "loss": 3.5287, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.004149406137334e-05, + "loss": 3.5435, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033124492666554e-05, + "loss": 3.5286, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0024738545156034e-05, + "loss": 3.5341, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016352597645514e-05, + "loss": 3.535, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0007966650134994e-05, + "loss": 3.5345, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.853952407836914, + "eval_runtime": 303.9701, + "eval_samples_per_second": 1255.357, + "eval_steps_per_second": 39.231, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9999597081428203e-05, + "loss": 3.5327, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991211133917686e-05, + "loss": 3.534, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9982825186407166e-05, + "loss": 3.5433, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974439238896646e-05, + "loss": 3.5431, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966069670189855e-05, + "loss": 3.5518, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957683722679335e-05, + "loss": 3.5307, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949297775168815e-05, + "loss": 3.5301, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9940911827658295e-05, + "loss": 3.5292, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9932542258951508e-05, + "loss": 3.5423, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9924156311440988e-05, + "loss": 3.533, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9915770363930467e-05, + "loss": 3.535, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9907384416419947e-05, + "loss": 3.5323, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899014847713157e-05, + "loss": 3.528, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.989062890020264e-05, + "loss": 3.5307, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.988224295269212e-05, + "loss": 3.5257, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.98738570051816e-05, + "loss": 3.5227, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986547105767108e-05, + "loss": 3.5326, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.985708511016056e-05, + "loss": 3.5329, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984869916265004e-05, + "loss": 3.5296, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.984031321513952e-05, + "loss": 3.5447, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9831943646432732e-05, + "loss": 3.5333, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823557698922212e-05, + "loss": 3.5384, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815171751411692e-05, + "loss": 3.5321, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9806785803901172e-05, + "loss": 3.5427, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.979841623519438e-05, + "loss": 3.5325, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.979003028768386e-05, + "loss": 3.5366, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.978164434017334e-05, + "loss": 3.5275, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773274771466553e-05, + "loss": 3.5345, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9764888823956033e-05, + "loss": 3.5237, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9756502876445513e-05, + "loss": 3.5305, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748116928934993e-05, + "loss": 3.5386, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9739747360228202e-05, + "loss": 3.5354, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731361412717686e-05, + "loss": 3.539, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9722975465207166e-05, + "loss": 3.5361, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714589517696646e-05, + "loss": 3.5297, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706203570186126e-05, + "loss": 3.5416, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9697834001479335e-05, + "loss": 3.5239, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689448053968815e-05, + "loss": 3.5284, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681062106458295e-05, + "loss": 3.5165, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9672676158947778e-05, + "loss": 3.5241, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664306590240987e-05, + "loss": 3.5236, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9655920642730467e-05, + "loss": 3.5422, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9647534695219947e-05, + "loss": 3.5273, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639148747709427e-05, + "loss": 3.5236, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.963077917900264e-05, + "loss": 3.5348, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962239323149212e-05, + "loss": 3.5334, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.96140072839816e-05, + "loss": 3.523, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960563771527481e-05, + "loss": 3.5138, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959725176776429e-05, + "loss": 3.5197, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.958886582025377e-05, + "loss": 3.5393, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.958047987274325e-05, + "loss": 3.5387, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.957211030403646e-05, + "loss": 3.5236, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.956374073532967e-05, + "loss": 3.5212, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.955535478781915e-05, + "loss": 3.535, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.954696884030863e-05, + "loss": 3.5184, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.953858289279811e-05, + "loss": 3.535, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530196945287593e-05, + "loss": 3.5168, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9521810997777073e-05, + "loss": 3.5431, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513425050266553e-05, + "loss": 3.533, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505039102756033e-05, + "loss": 3.5205, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9496669534049242e-05, + "loss": 3.5219, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488283586538722e-05, + "loss": 3.5372, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9479897639028202e-05, + "loss": 3.5079, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471511691517685e-05, + "loss": 3.5198, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463142122810894e-05, + "loss": 3.5378, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9454756175300374e-05, + "loss": 3.5266, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446370227789854e-05, + "loss": 3.5211, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.943798428027933e-05, + "loss": 3.5118, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9429614711572547e-05, + "loss": 3.5196, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421228764062027e-05, + "loss": 3.5168, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9412842816551507e-05, + "loss": 3.5344, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.940445686904098e-05, + "loss": 3.517, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396087300334196e-05, + "loss": 3.531, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9387701352823676e-05, + "loss": 3.5281, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379315405313156e-05, + "loss": 3.5328, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9370929457802632e-05, + "loss": 3.5196, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9362559889095848e-05, + "loss": 3.5259, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354173941585328e-05, + "loss": 3.53, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.93457879940748e-05, + "loss": 3.5297, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337402046564285e-05, + "loss": 3.5266, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329016099053765e-05, + "loss": 3.5249, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.932064653034698e-05, + "loss": 3.5272, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312260582836454e-05, + "loss": 3.524, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9303874635325934e-05, + "loss": 3.5164, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9295488687815413e-05, + "loss": 3.5174, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.928711911910863e-05, + "loss": 3.5263, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9278733171598106e-05, + "loss": 3.5265, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270347224087586e-05, + "loss": 3.523, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9261961276577066e-05, + "loss": 3.523, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253591707870275e-05, + "loss": 3.5192, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245205760359755e-05, + "loss": 3.5142, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9236819812849235e-05, + "loss": 3.5183, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9228433865338718e-05, + "loss": 3.5255, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220064296631927e-05, + "loss": 3.5263, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9211678349121407e-05, + "loss": 3.5343, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203292401610887e-05, + "loss": 3.5289, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9194906454100367e-05, + "loss": 3.517, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918653688539358e-05, + "loss": 3.5212, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.917815093788306e-05, + "loss": 3.5271, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.916976499037254e-05, + "loss": 3.5288, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916137904286202e-05, + "loss": 3.5307, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915300947415523e-05, + "loss": 3.5169, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914462352664471e-05, + "loss": 3.5187, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.913623757913419e-05, + "loss": 3.5389, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9127851631623672e-05, + "loss": 3.5153, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.911948206291688e-05, + "loss": 3.5189, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.911109611540636e-05, + "loss": 3.5234, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.910271016789584e-05, + "loss": 3.5263, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.909432422038532e-05, + "loss": 3.5138, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9085954651678533e-05, + "loss": 3.5209, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9077568704168013e-05, + "loss": 3.517, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069182756657493e-05, + "loss": 3.5267, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9060796809146973e-05, + "loss": 3.5227, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052427240440182e-05, + "loss": 3.5199, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044041292929662e-05, + "loss": 3.5297, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9035655345419142e-05, + "loss": 3.5364, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027269397908626e-05, + "loss": 3.5264, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9018899829201835e-05, + "loss": 3.5182, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9010513881691315e-05, + "loss": 3.5189, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002127934180795e-05, + "loss": 3.5181, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8993741986670274e-05, + "loss": 3.5213, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985372417963487e-05, + "loss": 3.5226, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8976986470452967e-05, + "loss": 3.5145, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8968600522942447e-05, + "loss": 3.5237, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960214575431927e-05, + "loss": 3.5249, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8951845006725136e-05, + "loss": 3.5237, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943459059214616e-05, + "loss": 3.5207, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935073111704096e-05, + "loss": 3.5213, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.892668716419358e-05, + "loss": 3.5186, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8918317595486788e-05, + "loss": 3.5331, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8909931647976268e-05, + "loss": 3.5335, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8901545700465748e-05, + "loss": 3.5293, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893159752955228e-05, + "loss": 3.5088, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.888479018424844e-05, + "loss": 3.5277, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887640423673792e-05, + "loss": 3.5244, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.88680182892274e-05, + "loss": 3.5249, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.885963234171688e-05, + "loss": 3.5223, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885126277301009e-05, + "loss": 3.5376, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.884287682549957e-05, + "loss": 3.5209, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.883449087798905e-05, + "loss": 3.5423, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826104930478533e-05, + "loss": 3.5183, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8817735361771742e-05, + "loss": 3.5298, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809349414261222e-05, + "loss": 3.521, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8800963466750702e-05, + "loss": 3.5186, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8792577519240182e-05, + "loss": 3.526, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784207950533394e-05, + "loss": 3.5158, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8775822003022874e-05, + "loss": 3.5199, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767436055512354e-05, + "loss": 3.5205, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759050108001834e-05, + "loss": 3.5205, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8551080226898193, + "eval_runtime": 303.9137, + "eval_samples_per_second": 1255.59, + "eval_steps_per_second": 39.238, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8750664160491314e-05, + "loss": 3.5201, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742278212980794e-05, + "loss": 3.5182, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8733892265470274e-05, + "loss": 3.5315, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725522696763487e-05, + "loss": 3.5265, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717136749252966e-05, + "loss": 3.5391, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8708750801742446e-05, + "loss": 3.5167, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700364854231926e-05, + "loss": 3.519, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8691978906721406e-05, + "loss": 3.515, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8683609338014615e-05, + "loss": 3.5286, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675223390504095e-05, + "loss": 3.5205, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866683744299358e-05, + "loss": 3.5182, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865845149548306e-05, + "loss": 3.5233, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650098305579997e-05, + "loss": 3.5096, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641712358069477e-05, + "loss": 3.5196, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633326410558957e-05, + "loss": 3.5102, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.862494046304844e-05, + "loss": 3.5113, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.861655451553792e-05, + "loss": 3.5169, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.86081685680274e-05, + "loss": 3.5158, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.859978262051688e-05, + "loss": 3.5164, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591396673006353e-05, + "loss": 3.5362, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.858302710429957e-05, + "loss": 3.5196, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.857464115678905e-05, + "loss": 3.5211, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.856625520927853e-05, + "loss": 3.5205, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8557869261768006e-05, + "loss": 3.5251, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.854949969306122e-05, + "loss": 3.5202, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.85411137455507e-05, + "loss": 3.5251, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.853272779804018e-05, + "loss": 3.511, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524341850529658e-05, + "loss": 3.5195, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8515972281822874e-05, + "loss": 3.5065, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8507586334312354e-05, + "loss": 3.5199, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499200386801827e-05, + "loss": 3.5215, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8490814439291307e-05, + "loss": 3.5211, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482444870584523e-05, + "loss": 3.5274, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474058923074003e-05, + "loss": 3.5165, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.846567297556348e-05, + "loss": 3.521, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.845728702805296e-05, + "loss": 3.5244, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8448917459346175e-05, + "loss": 3.5148, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440531511835655e-05, + "loss": 3.5121, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843214556432513e-05, + "loss": 3.5019, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842375961681461e-05, + "loss": 3.5107, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415390048107827e-05, + "loss": 3.5127, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.84070041005973e-05, + "loss": 3.5273, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839861815308678e-05, + "loss": 3.5143, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.839023220557626e-05, + "loss": 3.509, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8381862636869476e-05, + "loss": 3.5219, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373476689358953e-05, + "loss": 3.5155, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365090741848433e-05, + "loss": 3.5133, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8356704794337913e-05, + "loss": 3.5025, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834833522563113e-05, + "loss": 3.5033, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8339949278120602e-05, + "loss": 3.5271, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331563330610082e-05, + "loss": 3.5245, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323177383099565e-05, + "loss": 3.5103, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8314807814392774e-05, + "loss": 3.5103, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.830643824568599e-05, + "loss": 3.5199, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.829805229817547e-05, + "loss": 3.5052, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.828966635066495e-05, + "loss": 3.5233, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281280403154427e-05, + "loss": 3.5014, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8272894455643907e-05, + "loss": 3.5259, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264508508133387e-05, + "loss": 3.5229, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256122560622867e-05, + "loss": 3.5088, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8247752991916076e-05, + "loss": 3.5085, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239367044405556e-05, + "loss": 3.5225, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8230981096895036e-05, + "loss": 3.4916, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.822259514938452e-05, + "loss": 3.5086, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214225580677728e-05, + "loss": 3.5237, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8205839633167208e-05, + "loss": 3.5167, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197453685656688e-05, + "loss": 3.5051, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189067738146168e-05, + "loss": 3.499, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.818069816943938e-05, + "loss": 3.5061, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.817231222192886e-05, + "loss": 3.5064, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.816392627441834e-05, + "loss": 3.5126, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815554032690782e-05, + "loss": 3.5073, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.814717075820103e-05, + "loss": 3.5202, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.813878481069051e-05, + "loss": 3.5156, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.813039886317999e-05, + "loss": 3.517, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122012915669473e-05, + "loss": 3.5051, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8113643346962682e-05, + "loss": 3.5146, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810525739945216e-05, + "loss": 3.5158, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809687145194164e-05, + "loss": 3.5153, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808848550443112e-05, + "loss": 3.516, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080115935724334e-05, + "loss": 3.5114, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071729988213814e-05, + "loss": 3.5167, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063344040703294e-05, + "loss": 3.5107, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8054958093192774e-05, + "loss": 3.4981, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046588524485983e-05, + "loss": 3.505, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038202576975463e-05, + "loss": 3.5095, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8029816629464943e-05, + "loss": 3.5172, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021430681954426e-05, + "loss": 3.5113, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013061113247635e-05, + "loss": 3.5077, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004675165737115e-05, + "loss": 3.5051, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996289218226595e-05, + "loss": 3.4991, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7987903270716075e-05, + "loss": 3.5024, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979533702009288e-05, + "loss": 3.5142, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971147754498768e-05, + "loss": 3.5124, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7962761806988248e-05, + "loss": 3.5214, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954375859477728e-05, + "loss": 3.5138, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946006290770937e-05, + "loss": 3.5058, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937620343260417e-05, + "loss": 3.5098, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929234395749897e-05, + "loss": 3.51, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.792084844823938e-05, + "loss": 3.5148, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791247887953259e-05, + "loss": 3.5186, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790409293202207e-05, + "loss": 3.5082, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789570698451155e-05, + "loss": 3.5029, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.788732103700103e-05, + "loss": 3.5231, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787895146829424e-05, + "loss": 3.5011, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.787056552078372e-05, + "loss": 3.5097, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.78621795732732e-05, + "loss": 3.5127, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785379362576268e-05, + "loss": 3.5099, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784542405705589e-05, + "loss": 3.5017, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783703810954537e-05, + "loss": 3.5113, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.782865216203485e-05, + "loss": 3.5003, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820266214524334e-05, + "loss": 3.5131, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7811896645817543e-05, + "loss": 3.5109, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803510698307023e-05, + "loss": 3.5045, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795124750796503e-05, + "loss": 3.5213, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7786738803285983e-05, + "loss": 3.5235, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778369234579195e-05, + "loss": 3.5118, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7769983287068675e-05, + "loss": 3.5078, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761597339558155e-05, + "loss": 3.5035, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753211392047635e-05, + "loss": 3.5091, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7744841823340844e-05, + "loss": 3.5021, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736455875830324e-05, + "loss": 3.5161, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728069928319804e-05, + "loss": 3.4991, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719683980809287e-05, + "loss": 3.5091, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711314412102496e-05, + "loss": 3.5114, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7702928464591976e-05, + "loss": 3.5149, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694542517081456e-05, + "loss": 3.5034, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686156569570936e-05, + "loss": 3.5077, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767778700086415e-05, + "loss": 3.5105, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.766940105335363e-05, + "loss": 3.512, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.766101510584311e-05, + "loss": 3.5186, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765262915833259e-05, + "loss": 3.5148, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644259589625798e-05, + "loss": 3.4992, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7635873642115278e-05, + "loss": 3.5108, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627487694604758e-05, + "loss": 3.513, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619101747094238e-05, + "loss": 3.5098, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761073217838745e-05, + "loss": 3.5117, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760234623087693e-05, + "loss": 3.5212, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759396028336641e-05, + "loss": 3.5105, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758557433585589e-05, + "loss": 3.528, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577204767149102e-05, + "loss": 3.5052, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7568818819638582e-05, + "loss": 3.5173, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560432872128062e-05, + "loss": 3.5092, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552046924617542e-05, + "loss": 3.5051, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.754367735591075e-05, + "loss": 3.511, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.753529140840023e-05, + "loss": 3.5064, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.752690546088971e-05, + "loss": 3.5064, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.751851951337919e-05, + "loss": 3.5029, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510149944672404e-05, + "loss": 3.5063, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.8564586639404297, + "eval_runtime": 306.0096, + "eval_samples_per_second": 1246.99, + "eval_steps_per_second": 38.969, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7501763997161884e-05, + "loss": 3.5092, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493378049651364e-05, + "loss": 3.5063, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485008480944573e-05, + "loss": 3.5196, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7476622533434053e-05, + "loss": 3.5103, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468236585923536e-05, + "loss": 3.5295, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7459850638413016e-05, + "loss": 3.5029, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451481069706225e-05, + "loss": 3.5098, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443095122195705e-05, + "loss": 3.4978, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7434709174685185e-05, + "loss": 3.5152, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.7426323227174665e-05, + "loss": 3.5084, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7417953658467877e-05, + "loss": 3.5027, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7409567710957357e-05, + "loss": 3.5134, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401198142250566e-05, + "loss": 3.4971, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7392812194740046e-05, + "loss": 3.5082, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384426247229526e-05, + "loss": 3.4948, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376040299719006e-05, + "loss": 3.499, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.736765435220849e-05, + "loss": 3.4965, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735926840469797e-05, + "loss": 3.5076, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.735088245718745e-05, + "loss": 3.5019, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7342496509676923e-05, + "loss": 3.5216, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.733412694097014e-05, + "loss": 3.508, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.732574099345962e-05, + "loss": 3.5073, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317355045949095e-05, + "loss": 3.5087, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.730898547724231e-05, + "loss": 3.5127, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.730059952973179e-05, + "loss": 3.5043, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.729221358222127e-05, + "loss": 3.5126, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7283827634710744e-05, + "loss": 3.5003, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.727545806600396e-05, + "loss": 3.5059, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267072118493443e-05, + "loss": 3.4919, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7258686170982923e-05, + "loss": 3.5082, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250300223472396e-05, + "loss": 3.5096, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7241930654765612e-05, + "loss": 3.5073, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233544707255092e-05, + "loss": 3.5173, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.722515875974457e-05, + "loss": 3.5048, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.721677281223405e-05, + "loss": 3.5021, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208403243527265e-05, + "loss": 3.5132, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200017296016745e-05, + "loss": 3.5035, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7191631348506218e-05, + "loss": 3.4968, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7183245400995698e-05, + "loss": 3.4902, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717485945348518e-05, + "loss": 3.4966, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166489884778397e-05, + "loss": 3.4996, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.715810393726787e-05, + "loss": 3.5134, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.714971798975735e-05, + "loss": 3.5048, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.714133204224683e-05, + "loss": 3.4929, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7132962473540043e-05, + "loss": 3.5107, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7124576526029523e-05, + "loss": 3.5027, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116190578519003e-05, + "loss": 3.4986, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.710782100981222e-05, + "loss": 3.4918, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.709943506230169e-05, + "loss": 3.4884, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.709104911479117e-05, + "loss": 3.5135, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.708266316728065e-05, + "loss": 3.5124, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074293598573867e-05, + "loss": 3.4982, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7065907651063344e-05, + "loss": 3.4972, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.705753808235656e-05, + "loss": 3.5095, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.704915213484604e-05, + "loss": 3.4887, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7040766187335513e-05, + "loss": 3.5083, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7032380239824996e-05, + "loss": 3.4897, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7023994292314476e-05, + "loss": 3.5087, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7015608344803956e-05, + "loss": 3.5133, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007222397293436e-05, + "loss": 3.497, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6998852828586645e-05, + "loss": 3.4924, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990466881076125e-05, + "loss": 3.5106, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982080933565605e-05, + "loss": 3.4814, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.697369498605509e-05, + "loss": 3.4955, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965325417348298e-05, + "loss": 3.5078, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6956939469837778e-05, + "loss": 3.5054, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6948553522327257e-05, + "loss": 3.4944, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940167574816737e-05, + "loss": 3.4862, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.693179800610995e-05, + "loss": 3.4907, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.692341205859943e-05, + "loss": 3.4915, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.691502611108891e-05, + "loss": 3.5024, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.690664016357839e-05, + "loss": 3.4913, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.68982705948716e-05, + "loss": 3.5066, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.688988464736108e-05, + "loss": 3.5052, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.688149869985056e-05, + "loss": 3.5044, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873112752340042e-05, + "loss": 3.4902, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686474318363325e-05, + "loss": 3.502, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.685635723612273e-05, + "loss": 3.505, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.684797128861221e-05, + "loss": 3.4994, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.683958534110169e-05, + "loss": 3.5046, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.683119939359117e-05, + "loss": 3.4986, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6822829824884384e-05, + "loss": 3.4994, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6814443877373864e-05, + "loss": 3.5003, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806057929863343e-05, + "loss": 3.4843, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6797671982352823e-05, + "loss": 3.4965, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789302413646033e-05, + "loss": 3.4933, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6780916466135512e-05, + "loss": 3.5038, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772530518624996e-05, + "loss": 3.498, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764144571114476e-05, + "loss": 3.4952, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6755775002407685e-05, + "loss": 3.4915, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747389054897165e-05, + "loss": 3.488, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739003107386645e-05, + "loss": 3.4878, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730633538679857e-05, + "loss": 3.4974, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722247591169337e-05, + "loss": 3.5099, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6713861643658817e-05, + "loss": 3.5038, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6705475696148297e-05, + "loss": 3.5005, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697106127441506e-05, + "loss": 3.4937, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6688720179930986e-05, + "loss": 3.4997, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680334232420466e-05, + "loss": 3.4937, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.667194828490995e-05, + "loss": 3.5043, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.666357871620316e-05, + "loss": 3.5026, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.665519276869264e-05, + "loss": 3.4937, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664680682118212e-05, + "loss": 3.4882, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.66384208736716e-05, + "loss": 3.5116, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.663005130496481e-05, + "loss": 3.4893, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.662166535745429e-05, + "loss": 3.4986, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.661327940994377e-05, + "loss": 3.4927, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.660489346243325e-05, + "loss": 3.4977, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.659652389372646e-05, + "loss": 3.4899, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.658813794621594e-05, + "loss": 3.5004, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.657975199870542e-05, + "loss": 3.4906, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.65713660511949e-05, + "loss": 3.493, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6562996482488112e-05, + "loss": 3.5006, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554610534977592e-05, + "loss": 3.4905, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546224587467072e-05, + "loss": 3.507, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6537838639956552e-05, + "loss": 3.5095, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.652946907124976e-05, + "loss": 3.4997, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521083123739245e-05, + "loss": 3.4951, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6512697176228725e-05, + "loss": 3.4932, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504311228718204e-05, + "loss": 3.494, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6495941660011414e-05, + "loss": 3.4902, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6487555712500894e-05, + "loss": 3.5013, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479169764990373e-05, + "loss": 3.4871, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6470783817479853e-05, + "loss": 3.4948, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462414248773066e-05, + "loss": 3.5022, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454028301262546e-05, + "loss": 3.5002, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6445642353752026e-05, + "loss": 3.4912, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6437256406241506e-05, + "loss": 3.4947, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6428886837534715e-05, + "loss": 3.5003, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6420500890024198e-05, + "loss": 3.499, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412114942513678e-05, + "loss": 3.5007, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6403728995003158e-05, + "loss": 3.5062, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395359426296367e-05, + "loss": 3.4861, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6386973478785847e-05, + "loss": 3.4998, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6378587531275327e-05, + "loss": 3.5003, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370201583764807e-05, + "loss": 3.4955, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636183201505802e-05, + "loss": 3.4965, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.63534460675475e-05, + "loss": 3.5102, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.634506012003698e-05, + "loss": 3.4968, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.633667417252646e-05, + "loss": 3.5143, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.632830460381967e-05, + "loss": 3.4933, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6319918656309152e-05, + "loss": 3.5, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311532708798632e-05, + "loss": 3.4978, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303146761288112e-05, + "loss": 3.4932, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629477719258132e-05, + "loss": 3.4972, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.62863912450708e-05, + "loss": 3.4953, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627800529756028e-05, + "loss": 3.4906, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.626961935004976e-05, + "loss": 3.4913, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6261249781342973e-05, + "loss": 3.4944, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.858982801437378, + "eval_runtime": 305.8862, + "eval_samples_per_second": 1247.493, + "eval_steps_per_second": 38.985, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6252863833832453e-05, + "loss": 3.4949, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244477886321933e-05, + "loss": 3.491, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236091938811413e-05, + "loss": 3.5034, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227705991300893e-05, + "loss": 3.4966, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219336422594106e-05, + "loss": 3.5176, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6210950475083586e-05, + "loss": 3.492, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202564527573065e-05, + "loss": 3.4955, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.619417858006254e-05, + "loss": 3.4817, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6185809011355755e-05, + "loss": 3.5029, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177423063845234e-05, + "loss": 3.4996, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169037116334714e-05, + "loss": 3.4901, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.616065116882419e-05, + "loss": 3.4955, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152297978921136e-05, + "loss": 3.4882, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6143912031410616e-05, + "loss": 3.4942, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135526083900096e-05, + "loss": 3.482, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127140136389576e-05, + "loss": 3.4828, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611875418887906e-05, + "loss": 3.484, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611036824136854e-05, + "loss": 3.493, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6101982293858012e-05, + "loss": 3.4906, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093596346347492e-05, + "loss": 3.5089, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085226777640708e-05, + "loss": 3.4953, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6076840830130188e-05, + "loss": 3.5008, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068454882619665e-05, + "loss": 3.4918, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060068935109145e-05, + "loss": 3.4974, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.605169936640236e-05, + "loss": 3.4912, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043313418891834e-05, + "loss": 3.4999, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6034927471381314e-05, + "loss": 3.4882, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026541523870797e-05, + "loss": 3.4902, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018171955164013e-05, + "loss": 3.4811, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6009786007653486e-05, + "loss": 3.4931, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001400060142966e-05, + "loss": 3.5018, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993014112632446e-05, + "loss": 3.4912, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984644543925662e-05, + "loss": 3.506, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597625859641514e-05, + "loss": 3.4928, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596787264890462e-05, + "loss": 3.4894, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959503080197834e-05, + "loss": 3.496, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951117132687307e-05, + "loss": 3.4969, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5942731185176787e-05, + "loss": 3.4812, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934345237666267e-05, + "loss": 3.4778, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.592595929015575e-05, + "loss": 3.4828, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.591758972144896e-05, + "loss": 3.4914, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.590920377393844e-05, + "loss": 3.4958, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.590081782642792e-05, + "loss": 3.4949, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.58924318789174e-05, + "loss": 3.479, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884062310210612e-05, + "loss": 3.4954, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5875676362700092e-05, + "loss": 3.4919, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867290415189572e-05, + "loss": 3.4865, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5858904467679052e-05, + "loss": 3.4776, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.585053489897226e-05, + "loss": 3.4711, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.584214895146174e-05, + "loss": 3.5069, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583376300395122e-05, + "loss": 3.4972, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825393435244433e-05, + "loss": 3.4867, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817007487733913e-05, + "loss": 3.4877, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580863791902713e-05, + "loss": 3.4909, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.580025197151661e-05, + "loss": 3.4778, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5791866024006082e-05, + "loss": 3.4935, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783480076495566e-05, + "loss": 3.4811, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775094128985046e-05, + "loss": 3.4906, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766708181474526e-05, + "loss": 3.5052, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758322233964006e-05, + "loss": 3.4845, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5749936286453486e-05, + "loss": 3.4754, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741566717746695e-05, + "loss": 3.5018, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733180770236175e-05, + "loss": 3.4681, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724794822725658e-05, + "loss": 3.4797, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716425254018867e-05, + "loss": 3.5009, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708039306508347e-05, + "loss": 3.4903, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5699653358997827e-05, + "loss": 3.4815, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691267411487307e-05, + "loss": 3.4777, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568289784278052e-05, + "loss": 3.4748, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567451189527e-05, + "loss": 3.4776, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566612594775948e-05, + "loss": 3.4913, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565774000024896e-05, + "loss": 3.4752, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564937043154217e-05, + "loss": 3.4954, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.564098448403165e-05, + "loss": 3.488, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.563259853652113e-05, + "loss": 3.4969, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624212589010608e-05, + "loss": 3.4807, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.561584302030382e-05, + "loss": 3.4837, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.56074570727933e-05, + "loss": 3.4939, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559907112528278e-05, + "loss": 3.4824, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.559068517777226e-05, + "loss": 3.4976, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558231560906547e-05, + "loss": 3.4855, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5573929661554953e-05, + "loss": 3.4859, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565543714044433e-05, + "loss": 3.4859, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557157766533913e-05, + "loss": 3.473, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548788197827122e-05, + "loss": 3.481, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540402250316602e-05, + "loss": 3.4851, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532016302806082e-05, + "loss": 3.4895, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523630355295562e-05, + "loss": 3.4826, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515260786588774e-05, + "loss": 3.4845, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5506874839078254e-05, + "loss": 3.4791, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498488891567734e-05, + "loss": 3.4734, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490102944057214e-05, + "loss": 3.4765, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481733375350423e-05, + "loss": 3.4819, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473347427839907e-05, + "loss": 3.4974, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5464961480329387e-05, + "loss": 3.4962, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456575532818867e-05, + "loss": 3.4874, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448205964112076e-05, + "loss": 3.4781, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5439820016601556e-05, + "loss": 3.4857, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431434069091036e-05, + "loss": 3.4831, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423048121580516e-05, + "loss": 3.4886, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414678552873728e-05, + "loss": 3.4903, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406292605363208e-05, + "loss": 3.4835, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5397906657852688e-05, + "loss": 3.4764, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5389520710342168e-05, + "loss": 3.5019, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381151141635377e-05, + "loss": 3.4721, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537276519412486e-05, + "loss": 3.4876, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536437924661434e-05, + "loss": 3.4792, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535599329910382e-05, + "loss": 3.4874, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.534762373039703e-05, + "loss": 3.4775, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.533923778288651e-05, + "loss": 3.4859, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.533085183537599e-05, + "loss": 3.481, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.532246588786547e-05, + "loss": 3.481, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314096319158682e-05, + "loss": 3.4858, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305710371648162e-05, + "loss": 3.4794, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297324424137642e-05, + "loss": 3.4938, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.528893847662712e-05, + "loss": 3.4986, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.528056890792033e-05, + "loss": 3.4889, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272182960409814e-05, + "loss": 3.4817, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5263797012899294e-05, + "loss": 3.4806, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255411065388774e-05, + "loss": 3.4792, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247041496681983e-05, + "loss": 3.4787, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238655549171463e-05, + "loss": 3.4904, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230269601660943e-05, + "loss": 3.4706, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5221883654150423e-05, + "loss": 3.4853, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213514085443635e-05, + "loss": 3.4827, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205128137933115e-05, + "loss": 3.4917, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196742190422595e-05, + "loss": 3.4781, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188356242912075e-05, + "loss": 3.4841, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5179986674205284e-05, + "loss": 3.481, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171600726694768e-05, + "loss": 3.4938, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163214779184248e-05, + "loss": 3.4868, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5154828831673728e-05, + "loss": 3.4951, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146459262966937e-05, + "loss": 3.4741, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138073315456417e-05, + "loss": 3.4872, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5129687367945897e-05, + "loss": 3.4896, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121301420435377e-05, + "loss": 3.4825, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511293185172859e-05, + "loss": 3.4829, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510454590421807e-05, + "loss": 3.4988, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.509615995670755e-05, + "loss": 3.4878, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087790388000758e-05, + "loss": 3.5034, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079404440490238e-05, + "loss": 3.4793, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.507101849297972e-05, + "loss": 3.4885, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.50626325454692e-05, + "loss": 3.4804, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.505424659795868e-05, + "loss": 3.4817, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.504587702925189e-05, + "loss": 3.4857, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.503749108174137e-05, + "loss": 3.4839, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.502910513423085e-05, + "loss": 3.4807, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.502071918672033e-05, + "loss": 3.4771, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012349618013543e-05, + "loss": 3.4828, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8615081310272217, + "eval_runtime": 304.892, + "eval_samples_per_second": 1251.561, + "eval_steps_per_second": 39.112, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5003963670503023e-05, + "loss": 3.4833, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.49955777229925e-05, + "loss": 3.4792, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498719177548198e-05, + "loss": 3.492, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497880582797146e-05, + "loss": 3.4847, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970436259264672e-05, + "loss": 3.5027, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496205031175415e-05, + "loss": 3.4833, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495366436424363e-05, + "loss": 3.4836, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494527841673311e-05, + "loss": 3.4708, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493690884802632e-05, + "loss": 3.4891, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.49285229005158e-05, + "loss": 3.4836, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920136953005284e-05, + "loss": 3.4825, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911751005494764e-05, + "loss": 3.4803, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903397815591706e-05, + "loss": 3.4747, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895011868081186e-05, + "loss": 3.484, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886625920570662e-05, + "loss": 3.4705, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878239973060145e-05, + "loss": 3.4715, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869854025549625e-05, + "loss": 3.4707, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861468078039105e-05, + "loss": 3.4831, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853082130528585e-05, + "loss": 3.4769, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844696183018065e-05, + "loss": 3.4947, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836326614311274e-05, + "loss": 3.4823, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4827940666800754e-05, + "loss": 3.4919, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819554719290238e-05, + "loss": 3.4796, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811168771779718e-05, + "loss": 3.4822, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802799203072927e-05, + "loss": 3.4801, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794413255562407e-05, + "loss": 3.4892, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786027308051887e-05, + "loss": 3.4768, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777641360541367e-05, + "loss": 3.4796, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476927179183458e-05, + "loss": 3.4708, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476088584432406e-05, + "loss": 3.4765, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475249989681354e-05, + "loss": 3.4896, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474411394930302e-05, + "loss": 3.483, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735744380596228e-05, + "loss": 3.4894, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727358433085708e-05, + "loss": 3.4764, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.471897248557519e-05, + "loss": 3.479, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710586538064668e-05, + "loss": 3.4869, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470221696935788e-05, + "loss": 3.4859, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469383102184736e-05, + "loss": 3.4648, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468544507433684e-05, + "loss": 3.4701, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677059126826317e-05, + "loss": 3.4701, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668689558119533e-05, + "loss": 3.4757, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660303610609013e-05, + "loss": 3.4865, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651917663098493e-05, + "loss": 3.4814, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464353171558797e-05, + "loss": 3.4713, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463516214688118e-05, + "loss": 3.4806, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462677619937066e-05, + "loss": 3.4763, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461839025186014e-05, + "loss": 3.4782, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.461000430434962e-05, + "loss": 3.4699, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601634735642834e-05, + "loss": 3.4532, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593248788132314e-05, + "loss": 3.4947, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458486284062179e-05, + "loss": 3.4834, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457647689311127e-05, + "loss": 3.481, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568107324404486e-05, + "loss": 3.4736, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559737755697695e-05, + "loss": 3.4775, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551351808187175e-05, + "loss": 3.4676, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542965860676655e-05, + "loss": 3.478, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534579913166135e-05, + "loss": 3.4749, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526193965655615e-05, + "loss": 3.4771, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517808018145095e-05, + "loss": 3.4924, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509422070634575e-05, + "loss": 3.4716, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501036123124055e-05, + "loss": 3.4659, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492666554417264e-05, + "loss": 3.4899, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484280606906744e-05, + "loss": 3.4573, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475894659396224e-05, + "loss": 3.4682, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446752509068944e-05, + "loss": 3.4835, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459139143178917e-05, + "loss": 3.4788, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450753195668397e-05, + "loss": 3.4695, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442367248157877e-05, + "loss": 3.468, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4433997679451086e-05, + "loss": 3.4584, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442561173194057e-05, + "loss": 3.4683, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441722578443005e-05, + "loss": 3.4773, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440883983691953e-05, + "loss": 3.4682, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400470268212738e-05, + "loss": 3.4792, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392084320702218e-05, + "loss": 3.4767, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383698373191698e-05, + "loss": 3.4853, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375312425681178e-05, + "loss": 3.4688, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436694285697439e-05, + "loss": 3.4701, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435855690946387e-05, + "loss": 3.4796, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435017096195335e-05, + "loss": 3.4683, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434178501444283e-05, + "loss": 3.4895, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433341544573604e-05, + "loss": 3.4757, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325029498225523e-05, + "loss": 3.4732, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316643550715003e-05, + "loss": 3.4765, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308257603204483e-05, + "loss": 3.4601, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.429988803449769e-05, + "loss": 3.4678, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429150208698717e-05, + "loss": 3.4701, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428311613947665e-05, + "loss": 3.4798, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427473019196613e-05, + "loss": 3.4661, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266360623259344e-05, + "loss": 3.4729, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257974675748824e-05, + "loss": 3.4651, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249588728238304e-05, + "loss": 3.4675, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241202780727784e-05, + "loss": 3.4605, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232833212020993e-05, + "loss": 3.4732, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224447264510476e-05, + "loss": 3.484, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216061316999956e-05, + "loss": 3.4787, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207675369489436e-05, + "loss": 3.4809, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199305800782645e-05, + "loss": 3.4644, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190919853272125e-05, + "loss": 3.4731, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182533905761605e-05, + "loss": 3.4686, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174147958251085e-05, + "loss": 3.4793, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165778389544298e-05, + "loss": 3.4784, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157392442033778e-05, + "loss": 3.4712, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149006494523258e-05, + "loss": 3.4669, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140620547012738e-05, + "loss": 3.4875, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132250978305947e-05, + "loss": 3.4619, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412386503079543e-05, + "loss": 3.4723, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411547908328491e-05, + "loss": 3.4653, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410709313577439e-05, + "loss": 3.4761, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.40987235670676e-05, + "loss": 3.4651, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409033761955708e-05, + "loss": 3.4764, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408195167204656e-05, + "loss": 3.4655, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.407356572453604e-05, + "loss": 3.4727, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406519615582925e-05, + "loss": 3.4747, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405681020831873e-05, + "loss": 3.47, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404842426080821e-05, + "loss": 3.4805, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040038313297688e-05, + "loss": 3.4859, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.40316687445909e-05, + "loss": 3.4736, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023282797080384e-05, + "loss": 3.4743, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014896849569864e-05, + "loss": 3.4657, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400651090205934e-05, + "loss": 3.4717, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998141333352553e-05, + "loss": 3.4656, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989755385842033e-05, + "loss": 3.4801, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398136943833151e-05, + "loss": 3.4575, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972983490820993e-05, + "loss": 3.4725, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964613922114205e-05, + "loss": 3.4713, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956227974603685e-05, + "loss": 3.4774, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394784202709316e-05, + "loss": 3.4697, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393945607958264e-05, + "loss": 3.4718, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931086510875854e-05, + "loss": 3.4683, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922700563365337e-05, + "loss": 3.4781, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914314615854814e-05, + "loss": 3.4775, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905945047148026e-05, + "loss": 3.4811, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897559099637506e-05, + "loss": 3.4623, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889173152126983e-05, + "loss": 3.4765, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880787204616463e-05, + "loss": 3.4784, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387241763590968e-05, + "loss": 3.4702, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386403168839916e-05, + "loss": 3.4728, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855645740888635e-05, + "loss": 3.4834, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847259793378115e-05, + "loss": 3.474, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838890224671328e-05, + "loss": 3.4961, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830504277160808e-05, + "loss": 3.4669, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822118329650288e-05, + "loss": 3.4755, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813732382139768e-05, + "loss": 3.4679, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380536281343298e-05, + "loss": 3.4717, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796976865922457e-05, + "loss": 3.4767, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788590918411937e-05, + "loss": 3.4711, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780204970901416e-05, + "loss": 3.4704, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771835402194632e-05, + "loss": 3.4581, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376344945468411e-05, + "loss": 3.4734, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8610622882843018, + "eval_runtime": 303.3626, + "eval_samples_per_second": 1257.871, + "eval_steps_per_second": 39.309, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375506350717359e-05, + "loss": 3.4749, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374667755966307e-05, + "loss": 3.4679, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.373830799095628e-05, + "loss": 3.4766, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.372992204344576e-05, + "loss": 3.4765, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.372153609593524e-05, + "loss": 3.4872, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.371315014842472e-05, + "loss": 3.4705, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370478057971793e-05, + "loss": 3.4714, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369639463220741e-05, + "loss": 3.46, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368800868469689e-05, + "loss": 3.4756, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.367962273718637e-05, + "loss": 3.471, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671253168479583e-05, + "loss": 3.4745, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662867220969063e-05, + "loss": 3.4642, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654481273458543e-05, + "loss": 3.4705, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646095325948023e-05, + "loss": 3.4663, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363772575724123e-05, + "loss": 3.4631, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629339809730715e-05, + "loss": 3.4555, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620953862220195e-05, + "loss": 3.4611, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612567914709675e-05, + "loss": 3.4695, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604198346002884e-05, + "loss": 3.4649, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595812398492364e-05, + "loss": 3.4824, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587426450981844e-05, + "loss": 3.4725, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579040503471324e-05, + "loss": 3.4801, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570670934764536e-05, + "loss": 3.4667, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562284987254016e-05, + "loss": 3.4694, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553899039743496e-05, + "loss": 3.469, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545513092232976e-05, + "loss": 3.4803, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537143523526185e-05, + "loss": 3.4654, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.352875757601567e-05, + "loss": 3.4663, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.352037162850515e-05, + "loss": 3.4604, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.351198568099463e-05, + "loss": 3.4662, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503616112287838e-05, + "loss": 3.4714, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495230164777318e-05, + "loss": 3.4741, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486844217266798e-05, + "loss": 3.4763, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478458269756277e-05, + "loss": 3.4713, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.347008870104949e-05, + "loss": 3.4676, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346170275353897e-05, + "loss": 3.4749, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345331680602845e-05, + "loss": 3.4723, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.344493085851793e-05, + "loss": 3.4582, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.343656128981114e-05, + "loss": 3.459, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428175342300622e-05, + "loss": 3.4575, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419789394790102e-05, + "loss": 3.4625, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.341141982608331e-05, + "loss": 3.4774, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340303387857279e-05, + "loss": 3.4694, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339464793106227e-05, + "loss": 3.4595, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338626198355175e-05, + "loss": 3.4698, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377892414844964e-05, + "loss": 3.4646, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369506467334444e-05, + "loss": 3.4661, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361120519823924e-05, + "loss": 3.4552, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352734572313404e-05, + "loss": 3.441, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344365003606613e-05, + "loss": 3.4843, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3335979056096093e-05, + "loss": 3.4695, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327593108585573e-05, + "loss": 3.473, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319207161075056e-05, + "loss": 3.4601, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310837592368265e-05, + "loss": 3.4688, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302451644857745e-05, + "loss": 3.4536, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294065697347225e-05, + "loss": 3.4631, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285679749836705e-05, + "loss": 3.466, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277293802326185e-05, + "loss": 3.4653, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268907854815665e-05, + "loss": 3.4828, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260521907305145e-05, + "loss": 3.4587, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252135959794625e-05, + "loss": 3.4525, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243766391087834e-05, + "loss": 3.4793, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235380443577314e-05, + "loss": 3.4446, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3226994496066794e-05, + "loss": 3.4554, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3218608548556277e-05, + "loss": 3.4736, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210238979849486e-05, + "loss": 3.4703, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201853032338966e-05, + "loss": 3.4534, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193467084828446e-05, + "loss": 3.4621, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185097516121655e-05, + "loss": 3.4457, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317671156861114e-05, + "loss": 3.4584, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316832562110062e-05, + "loss": 3.4643, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.31599396735901e-05, + "loss": 3.4547, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151570104883308e-05, + "loss": 3.4672, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143184157372787e-05, + "loss": 3.4665, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134798209862267e-05, + "loss": 3.4766, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126412262351747e-05, + "loss": 3.4549, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311804269364496e-05, + "loss": 3.4632, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310965674613444e-05, + "loss": 3.4693, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310127079862392e-05, + "loss": 3.4561, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.30928848511134e-05, + "loss": 3.4731, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308451528240661e-05, + "loss": 3.4664, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076129334896092e-05, + "loss": 3.462, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067743387385572e-05, + "loss": 3.468, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059357439875052e-05, + "loss": 3.449, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305098787116826e-05, + "loss": 3.4532, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304260192365774e-05, + "loss": 3.4612, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034232354950954e-05, + "loss": 3.4656, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025846407440434e-05, + "loss": 3.4601, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017460459929914e-05, + "loss": 3.4615, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009074512419393e-05, + "loss": 3.4483, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000688564908873e-05, + "loss": 3.4573, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992302617398353e-05, + "loss": 3.4517, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2983916669887833e-05, + "loss": 3.4595, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297553072237731e-05, + "loss": 3.4752, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967161153670526e-05, + "loss": 3.4658, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958775206160006e-05, + "loss": 3.467, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950389258649482e-05, + "loss": 3.455, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942003311138962e-05, + "loss": 3.4608, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933633742432175e-05, + "loss": 3.4584, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925247794921655e-05, + "loss": 3.4692, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916861847411135e-05, + "loss": 3.4606, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908475899900615e-05, + "loss": 3.4671, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900106331193827e-05, + "loss": 3.4535, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891720383683304e-05, + "loss": 3.472, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883334436172784e-05, + "loss": 3.4549, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2874948488662264e-05, + "loss": 3.4597, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286657891995548e-05, + "loss": 3.4523, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858192972444956e-05, + "loss": 3.4671, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849807024934436e-05, + "loss": 3.4556, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.284143745622765e-05, + "loss": 3.4614, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.283305150871713e-05, + "loss": 3.4586, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.282466556120661e-05, + "loss": 3.4617, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281627961369609e-05, + "loss": 3.4585, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.28079100449893e-05, + "loss": 3.4575, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799524097478777e-05, + "loss": 3.4675, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2791138149968257e-05, + "loss": 3.4735, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782752202457737e-05, + "loss": 3.4636, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277438263375095e-05, + "loss": 3.466, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276599668624043e-05, + "loss": 3.4523, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275761073872991e-05, + "loss": 3.4576, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274922479121939e-05, + "loss": 3.4602, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740855222512602e-05, + "loss": 3.4658, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.273246927500208e-05, + "loss": 3.446, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724083327491562e-05, + "loss": 3.4612, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715697379981042e-05, + "loss": 3.4611, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.270732781127425e-05, + "loss": 3.464, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.269894186376373e-05, + "loss": 3.4592, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.269055591625321e-05, + "loss": 3.4605, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268216996874269e-05, + "loss": 3.4571, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673800400035903e-05, + "loss": 3.4689, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665414452525383e-05, + "loss": 3.4664, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657028505014863e-05, + "loss": 3.4715, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648642557504343e-05, + "loss": 3.452, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640272988797552e-05, + "loss": 3.4642, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631887041287032e-05, + "loss": 3.4656, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623501093776516e-05, + "loss": 3.4588, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615115146265996e-05, + "loss": 3.4603, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606745577559205e-05, + "loss": 3.4696, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598359630048685e-05, + "loss": 3.4651, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589973682538165e-05, + "loss": 3.4788, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581587735027645e-05, + "loss": 3.4604, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573218166320857e-05, + "loss": 3.4639, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564832218810337e-05, + "loss": 3.4601, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556446271299817e-05, + "loss": 3.4618, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548060323789297e-05, + "loss": 3.4582, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539690755082506e-05, + "loss": 3.4565, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531304807571986e-05, + "loss": 3.4636, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522918860061466e-05, + "loss": 3.4443, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251453291255095e-05, + "loss": 3.465, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8627467155456543, + "eval_runtime": 302.6277, + "eval_samples_per_second": 1260.926, + "eval_steps_per_second": 39.405, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250614696504043e-05, + "loss": 3.4661, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497761017529906e-05, + "loss": 3.4574, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489375070019386e-05, + "loss": 3.464, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2480989122508866e-05, + "loss": 3.4645, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472619553802078e-05, + "loss": 3.4767, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464233606291558e-05, + "loss": 3.4586, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2455847658781038e-05, + "loss": 3.4612, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2447461711270518e-05, + "loss": 3.4504, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243909214256373e-05, + "loss": 3.4659, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430706195053207e-05, + "loss": 3.4618, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422320247542687e-05, + "loss": 3.4611, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.241393430003217e-05, + "loss": 3.4527, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405581110129112e-05, + "loss": 3.4558, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397195162618592e-05, + "loss": 3.4514, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388809215108072e-05, + "loss": 3.4568, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380423267597552e-05, + "loss": 3.4455, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372037320087032e-05, + "loss": 3.4498, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363651372576512e-05, + "loss": 3.4562, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355265425065992e-05, + "loss": 3.4556, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346879477555472e-05, + "loss": 3.4684, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233850990884868e-05, + "loss": 3.4647, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.233012396133816e-05, + "loss": 3.4699, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.232173801382764e-05, + "loss": 3.4507, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313352066317124e-05, + "loss": 3.4604, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304982497610333e-05, + "loss": 3.4577, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296596550099813e-05, + "loss": 3.4669, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288210602589293e-05, + "loss": 3.4536, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279824655078773e-05, + "loss": 3.4584, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271455086371986e-05, + "loss": 3.452, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263069138861466e-05, + "loss": 3.4529, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254683191350945e-05, + "loss": 3.4582, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246297243840425e-05, + "loss": 3.4666, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237927675133635e-05, + "loss": 3.4649, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229541727623114e-05, + "loss": 3.4627, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221155780112594e-05, + "loss": 3.4552, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212769832602078e-05, + "loss": 3.459, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204400263895287e-05, + "loss": 3.4615, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196014316384767e-05, + "loss": 3.4494, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187628368874247e-05, + "loss": 3.4438, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179258800167456e-05, + "loss": 3.443, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.217087285265694e-05, + "loss": 3.4514, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216248690514642e-05, + "loss": 3.4598, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.21541009576359e-05, + "loss": 3.4612, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145731388929108e-05, + "loss": 3.4514, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137345441418588e-05, + "loss": 3.4555, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2128959493908068e-05, + "loss": 3.4564, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120573546397548e-05, + "loss": 3.4571, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.211220397769076e-05, + "loss": 3.4441, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210381803018024e-05, + "loss": 3.4297, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209543208266972e-05, + "loss": 3.4717, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.20870461351592e-05, + "loss": 3.4559, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207867656645241e-05, + "loss": 3.4632, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.207029061894189e-05, + "loss": 3.4507, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061921050235102e-05, + "loss": 3.4543, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053535102724582e-05, + "loss": 3.4439, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045149155214062e-05, + "loss": 3.451, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2036763207703542e-05, + "loss": 3.4583, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028377260193022e-05, + "loss": 3.4508, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2019991312682502e-05, + "loss": 3.4713, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011605365171982e-05, + "loss": 3.4517, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003219417661462e-05, + "loss": 3.442, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994849848954674e-05, + "loss": 3.4664, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986463901444154e-05, + "loss": 3.4371, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197807795393363e-05, + "loss": 3.4378, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196969200642311e-05, + "loss": 3.4664, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961322437716327e-05, + "loss": 3.4601, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952936490205803e-05, + "loss": 3.4415, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944550542695283e-05, + "loss": 3.4518, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936164595184763e-05, + "loss": 3.4354, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927795026477975e-05, + "loss": 3.4486, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919409078967455e-05, + "loss": 3.4514, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911023131456935e-05, + "loss": 3.4457, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902653562750148e-05, + "loss": 3.4566, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894267615239628e-05, + "loss": 3.4547, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885881667729104e-05, + "loss": 3.4623, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877495720218584e-05, + "loss": 3.4437, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869126151511797e-05, + "loss": 3.4514, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860740204001277e-05, + "loss": 3.4558, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185237063529449e-05, + "loss": 3.4466, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.184398468778397e-05, + "loss": 3.46, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.183559874027345e-05, + "loss": 3.4543, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827212792762926e-05, + "loss": 3.4477, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.181882684525241e-05, + "loss": 3.4618, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181044089774189e-05, + "loss": 3.4358, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180205495023137e-05, + "loss": 3.4432, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179366900272085e-05, + "loss": 3.4511, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178531581281779e-05, + "loss": 3.4522, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177692986530727e-05, + "loss": 3.4474, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.176854391779675e-05, + "loss": 3.4509, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.176015797028623e-05, + "loss": 3.4345, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175177202277571e-05, + "loss": 3.4488, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174338607526519e-05, + "loss": 3.4396, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173500012775467e-05, + "loss": 3.4504, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172661418024415e-05, + "loss": 3.4628, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718244611537363e-05, + "loss": 3.4538, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709858664026843e-05, + "loss": 3.4556, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701472716516323e-05, + "loss": 3.4449, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693086769005803e-05, + "loss": 3.4483, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684717200299012e-05, + "loss": 3.4448, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676331252788492e-05, + "loss": 3.461, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166794530527797e-05, + "loss": 3.4505, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165955935776745e-05, + "loss": 3.4562, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651189789060664e-05, + "loss": 3.4411, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642803841550144e-05, + "loss": 3.4588, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634417894039624e-05, + "loss": 3.4487, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626031946529104e-05, + "loss": 3.4483, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617662377822313e-05, + "loss": 3.4406, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609276430311796e-05, + "loss": 3.4557, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600890482801276e-05, + "loss": 3.4436, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592504535290753e-05, + "loss": 3.4523, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584134966583965e-05, + "loss": 3.4408, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575749019073445e-05, + "loss": 3.4541, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567363071562925e-05, + "loss": 3.4468, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1558977124052405e-05, + "loss": 3.4457, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550607555345618e-05, + "loss": 3.4577, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542221607835098e-05, + "loss": 3.4611, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533835660324578e-05, + "loss": 3.4557, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525466091617787e-05, + "loss": 3.4513, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517096522911e-05, + "loss": 3.4449, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150871057540048e-05, + "loss": 3.4464, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150032462788996e-05, + "loss": 3.4472, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149193868037944e-05, + "loss": 3.4507, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.148355273286892e-05, + "loss": 3.4375, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.14751667853584e-05, + "loss": 3.4492, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146678083784788e-05, + "loss": 3.4513, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145839489033736e-05, + "loss": 3.4537, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.145002532163057e-05, + "loss": 3.4484, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144163937412005e-05, + "loss": 3.4481, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433253426609528e-05, + "loss": 3.4454, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424867479099008e-05, + "loss": 3.4589, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141649791039222e-05, + "loss": 3.457, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.14081119628817e-05, + "loss": 3.4564, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.139972601537118e-05, + "loss": 3.4408, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139134006786066e-05, + "loss": 3.4568, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1382970499153873e-05, + "loss": 3.4513, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137458455164335e-05, + "loss": 3.4468, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366198604132833e-05, + "loss": 3.4522, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357829035426045e-05, + "loss": 3.4554, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349443087915525e-05, + "loss": 3.4538, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341057140405e-05, + "loss": 3.4678, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133267119289448e-05, + "loss": 3.4467, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324301624187694e-05, + "loss": 3.4533, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1315915676677174e-05, + "loss": 3.4527, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307529729166654e-05, + "loss": 3.4517, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299143781656134e-05, + "loss": 3.4457, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290774212949346e-05, + "loss": 3.4445, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282388265438823e-05, + "loss": 3.452, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274002317928303e-05, + "loss": 3.4364, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265616370417786e-05, + "loss": 3.4547, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8663766384124756, + "eval_runtime": 306.7692, + "eval_samples_per_second": 1243.903, + "eval_steps_per_second": 38.873, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257246801711e-05, + "loss": 3.4544, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248860854200475e-05, + "loss": 3.4437, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240474906689955e-05, + "loss": 3.4526, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232088959179435e-05, + "loss": 3.4541, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223719390472648e-05, + "loss": 3.4664, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215333442962128e-05, + "loss": 3.4471, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1206947495451608e-05, + "loss": 3.4538, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1198561547941088e-05, + "loss": 3.4441, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1190191979234297e-05, + "loss": 3.4456, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181806031723777e-05, + "loss": 3.4555, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173420084213257e-05, + "loss": 3.4496, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165034136702737e-05, + "loss": 3.44, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115666456799595e-05, + "loss": 3.4531, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114827862048543e-05, + "loss": 3.4383, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113989267297491e-05, + "loss": 3.439, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113150672546439e-05, + "loss": 3.4387, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1123137156757598e-05, + "loss": 3.4377, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111475120924708e-05, + "loss": 3.4479, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110636526173656e-05, + "loss": 3.4392, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109797931422604e-05, + "loss": 3.4605, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108960974551925e-05, + "loss": 3.4511, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108122379800873e-05, + "loss": 3.4578, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107283785049821e-05, + "loss": 3.4437, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106445190298769e-05, + "loss": 3.4466, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056082334280903e-05, + "loss": 3.4522, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047696386770383e-05, + "loss": 3.4547, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039310439259863e-05, + "loss": 3.4406, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1030924491749343e-05, + "loss": 3.4493, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022554923042552e-05, + "loss": 3.4387, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014168975532035e-05, + "loss": 3.4417, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005799406825244e-05, + "loss": 3.4458, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997413459314724e-05, + "loss": 3.4556, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989027511804204e-05, + "loss": 3.4536, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980641564293684e-05, + "loss": 3.4525, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972255616783164e-05, + "loss": 3.4449, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963869669272644e-05, + "loss": 3.4463, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955483721762124e-05, + "loss": 3.4541, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947097774251604e-05, + "loss": 3.4403, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938728205544816e-05, + "loss": 3.4367, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930342258034296e-05, + "loss": 3.4333, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0921956310523773e-05, + "loss": 3.4396, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913570363013256e-05, + "loss": 3.4448, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.090520079430647e-05, + "loss": 3.4508, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089681484679595e-05, + "loss": 3.4431, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888428899285425e-05, + "loss": 3.4425, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0880042951774905e-05, + "loss": 3.4452, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871673383068118e-05, + "loss": 3.4487, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863287435557598e-05, + "loss": 3.4331, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0854901488047078e-05, + "loss": 3.4188, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0846515540536558e-05, + "loss": 3.4545, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083814597182977e-05, + "loss": 3.4476, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0829760024319247e-05, + "loss": 3.4529, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0821374076808727e-05, + "loss": 3.44, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081298812929821e-05, + "loss": 3.4427, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0804618560591422e-05, + "loss": 3.4342, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.07962326130809e-05, + "loss": 3.4387, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078784666557038e-05, + "loss": 3.4518, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.077946071805986e-05, + "loss": 3.4348, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077109114935307e-05, + "loss": 3.4628, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.076270520184255e-05, + "loss": 3.4436, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754335633135764e-05, + "loss": 3.426, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0745949685625244e-05, + "loss": 3.4551, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073756373811472e-05, + "loss": 3.4279, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.07291777906042e-05, + "loss": 3.4251, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.072079184309368e-05, + "loss": 3.4551, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071240589558316e-05, + "loss": 3.4458, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704019948072643e-05, + "loss": 3.4319, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695634000562123e-05, + "loss": 3.4396, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687264431855333e-05, + "loss": 3.4263, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0678878484344813e-05, + "loss": 3.4366, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670492536834292e-05, + "loss": 3.438, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662122968127505e-05, + "loss": 3.4348, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653737020616985e-05, + "loss": 3.4457, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645351073106465e-05, + "loss": 3.4387, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0636965125595945e-05, + "loss": 3.4514, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628579178085425e-05, + "loss": 3.4343, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.06201932305749e-05, + "loss": 3.4457, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.061180728306438e-05, + "loss": 3.4419, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603421335553865e-05, + "loss": 3.4356, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0595051766847077e-05, + "loss": 3.4506, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586665819336554e-05, + "loss": 3.4468, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578279871826034e-05, + "loss": 3.4346, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0569893924315514e-05, + "loss": 3.4496, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0561524355608726e-05, + "loss": 3.4255, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0553138408098206e-05, + "loss": 3.4287, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544752460587686e-05, + "loss": 3.4435, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.05363828918809e-05, + "loss": 3.4418, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0527996944370375e-05, + "loss": 3.4373, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519610996859855e-05, + "loss": 3.4458, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511225049349335e-05, + "loss": 3.4256, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0502839101838818e-05, + "loss": 3.4348, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0494453154328298e-05, + "loss": 3.4311, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0486067206817778e-05, + "loss": 3.4362, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477681259307258e-05, + "loss": 3.4538, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469311690600467e-05, + "loss": 3.4418, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460925743089947e-05, + "loss": 3.4473, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452539795579427e-05, + "loss": 3.4317, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444153848068907e-05, + "loss": 3.4381, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043578427936212e-05, + "loss": 3.4347, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.04273983318516e-05, + "loss": 3.4467, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041901238434108e-05, + "loss": 3.4387, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410626436830556e-05, + "loss": 3.4463, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.040225686812377e-05, + "loss": 3.4336, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393870920613252e-05, + "loss": 3.4426, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385484973102732e-05, + "loss": 3.4412, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037709902559221e-05, + "loss": 3.4367, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036872945688542e-05, + "loss": 3.4293, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.036035988817863e-05, + "loss": 3.4478, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0351973940668113e-05, + "loss": 3.4326, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343587993157593e-05, + "loss": 3.439, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335202045647073e-05, + "loss": 3.4295, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0326832476940282e-05, + "loss": 3.4422, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318446529429762e-05, + "loss": 3.4385, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0310060581919242e-05, + "loss": 3.4359, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301674634408722e-05, + "loss": 3.4436, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293288686898202e-05, + "loss": 3.4534, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0284902739387682e-05, + "loss": 3.4495, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276516791877162e-05, + "loss": 3.4381, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268147223170375e-05, + "loss": 3.4335, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025976127565985e-05, + "loss": 3.4336, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251375328149335e-05, + "loss": 3.4375, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0242989380638814e-05, + "loss": 3.4383, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234603433128294e-05, + "loss": 3.4289, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226217485617774e-05, + "loss": 3.4393, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0217831538107254e-05, + "loss": 3.4439, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0209445590596734e-05, + "loss": 3.439, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0201076021889943e-05, + "loss": 3.4375, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192690074379427e-05, + "loss": 3.4404, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184304126868907e-05, + "loss": 3.4332, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0175918179358383e-05, + "loss": 3.4451, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167548610651596e-05, + "loss": 3.4427, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159162663141076e-05, + "loss": 3.4474, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0150776715630556e-05, + "loss": 3.4312, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0142390768120036e-05, + "loss": 3.4422, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0134021199413248e-05, + "loss": 3.4415, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125635251902728e-05, + "loss": 3.4392, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117249304392208e-05, + "loss": 3.4396, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0108863356881685e-05, + "loss": 3.4414, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100493788174897e-05, + "loss": 3.4437, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092107840664377e-05, + "loss": 3.46, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0083721893153857e-05, + "loss": 3.4325, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.007535232444707e-05, + "loss": 3.4446, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.006696637693655e-05, + "loss": 3.4406, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.005858042942603e-05, + "loss": 3.439, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050194481915506e-05, + "loss": 3.4351, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041824913208722e-05, + "loss": 3.432, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033438965698202e-05, + "loss": 3.4413, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025053018187682e-05, + "loss": 3.4258, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0016667070677158e-05, + "loss": 3.4431, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8673503398895264, + "eval_runtime": 305.0573, + "eval_samples_per_second": 1250.883, + "eval_steps_per_second": 39.091, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008281123166638e-05, + "loss": 3.4421, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999895175656118e-05, + "loss": 3.4357, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991509228145598e-05, + "loss": 3.4411, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.998312328063508e-05, + "loss": 3.4421, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997475371192829e-05, + "loss": 3.4519, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996636776441777e-05, + "loss": 3.4361, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995798181690725e-05, + "loss": 3.4462, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.994959586939673e-05, + "loss": 3.4312, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941226300689943e-05, + "loss": 3.4347, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932840353179423e-05, + "loss": 3.4468, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924454405668903e-05, + "loss": 3.4371, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916068458158383e-05, + "loss": 3.4293, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907715268255324e-05, + "loss": 3.4449, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899329320744804e-05, + "loss": 3.4245, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890943373234284e-05, + "loss": 3.4309, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882557425723764e-05, + "loss": 3.4214, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874171478213244e-05, + "loss": 3.4298, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865785530702724e-05, + "loss": 3.4384, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857399583192204e-05, + "loss": 3.4278, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9849013635681684e-05, + "loss": 3.4475, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840644066974897e-05, + "loss": 3.444, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832258119464377e-05, + "loss": 3.4457, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823872171953857e-05, + "loss": 3.4341, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815486224443336e-05, + "loss": 3.4371, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807116655736546e-05, + "loss": 3.442, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798730708226026e-05, + "loss": 3.442, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790344760715505e-05, + "loss": 3.4294, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9781958813204985e-05, + "loss": 3.4397, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773589244498198e-05, + "loss": 3.4267, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765203296987678e-05, + "loss": 3.4317, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756817349477158e-05, + "loss": 3.4351, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748431401966634e-05, + "loss": 3.4413, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.974007821206358e-05, + "loss": 3.4435, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973169226455306e-05, + "loss": 3.4441, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972330631704254e-05, + "loss": 3.429, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971492036953202e-05, + "loss": 3.4377, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.97065344220215e-05, + "loss": 3.4413, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969814847451098e-05, + "loss": 3.4265, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.968976252700046e-05, + "loss": 3.4282, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.968137657948994e-05, + "loss": 3.4234, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967300701078315e-05, + "loss": 3.4248, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966462106327263e-05, + "loss": 3.4346, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9656235115762108e-05, + "loss": 3.4423, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9647849168251588e-05, + "loss": 3.431, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.96394795995448e-05, + "loss": 3.4313, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.963109365203428e-05, + "loss": 3.4302, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.962270770452376e-05, + "loss": 3.4409, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961432175701324e-05, + "loss": 3.4206, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9605952188306453e-05, + "loss": 3.4099, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959756624079593e-05, + "loss": 3.4435, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589180293285413e-05, + "loss": 3.4365, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580794345774893e-05, + "loss": 3.4418, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572424777068105e-05, + "loss": 3.4288, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564055208361314e-05, + "loss": 3.4318, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555669260850794e-05, + "loss": 3.4266, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9547283313340274e-05, + "loss": 3.4294, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9538897365829754e-05, + "loss": 3.4399, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530511418319234e-05, + "loss": 3.4214, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522125470808714e-05, + "loss": 3.4537, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513739523298194e-05, + "loss": 3.4291, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505369954591403e-05, + "loss": 3.4139, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9496984007080883e-05, + "loss": 3.4463, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488598059570366e-05, + "loss": 3.4244, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480212112059846e-05, + "loss": 3.4123, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471826164549326e-05, + "loss": 3.4417, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463440217038806e-05, + "loss": 3.436, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455054269528286e-05, + "loss": 3.4246, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446668322017763e-05, + "loss": 3.4266, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438298753310975e-05, + "loss": 3.4148, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.942991280580046e-05, + "loss": 3.423, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421526858289935e-05, + "loss": 3.4326, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413157289583148e-05, + "loss": 3.4246, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404771342072628e-05, + "loss": 3.4317, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396385394562108e-05, + "loss": 3.4282, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9387999447051584e-05, + "loss": 3.4395, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379613499541068e-05, + "loss": 3.425, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371227552030548e-05, + "loss": 3.434, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362841604520027e-05, + "loss": 3.429, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354455657009507e-05, + "loss": 3.4258, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346086088302717e-05, + "loss": 3.4414, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337700140792196e-05, + "loss": 3.4333, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9329314193281676e-05, + "loss": 3.4267, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.932092824577116e-05, + "loss": 3.4372, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931255867706437e-05, + "loss": 3.4158, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930417272955385e-05, + "loss": 3.4207, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929578678204333e-05, + "loss": 3.43, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.928740083453281e-05, + "loss": 3.4329, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.927901488702229e-05, + "loss": 3.4215, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.927062893951177e-05, + "loss": 3.4344, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.926224299200125e-05, + "loss": 3.419, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925387342329446e-05, + "loss": 3.4212, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924548747578394e-05, + "loss": 3.4186, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9237101528273418e-05, + "loss": 3.4276, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228715580762898e-05, + "loss": 3.4417, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220346012056113e-05, + "loss": 3.4301, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.921196006454559e-05, + "loss": 3.4365, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9203590495838803e-05, + "loss": 3.4224, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9195204548328282e-05, + "loss": 3.427, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186818600817762e-05, + "loss": 3.4237, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917843265330724e-05, + "loss": 3.4364, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9170046705796722e-05, + "loss": 3.4299, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161660758286202e-05, + "loss": 3.4327, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153274810775682e-05, + "loss": 3.4285, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9144888863265162e-05, + "loss": 3.43, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913651929455837e-05, + "loss": 3.4312, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912813334704785e-05, + "loss": 3.4273, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.911974739953733e-05, + "loss": 3.4179, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111377830830544e-05, + "loss": 3.435, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9102991883320024e-05, + "loss": 3.4248, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094605935809504e-05, + "loss": 3.4257, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086219988298984e-05, + "loss": 3.4241, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077850419592193e-05, + "loss": 3.4271, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069464472081676e-05, + "loss": 3.4277, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061078524571156e-05, + "loss": 3.4222, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052692577060636e-05, + "loss": 3.4381, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044306629550116e-05, + "loss": 3.4392, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9035920682039592e-05, + "loss": 3.4356, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027534734529072e-05, + "loss": 3.426, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019165165822285e-05, + "loss": 3.4286, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010779218311768e-05, + "loss": 3.4236, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002393270801245e-05, + "loss": 3.4273, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994007323290725e-05, + "loss": 3.4302, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985621375780205e-05, + "loss": 3.4168, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977235428269685e-05, + "loss": 3.4254, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8968849480759165e-05, + "loss": 3.43, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8960463533248645e-05, + "loss": 3.4303, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8952093964541857e-05, + "loss": 3.4241, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943708017031337e-05, + "loss": 3.4307, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935322069520817e-05, + "loss": 3.4219, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8926936122010297e-05, + "loss": 3.438, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918566553303506e-05, + "loss": 3.4312, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910180605792986e-05, + "loss": 3.4394, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890179465828247e-05, + "loss": 3.4209, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889340871077195e-05, + "loss": 3.4292, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888503914206516e-05, + "loss": 3.433, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887665319455464e-05, + "loss": 3.427, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868267247044118e-05, + "loss": 3.4278, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8859881299533598e-05, + "loss": 3.4319, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.885152810963054e-05, + "loss": 3.4322, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884314216212002e-05, + "loss": 3.4485, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.88347562146095e-05, + "loss": 3.4271, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.882637026709898e-05, + "loss": 3.4312, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.881798431958846e-05, + "loss": 3.434, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.880959837207794e-05, + "loss": 3.4257, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801212424567423e-05, + "loss": 3.4247, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.87928264770569e-05, + "loss": 3.4224, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784456908350112e-05, + "loss": 3.4293, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776070960839592e-05, + "loss": 3.4213, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767685013329072e-05, + "loss": 3.4279, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.8685896396636963, + "eval_runtime": 306.3937, + "eval_samples_per_second": 1245.427, + "eval_steps_per_second": 38.921, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8759299065818552e-05, + "loss": 3.4295, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8750929497111764e-05, + "loss": 3.423, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742543549601244e-05, + "loss": 3.4287, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.873415760209072e-05, + "loss": 3.4347, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.87257716545802e-05, + "loss": 3.4452, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717402085873413e-05, + "loss": 3.4255, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8709016138362893e-05, + "loss": 3.4288, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700630190852373e-05, + "loss": 3.4229, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8692244243341853e-05, + "loss": 3.4267, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8683874674635066e-05, + "loss": 3.4306, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675488727124546e-05, + "loss": 3.4308, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8667102779614022e-05, + "loss": 3.4192, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658733210907238e-05, + "loss": 3.433, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8650347263396718e-05, + "loss": 3.4144, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8641961315886195e-05, + "loss": 3.4179, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633575368375675e-05, + "loss": 3.4074, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625189420865155e-05, + "loss": 3.4232, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8616803473354634e-05, + "loss": 3.4277, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8608417525844114e-05, + "loss": 3.4189, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8600031578333594e-05, + "loss": 3.4342, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591662009626807e-05, + "loss": 3.4328, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583276062116287e-05, + "loss": 3.4375, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8574890114605767e-05, + "loss": 3.4267, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566504167095247e-05, + "loss": 3.4246, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8558134598388456e-05, + "loss": 3.4272, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854974865087794e-05, + "loss": 3.434, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.854136270336742e-05, + "loss": 3.4155, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.85329767558569e-05, + "loss": 3.4292, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524607187150108e-05, + "loss": 3.414, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516221239639588e-05, + "loss": 3.4217, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8507835292129068e-05, + "loss": 3.4267, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.849946572342228e-05, + "loss": 3.4319, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.849107977591176e-05, + "loss": 3.4262, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.848269382840124e-05, + "loss": 3.4387, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.847430788089072e-05, + "loss": 3.4197, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.84659219333802e-05, + "loss": 3.4249, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457535985869677e-05, + "loss": 3.4314, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.844915003835916e-05, + "loss": 3.4144, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440780469652373e-05, + "loss": 3.4154, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.843239452214185e-05, + "loss": 3.417, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.842400857463133e-05, + "loss": 3.4145, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.841562262712081e-05, + "loss": 3.422, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.840723667961029e-05, + "loss": 3.4354, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.839885073209977e-05, + "loss": 3.4181, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.839046478458925e-05, + "loss": 3.4207, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8382078837078732e-05, + "loss": 3.4205, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837370926837194e-05, + "loss": 3.4284, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.836532332086142e-05, + "loss": 3.4099, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.83569373733509e-05, + "loss": 3.4031, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8348551425840378e-05, + "loss": 3.4329, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8340181857133594e-05, + "loss": 3.4262, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331795909623074e-05, + "loss": 3.4359, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323409962112554e-05, + "loss": 3.4156, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8315040393405763e-05, + "loss": 3.419, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8306654445895243e-05, + "loss": 3.4152, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8298268498384723e-05, + "loss": 3.4167, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8289898929677935e-05, + "loss": 3.4327, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281512982167415e-05, + "loss": 3.4069, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273127034656895e-05, + "loss": 3.4451, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264741087146375e-05, + "loss": 3.4236, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256371518439584e-05, + "loss": 3.4015, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8247985570929064e-05, + "loss": 3.4303, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239599623418548e-05, + "loss": 3.4151, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8231213675908028e-05, + "loss": 3.4039, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8222827728397504e-05, + "loss": 3.4283, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214441780886984e-05, + "loss": 3.4286, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206055833376464e-05, + "loss": 3.4103, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197669885865944e-05, + "loss": 3.4166, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.8189300317159156e-05, + "loss": 3.4039, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8180914369648636e-05, + "loss": 3.4145, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8172528422138116e-05, + "loss": 3.4214, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164158853431325e-05, + "loss": 3.4111, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8155772905920805e-05, + "loss": 3.4268, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8147386958410285e-05, + "loss": 3.4123, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813900101089977e-05, + "loss": 3.4337, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.813061506338925e-05, + "loss": 3.4153, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.812222911587873e-05, + "loss": 3.4246, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.811384316836821e-05, + "loss": 3.4192, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8105473599661418e-05, + "loss": 3.4162, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8097087652150898e-05, + "loss": 3.4282, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088701704640378e-05, + "loss": 3.4187, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080315757129858e-05, + "loss": 3.4234, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8071929809619338e-05, + "loss": 3.4231, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806356024091255e-05, + "loss": 3.4131, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.805517429340203e-05, + "loss": 3.4022, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046788345891507e-05, + "loss": 3.4182, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8038402398380986e-05, + "loss": 3.4235, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.803001645087047e-05, + "loss": 3.4112, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.802163050335995e-05, + "loss": 3.421, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801324455584943e-05, + "loss": 3.4078, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.800485860833891e-05, + "loss": 3.412, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.799648903963212e-05, + "loss": 3.4091, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.79881030921216e-05, + "loss": 3.4182, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.797973352341481e-05, + "loss": 3.428, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.797134757590429e-05, + "loss": 3.4185, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.796296162839377e-05, + "loss": 3.4268, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795457568088325e-05, + "loss": 3.4145, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.794618973337273e-05, + "loss": 3.4188, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.793782016466594e-05, + "loss": 3.4156, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7929434217155424e-05, + "loss": 3.4244, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7921048269644903e-05, + "loss": 3.4185, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912662322134383e-05, + "loss": 3.4246, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904276374623863e-05, + "loss": 3.4177, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.789589042711334e-05, + "loss": 3.4158, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.788750447960282e-05, + "loss": 3.4245, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7879134910896032e-05, + "loss": 3.4129, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7870748963385516e-05, + "loss": 3.4101, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862379394678725e-05, + "loss": 3.423, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7853993447168205e-05, + "loss": 3.4154, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845607499657685e-05, + "loss": 3.4142, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.783722155214716e-05, + "loss": 3.4134, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782883560463664e-05, + "loss": 3.4133, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7820449657126125e-05, + "loss": 3.4222, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7812063709615605e-05, + "loss": 3.4114, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803694140908814e-05, + "loss": 3.424, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7795308193398294e-05, + "loss": 3.4266, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7786922245887774e-05, + "loss": 3.4276, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7778536298377254e-05, + "loss": 3.418, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7770166729670466e-05, + "loss": 3.4179, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7761780782159946e-05, + "loss": 3.41, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7753394834649426e-05, + "loss": 3.423, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7745008887138906e-05, + "loss": 3.4164, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736622939628386e-05, + "loss": 3.409, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.7728236992117866e-05, + "loss": 3.4139, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.7719851044607342e-05, + "loss": 3.4183, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.7711465097096826e-05, + "loss": 3.4229, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7703095528390038e-05, + "loss": 3.4168, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694709580879518e-05, + "loss": 3.4173, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686323633368995e-05, + "loss": 3.4109, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7677937685858475e-05, + "loss": 3.4287, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7669568117151687e-05, + "loss": 3.4212, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7661182169641167e-05, + "loss": 3.4297, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7652796222130647e-05, + "loss": 3.411, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7644410274620127e-05, + "loss": 3.4192, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.763604070591334e-05, + "loss": 3.4227, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627654758402816e-05, + "loss": 3.4156, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619285189696032e-05, + "loss": 3.4176, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7610899242185512e-05, + "loss": 3.4191, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602513294674992e-05, + "loss": 3.4272, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.759412734716447e-05, + "loss": 3.431, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.758574139965395e-05, + "loss": 3.4216, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.757735545214343e-05, + "loss": 3.42, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7568969504632908e-05, + "loss": 3.424, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560583557122388e-05, + "loss": 3.4137, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.75522139884156e-05, + "loss": 3.4161, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.754382804090508e-05, + "loss": 3.4144, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.753544209339456e-05, + "loss": 3.4173, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.752707252468777e-05, + "loss": 3.4125, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.751868657717725e-05, + "loss": 3.4188, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8693342208862305, + "eval_runtime": 303.1561, + "eval_samples_per_second": 1258.728, + "eval_steps_per_second": 39.336, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510300629666733e-05, + "loss": 3.4196, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7501914682156213e-05, + "loss": 3.4135, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493528734645693e-05, + "loss": 3.4186, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485142787135173e-05, + "loss": 3.4235, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7476773218428382e-05, + "loss": 3.4349, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468387270917862e-05, + "loss": 3.4148, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7460001323407342e-05, + "loss": 3.4231, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451615375896822e-05, + "loss": 3.4118, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7443245807190034e-05, + "loss": 3.4149, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7434859859679514e-05, + "loss": 3.417, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7426473912168994e-05, + "loss": 3.4228, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741808796465847e-05, + "loss": 3.4116, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7409734774755416e-05, + "loss": 3.4216, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401348827244896e-05, + "loss": 3.4045, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7392962879734376e-05, + "loss": 3.4086, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384576932223856e-05, + "loss": 3.3946, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376190984713336e-05, + "loss": 3.4161, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7367805037202816e-05, + "loss": 3.4165, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7359419089692296e-05, + "loss": 3.4077, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7351033142181776e-05, + "loss": 3.4224, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342663573474988e-05, + "loss": 3.424, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7334277625964468e-05, + "loss": 3.4247, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7325891678453945e-05, + "loss": 3.4141, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317522109747157e-05, + "loss": 3.4149, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730913616223664e-05, + "loss": 3.4204, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.730075021472612e-05, + "loss": 3.422, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7292364267215597e-05, + "loss": 3.4059, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7283978319705077e-05, + "loss": 3.4178, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275592372194557e-05, + "loss": 3.4086, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267206424684037e-05, + "loss": 3.4072, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725883685597725e-05, + "loss": 3.4169, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7250467287270462e-05, + "loss": 3.4214, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.724208133975994e-05, + "loss": 3.4202, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233695392249418e-05, + "loss": 3.4246, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7225309444738898e-05, + "loss": 3.4111, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7216923497228378e-05, + "loss": 3.4173, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208537549717858e-05, + "loss": 3.4223, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.720015160220734e-05, + "loss": 3.4029, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.719178203350055e-05, + "loss": 3.4055, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.718339608599003e-05, + "loss": 3.4092, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717501013847951e-05, + "loss": 3.3987, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.716662419096899e-05, + "loss": 3.412, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.715823824345847e-05, + "loss": 3.4259, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.714985229594795e-05, + "loss": 3.4089, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.714146634843743e-05, + "loss": 3.4112, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.713308040092691e-05, + "loss": 3.4146, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7124710832220123e-05, + "loss": 3.4174, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.71163248847096e-05, + "loss": 3.3987, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.710793893719908e-05, + "loss": 3.3919, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099552989688563e-05, + "loss": 3.4194, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.709118342098177e-05, + "loss": 3.4159, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.708279747347125e-05, + "loss": 3.4269, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.707441152596073e-05, + "loss": 3.4054, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.706602557845021e-05, + "loss": 3.4071, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057656009743424e-05, + "loss": 3.4065, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7049270062232904e-05, + "loss": 3.4065, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7040884114722384e-05, + "loss": 3.4219, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032514546015596e-05, + "loss": 3.3946, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7024128598505073e-05, + "loss": 3.4363, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7015742650994553e-05, + "loss": 3.4126, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7007356703484033e-05, + "loss": 3.3941, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998970755973513e-05, + "loss": 3.4173, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6990584808462996e-05, + "loss": 3.4034, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6982198860952476e-05, + "loss": 3.3944, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6973812913441953e-05, + "loss": 3.419, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965443344735165e-05, + "loss": 3.4175, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6957057397224645e-05, + "loss": 3.4012, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6948671449714125e-05, + "loss": 3.4122, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6940285502203605e-05, + "loss": 3.3906, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6931915933496818e-05, + "loss": 3.4037, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923529985986298e-05, + "loss": 3.4054, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6915160417279507e-05, + "loss": 3.4056, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6906774469768987e-05, + "loss": 3.4113, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898388522258467e-05, + "loss": 3.4054, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.689000257474795e-05, + "loss": 3.4244, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881616627237426e-05, + "loss": 3.405, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873230679726906e-05, + "loss": 3.4175, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6864844732216386e-05, + "loss": 3.4069, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.68564751635096e-05, + "loss": 3.4041, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684808921599908e-05, + "loss": 3.4176, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.683970326848856e-05, + "loss": 3.4095, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.683131732097804e-05, + "loss": 3.4096, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.682293137346752e-05, + "loss": 3.416, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6814545425957e-05, + "loss": 3.404, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.680615947844648e-05, + "loss": 3.392, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.679777353093596e-05, + "loss": 3.4059, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.67894203410329e-05, + "loss": 3.4175, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.678103439352238e-05, + "loss": 3.398, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.677264844601186e-05, + "loss": 3.4138, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.676426249850134e-05, + "loss": 3.4009, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.675587655099082e-05, + "loss": 3.3971, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.67474906034803e-05, + "loss": 3.3995, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.673910465596978e-05, + "loss": 3.407, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6730735087262992e-05, + "loss": 3.4212, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6722349139752472e-05, + "loss": 3.4087, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6713963192241952e-05, + "loss": 3.4157, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6705577244731432e-05, + "loss": 3.4058, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.669719129722091e-05, + "loss": 3.4057, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.668882172851412e-05, + "loss": 3.4023, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680435781003605e-05, + "loss": 3.4132, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.667204983349308e-05, + "loss": 3.413, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.666366388598256e-05, + "loss": 3.4125, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665527793847204e-05, + "loss": 3.4081, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.664689199096152e-05, + "loss": 3.4017, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638506043451e-05, + "loss": 3.4152, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.663012009594048e-05, + "loss": 3.4044, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6621750527233693e-05, + "loss": 3.4007, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613380958526903e-05, + "loss": 3.408, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6604995011016383e-05, + "loss": 3.4069, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596609063505862e-05, + "loss": 3.4052, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6588223115995342e-05, + "loss": 3.4011, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6579853547288555e-05, + "loss": 3.4035, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6571467599778035e-05, + "loss": 3.4096, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6563081652267515e-05, + "loss": 3.4074, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6554695704756995e-05, + "loss": 3.4084, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6546309757246475e-05, + "loss": 3.4169, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6537923809735955e-05, + "loss": 3.4181, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6529537862225435e-05, + "loss": 3.4055, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6521168293518647e-05, + "loss": 3.4092, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6512782346008127e-05, + "loss": 3.4011, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504396398497607e-05, + "loss": 3.4081, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6496010450987084e-05, + "loss": 3.4072, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487624503476564e-05, + "loss": 3.4013, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6479238555966044e-05, + "loss": 3.4, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6470852608455527e-05, + "loss": 3.4117, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6462466660945007e-05, + "loss": 3.4141, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6454097092238216e-05, + "loss": 3.3999, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6445711144727696e-05, + "loss": 3.4062, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437325197217176e-05, + "loss": 3.4067, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6428939249706656e-05, + "loss": 3.4131, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420569680999868e-05, + "loss": 3.4119, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6412183733489348e-05, + "loss": 3.4192, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6403797785978828e-05, + "loss": 3.399, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395411838468308e-05, + "loss": 3.4106, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6387042269761517e-05, + "loss": 3.4132, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378656322250997e-05, + "loss": 3.402, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.637027037474048e-05, + "loss": 3.4085, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.636188442722996e-05, + "loss": 3.4114, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.635351485852317e-05, + "loss": 3.4196, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.634512891101265e-05, + "loss": 3.4196, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.633674296350213e-05, + "loss": 3.4072, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632835701599161e-05, + "loss": 3.4096, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6320003826088554e-05, + "loss": 3.4132, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.631161787857803e-05, + "loss": 3.4056, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630323193106751e-05, + "loss": 3.4064, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629484598355699e-05, + "loss": 3.4053, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.628646003604647e-05, + "loss": 3.4023, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627807408853595e-05, + "loss": 3.4068, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6269688141025434e-05, + "loss": 3.4056, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.871090888977051, + "eval_runtime": 303.7102, + "eval_samples_per_second": 1256.431, + "eval_steps_per_second": 39.264, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.6261302193514914e-05, + "loss": 3.4078, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.6252932624808123e-05, + "loss": 3.4057, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6244546677297603e-05, + "loss": 3.4099, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6236160729787083e-05, + "loss": 3.4106, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6227774782276563e-05, + "loss": 3.4209, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6219405213569776e-05, + "loss": 3.4055, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6211019266059256e-05, + "loss": 3.411, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6202633318548736e-05, + "loss": 3.4027, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.6194247371038212e-05, + "loss": 3.401, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.6185877802331425e-05, + "loss": 3.4067, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.6177491854820905e-05, + "loss": 3.4176, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6169122286114117e-05, + "loss": 3.4002, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6160736338603597e-05, + "loss": 3.4128, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6152350391093077e-05, + "loss": 3.391, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6143964443582557e-05, + "loss": 3.3985, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6135578496072037e-05, + "loss": 3.3878, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6127192548561513e-05, + "loss": 3.4058, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.6118806601050997e-05, + "loss": 3.405, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.6110420653540477e-05, + "loss": 3.4021, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6102051084833686e-05, + "loss": 3.4038, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6093665137323166e-05, + "loss": 3.4184, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6085279189812646e-05, + "loss": 3.4117, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.6076893242302126e-05, + "loss": 3.4062, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.6068523673595338e-05, + "loss": 3.4016, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6060137726084818e-05, + "loss": 3.4146, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.6051751778574298e-05, + "loss": 3.4084, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6043365831063778e-05, + "loss": 3.3993, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6034996262356987e-05, + "loss": 3.4052, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6026610314846467e-05, + "loss": 3.3988, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.601822436733595e-05, + "loss": 3.3944, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.600983841982543e-05, + "loss": 3.4092, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.6001485229922372e-05, + "loss": 3.4042, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5993099282411852e-05, + "loss": 3.412, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5984713334901332e-05, + "loss": 3.413, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5976327387390812e-05, + "loss": 3.3985, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5967941439880292e-05, + "loss": 3.4084, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959555492369772e-05, + "loss": 3.4081, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.5951169544859252e-05, + "loss": 3.3979, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.594279997615246e-05, + "loss": 3.3981, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.593441402864194e-05, + "loss": 3.3914, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.592602808113142e-05, + "loss": 3.3928, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5917642133620904e-05, + "loss": 3.4021, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5909256186110384e-05, + "loss": 3.4166, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5900870238599864e-05, + "loss": 3.3997, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.589248429108934e-05, + "loss": 3.3971, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.588409834357882e-05, + "loss": 3.4045, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.5875728774872033e-05, + "loss": 3.404, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5867342827361513e-05, + "loss": 3.3907, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5858956879850993e-05, + "loss": 3.3824, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5850570932340473e-05, + "loss": 3.4071, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5842201363633685e-05, + "loss": 3.4106, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5833815416123162e-05, + "loss": 3.4122, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5825429468612642e-05, + "loss": 3.3967, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5817043521102122e-05, + "loss": 3.395, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5808673952395338e-05, + "loss": 3.3966, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.5800288004884814e-05, + "loss": 3.3954, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5791902057374294e-05, + "loss": 3.4146, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5783532488667507e-05, + "loss": 3.3875, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.5775146541156987e-05, + "loss": 3.4219, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5766760593646467e-05, + "loss": 3.4025, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5758374646135947e-05, + "loss": 3.3886, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5749988698625427e-05, + "loss": 3.4046, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5741602751114906e-05, + "loss": 3.395, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5733216803604386e-05, + "loss": 3.3858, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5724847234897596e-05, + "loss": 3.405, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.5716461287387075e-05, + "loss": 3.4086, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.570807533987656e-05, + "loss": 3.3921, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.569968939236604e-05, + "loss": 3.4033, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.569130344485552e-05, + "loss": 3.3811, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5682917497344995e-05, + "loss": 3.395, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674531549834475e-05, + "loss": 3.3938, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5666161981127688e-05, + "loss": 3.3981, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5657776033617168e-05, + "loss": 3.3966, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5649390086106648e-05, + "loss": 3.3947, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5641004138596128e-05, + "loss": 3.4128, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5632618191085608e-05, + "loss": 3.3968, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5624232243575088e-05, + "loss": 3.4042, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5615846296064567e-05, + "loss": 3.3976, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5607476727357777e-05, + "loss": 3.3973, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.559909077984726e-05, + "loss": 3.4095, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.559070483233674e-05, + "loss": 3.4009, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.558231888482622e-05, + "loss": 3.3971, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.55739329373157e-05, + "loss": 3.4046, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.556556336860891e-05, + "loss": 3.3981, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.555717742109839e-05, + "loss": 3.3781, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.554879147358787e-05, + "loss": 3.3982, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5540405526077352e-05, + "loss": 3.4025, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.553201957856683e-05, + "loss": 3.3905, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.552363363105631e-05, + "loss": 3.3995, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.551524768354579e-05, + "loss": 3.3962, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.550686173603527e-05, + "loss": 3.3857, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.549849216732848e-05, + "loss": 3.393, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.549010621981796e-05, + "loss": 3.395, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.548172027230744e-05, + "loss": 3.4066, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.547333432479692e-05, + "loss": 3.4003, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.546496475609013e-05, + "loss": 3.4078, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.545657880857961e-05, + "loss": 3.3914, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5448209239872822e-05, + "loss": 3.3975, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5439823292362302e-05, + "loss": 3.3966, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5431437344851782e-05, + "loss": 3.403, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5423051397341262e-05, + "loss": 3.4029, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5414665449830742e-05, + "loss": 3.402, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5406279502320222e-05, + "loss": 3.3955, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5397893554809702e-05, + "loss": 3.3924, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5389523986102915e-05, + "loss": 3.4055, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5381154417396124e-05, + "loss": 3.3951, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5372768469885604e-05, + "loss": 3.3968, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5364382522375084e-05, + "loss": 3.3963, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5355996574864564e-05, + "loss": 3.3956, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5347610627354044e-05, + "loss": 3.3978, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.5339224679843524e-05, + "loss": 3.3888, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5330855111136736e-05, + "loss": 3.3932, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5322469163626216e-05, + "loss": 3.4018, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5314083216115696e-05, + "loss": 3.3978, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5305697268605176e-05, + "loss": 3.3955, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5297311321094652e-05, + "loss": 3.4054, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5288925373584136e-05, + "loss": 3.4107, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5280539426073616e-05, + "loss": 3.395, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5272169857366828e-05, + "loss": 3.3947, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5263783909856305e-05, + "loss": 3.3953, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5255397962345785e-05, + "loss": 3.3977, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5247012014835266e-05, + "loss": 3.3946, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5238626067324746e-05, + "loss": 3.391, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5230240119814226e-05, + "loss": 3.3896, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5221854172303706e-05, + "loss": 3.402, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5213468224793185e-05, + "loss": 3.3967, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5205098656086397e-05, + "loss": 3.394, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5196712708575877e-05, + "loss": 3.3995, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5188326761065359e-05, + "loss": 3.3956, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5179940813554835e-05, + "loss": 3.399, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171571244848048e-05, + "loss": 3.4019, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.516318529733753e-05, + "loss": 3.4073, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.515479934982701e-05, + "loss": 3.3909, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5146413402316486e-05, + "loss": 3.4017, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.51380438336097e-05, + "loss": 3.4032, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.512965788609918e-05, + "loss": 3.395, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5121271938588658e-05, + "loss": 3.3936, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5112885991078138e-05, + "loss": 3.4006, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.510451642237135e-05, + "loss": 3.4122, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.509613047486083e-05, + "loss": 3.4087, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5087744527350309e-05, + "loss": 3.4002, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5079358579839789e-05, + "loss": 3.3991, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5070989011133001e-05, + "loss": 3.4025, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5062603063622483e-05, + "loss": 3.3999, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.505421711611196e-05, + "loss": 3.3924, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.504583116860144e-05, + "loss": 3.3979, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5037461599894654e-05, + "loss": 3.3886, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.502907565238413e-05, + "loss": 3.3978, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5020689704873612e-05, + "loss": 3.3942, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.872307300567627, + "eval_runtime": 303.7428, + "eval_samples_per_second": 1256.297, + "eval_steps_per_second": 39.26, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012303757363092e-05, + "loss": 3.4135, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5003917809852572e-05, + "loss": 3.3902, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995531862342052e-05, + "loss": 3.3986, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4987145914831532e-05, + "loss": 3.4076, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4978776346124743e-05, + "loss": 3.4081, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970390398614223e-05, + "loss": 3.4029, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962004451103702e-05, + "loss": 3.402, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4953618503593184e-05, + "loss": 3.3943, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945248934886393e-05, + "loss": 3.3904, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4936862987375875e-05, + "loss": 3.4011, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928477039865355e-05, + "loss": 3.3957, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920091092354835e-05, + "loss": 3.3943, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4911737902451778e-05, + "loss": 3.4032, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903351954941255e-05, + "loss": 3.3816, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4894966007430736e-05, + "loss": 3.3907, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4886580059920216e-05, + "loss": 3.3755, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4878194112409696e-05, + "loss": 3.3988, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4869808164899176e-05, + "loss": 3.3899, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4861422217388656e-05, + "loss": 3.3944, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4853036269878138e-05, + "loss": 3.396, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4844666701171347e-05, + "loss": 3.4051, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4836280753660829e-05, + "loss": 3.4022, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4827894806150308e-05, + "loss": 3.3938, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819525237443518e-05, + "loss": 3.3936, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4811139289933e-05, + "loss": 3.4068, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.480275334242248e-05, + "loss": 3.398, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4794367394911959e-05, + "loss": 3.3898, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4785981447401437e-05, + "loss": 3.398, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4777595499890917e-05, + "loss": 3.3834, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4769209552380397e-05, + "loss": 3.39, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4760839983673608e-05, + "loss": 3.3981, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.475247041496682e-05, + "loss": 3.3961, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.47440844674563e-05, + "loss": 3.3978, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4735698519945782e-05, + "loss": 3.405, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4727312572435259e-05, + "loss": 3.3901, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4718926624924739e-05, + "loss": 3.3981, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.471054067741422e-05, + "loss": 3.401, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.47021547299037e-05, + "loss": 3.3838, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.469378516119691e-05, + "loss": 3.3897, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4685399213686391e-05, + "loss": 3.3831, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4677013266175871e-05, + "loss": 3.3838, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4668627318665351e-05, + "loss": 3.3918, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660241371154831e-05, + "loss": 3.4066, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4651855423644311e-05, + "loss": 3.3867, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.464346947613379e-05, + "loss": 3.3903, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635083528623269e-05, + "loss": 3.3947, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4626713959916483e-05, + "loss": 3.3945, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618328012405963e-05, + "loss": 3.3819, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.460994206489544e-05, + "loss": 3.3707, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4601556117384921e-05, + "loss": 3.3928, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593186548678134e-05, + "loss": 3.402, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4584800601167614e-05, + "loss": 3.4019, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576414653657092e-05, + "loss": 3.3829, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568045084950305e-05, + "loss": 3.3878, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4559659137439785e-05, + "loss": 3.3885, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551273189929263e-05, + "loss": 3.38, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4542887242418743e-05, + "loss": 3.4089, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534501294908223e-05, + "loss": 3.3764, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4526115347397703e-05, + "loss": 3.4105, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4517729399887184e-05, + "loss": 3.3937, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4509359831180393e-05, + "loss": 3.3793, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4500973883669875e-05, + "loss": 3.3937, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4492587936159355e-05, + "loss": 3.3879, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4484201988648835e-05, + "loss": 3.3746, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4475816041138315e-05, + "loss": 3.3937, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4467430093627795e-05, + "loss": 3.396, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4459044146117273e-05, + "loss": 3.3829, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4450658198606753e-05, + "loss": 3.3907, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4442288629899967e-05, + "loss": 3.3695, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4433902682389444e-05, + "loss": 3.3888, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4425516734878924e-05, + "loss": 3.383, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4417147166172138e-05, + "loss": 3.3903, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4408761218661618e-05, + "loss": 3.3857, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400375271151095e-05, + "loss": 3.3872, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4391989323640576e-05, + "loss": 3.405, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4383603376130056e-05, + "loss": 3.3883, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4375217428619536e-05, + "loss": 3.3933, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4366831481109016e-05, + "loss": 3.388, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4358461912402227e-05, + "loss": 3.3867, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4350075964891707e-05, + "loss": 3.3981, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4341690017381187e-05, + "loss": 3.3879, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333304069870668e-05, + "loss": 3.3915, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4324918122360148e-05, + "loss": 3.3895, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.431654855365336e-05, + "loss": 3.392, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308162606142839e-05, + "loss": 3.3662, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4299776658632319e-05, + "loss": 3.3918, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291390711121799e-05, + "loss": 3.3875, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283004763611277e-05, + "loss": 3.3813, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4274618816100757e-05, + "loss": 3.3886, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4266232868590237e-05, + "loss": 3.3835, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4257846921079717e-05, + "loss": 3.379, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249477352372928e-05, + "loss": 3.3772, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4241091404862408e-05, + "loss": 3.3884, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4232705457351888e-05, + "loss": 3.3933, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.422431950984137e-05, + "loss": 3.3916, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4215949941134579e-05, + "loss": 3.3955, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.420756399362406e-05, + "loss": 3.3845, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199194424917273e-05, + "loss": 3.3854, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.419080847740675e-05, + "loss": 3.3865, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182422529896231e-05, + "loss": 3.3928, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4174036582385711e-05, + "loss": 3.3888, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4165650634875191e-05, + "loss": 3.3943, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4157264687364671e-05, + "loss": 3.3872, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4148878739854152e-05, + "loss": 3.3835, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4140492792343629e-05, + "loss": 3.3951, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4132123223636842e-05, + "loss": 3.3848, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4123737276126323e-05, + "loss": 3.3853, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4115351328615803e-05, + "loss": 3.3851, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4106981759909014e-05, + "loss": 3.388, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4098595812398494e-05, + "loss": 3.3844, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4090209864887974e-05, + "loss": 3.3819, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4081840296181185e-05, + "loss": 3.3807, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4073454348670665e-05, + "loss": 3.3898, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4065068401160145e-05, + "loss": 3.3917, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4056682453649625e-05, + "loss": 3.381, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4048296506139103e-05, + "loss": 3.3954, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4039910558628583e-05, + "loss": 3.4006, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4031524611118063e-05, + "loss": 3.3864, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4023155042411277e-05, + "loss": 3.3865, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4014769094900753e-05, + "loss": 3.3841, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006383147390233e-05, + "loss": 3.3876, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3997997199879715e-05, + "loss": 3.3844, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3989611252369195e-05, + "loss": 3.383, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3981225304858675e-05, + "loss": 3.3816, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3972839357348155e-05, + "loss": 3.3895, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964453409837635e-05, + "loss": 3.3876, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956083841130846e-05, + "loss": 3.3887, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3947697893620326e-05, + "loss": 3.3884, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939311946109807e-05, + "loss": 3.3874, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3930925998599284e-05, + "loss": 3.3838, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3922556429892496e-05, + "loss": 3.3994, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914170482381978e-05, + "loss": 3.3954, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3905784534871458e-05, + "loss": 3.3827, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897398587360934e-05, + "loss": 3.386, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3889029018654149e-05, + "loss": 3.3957, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3880643071143629e-05, + "loss": 3.3802, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3872257123633109e-05, + "loss": 3.3883, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3863871176122587e-05, + "loss": 3.3902, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.385551798621953e-05, + "loss": 3.4019, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.384713203870901e-05, + "loss": 3.3945, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.383874609119849e-05, + "loss": 3.3937, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.383036014368797e-05, + "loss": 3.3859, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.382197419617745e-05, + "loss": 3.3964, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3813588248666932e-05, + "loss": 3.3857, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3805202301156408e-05, + "loss": 3.3816, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3796816353645888e-05, + "loss": 3.3876, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788446784939102e-05, + "loss": 3.3779, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3780060837428582e-05, + "loss": 3.3895, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.377167488991806e-05, + "loss": 3.3836, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.8747141361236572, + "eval_runtime": 301.8005, + "eval_samples_per_second": 1264.381, + "eval_steps_per_second": 39.513, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.376328894240754e-05, + "loss": 3.3905, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3754919373700753e-05, + "loss": 3.3842, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3746533426190231e-05, + "loss": 3.3879, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3738147478679711e-05, + "loss": 3.3984, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3729761531169191e-05, + "loss": 3.3955, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3721391962462404e-05, + "loss": 3.3982, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3713006014951882e-05, + "loss": 3.3844, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3704620067441362e-05, + "loss": 3.3856, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3696234119930842e-05, + "loss": 3.3761, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3687864551224056e-05, + "loss": 3.3921, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3679478603713533e-05, + "loss": 3.3871, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3671092656203014e-05, + "loss": 3.3844, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3662723087496227e-05, + "loss": 3.3968, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3654337139985703e-05, + "loss": 3.3684, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3645951192475185e-05, + "loss": 3.3765, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3637565244964665e-05, + "loss": 3.3738, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3629179297454145e-05, + "loss": 3.3858, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3620809728747356e-05, + "loss": 3.3835, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3612423781236836e-05, + "loss": 3.3813, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3604037833726316e-05, + "loss": 3.3872, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3595651886215795e-05, + "loss": 3.3916, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3587265938705277e-05, + "loss": 3.3913, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3578879991194757e-05, + "loss": 3.3878, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3570494043684237e-05, + "loss": 3.3821, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3562108096173715e-05, + "loss": 3.3978, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3553738527466928e-05, + "loss": 3.3831, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3545352579956408e-05, + "loss": 3.3812, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3536966632445886e-05, + "loss": 3.3878, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3528597063739098e-05, + "loss": 3.3774, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3520211116228578e-05, + "loss": 3.3806, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3511825168718058e-05, + "loss": 3.3848, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.350345560001127e-05, + "loss": 3.3856, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3495069652500749e-05, + "loss": 3.3904, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.348668370499023e-05, + "loss": 3.3939, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3478297757479707e-05, + "loss": 3.3789, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3469911809969187e-05, + "loss": 3.3896, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3461525862458669e-05, + "loss": 3.3942, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3453139914948149e-05, + "loss": 3.3748, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3444770346241358e-05, + "loss": 3.3793, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.343638439873084e-05, + "loss": 3.3689, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.342799845122032e-05, + "loss": 3.3771, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.34196125037098e-05, + "loss": 3.3769, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.341122655619928e-05, + "loss": 3.4021, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3402840608688761e-05, + "loss": 3.3752, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3394454661178241e-05, + "loss": 3.3783, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3386068713667718e-05, + "loss": 3.3843, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3377699144960932e-05, + "loss": 3.3839, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3369313197450412e-05, + "loss": 3.3763, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3360927249939888e-05, + "loss": 3.3622, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.335254130242937e-05, + "loss": 3.3855, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3344171733722583e-05, + "loss": 3.3897, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3335785786212063e-05, + "loss": 3.3887, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.332739983870154e-05, + "loss": 3.3785, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.331901389119102e-05, + "loss": 3.374, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3310644322484233e-05, + "loss": 3.383, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3302258374973713e-05, + "loss": 3.3709, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3293888806266924e-05, + "loss": 3.3981, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3285502858756404e-05, + "loss": 3.367, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3277116911245886e-05, + "loss": 3.3991, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3268730963735362e-05, + "loss": 3.3828, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3260345016224842e-05, + "loss": 3.3666, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3251975447518056e-05, + "loss": 3.3837, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3243589500007536e-05, + "loss": 3.3813, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3235203552497013e-05, + "loss": 3.3667, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3226817604986494e-05, + "loss": 3.375, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3218431657475974e-05, + "loss": 3.3925, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3210045709965454e-05, + "loss": 3.3735, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3201659762454934e-05, + "loss": 3.3761, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3193290193748145e-05, + "loss": 3.3632, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3184904246237625e-05, + "loss": 3.3792, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3176518298727105e-05, + "loss": 3.3714, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3168148730020316e-05, + "loss": 3.3822, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.3159762782509796e-05, + "loss": 3.3764, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3151376834999277e-05, + "loss": 3.3791, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3142990887488757e-05, + "loss": 3.388, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.3134604939978237e-05, + "loss": 3.3755, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.3126235371271448e-05, + "loss": 3.3808, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3117849423760928e-05, + "loss": 3.3798, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3109463476250408e-05, + "loss": 3.3791, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3101077528739888e-05, + "loss": 3.3868, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.309269158122937e-05, + "loss": 3.3798, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3084305633718846e-05, + "loss": 3.3798, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.3075919686208326e-05, + "loss": 3.3857, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.306755011750154e-05, + "loss": 3.3806, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3059164169991017e-05, + "loss": 3.3594, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3050778222480497e-05, + "loss": 3.3803, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3042392274969978e-05, + "loss": 3.3764, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3034022706263191e-05, + "loss": 3.3782, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.302563675875267e-05, + "loss": 3.3754, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.301725081124215e-05, + "loss": 3.3801, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3008864863731629e-05, + "loss": 3.367, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.3000478916221109e-05, + "loss": 3.3697, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2992092968710589e-05, + "loss": 3.3742, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.29837234000038e-05, + "loss": 3.3866, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.297533745249328e-05, + "loss": 3.3772, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.296695150498276e-05, + "loss": 3.3887, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2958565557472241e-05, + "loss": 3.3708, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2950179609961721e-05, + "loss": 3.3794, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2941810041254932e-05, + "loss": 3.3774, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2933424093744412e-05, + "loss": 3.3829, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2925038146233892e-05, + "loss": 3.38, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2916652198723372e-05, + "loss": 3.3849, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.290826625121285e-05, + "loss": 3.3752, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.289988030370233e-05, + "loss": 3.3745, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.289149435619181e-05, + "loss": 3.3884, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.288310840868129e-05, + "loss": 3.3719, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2874738839974501e-05, + "loss": 3.3732, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2866369271267713e-05, + "loss": 3.3789, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2857983323757195e-05, + "loss": 3.3757, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2849597376246672e-05, + "loss": 3.3741, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2841211428736152e-05, + "loss": 3.3766, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2832841860029366e-05, + "loss": 3.3677, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2824455912518846e-05, + "loss": 3.3805, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2816069965008324e-05, + "loss": 3.3816, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2807684017497804e-05, + "loss": 3.3736, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2799298069987284e-05, + "loss": 3.387, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2790912122476764e-05, + "loss": 3.3907, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2782526174966244e-05, + "loss": 3.3766, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2774156606259455e-05, + "loss": 3.3775, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2765770658748935e-05, + "loss": 3.3743, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2757384711238416e-05, + "loss": 3.3743, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2748998763727896e-05, + "loss": 3.3727, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2740612816217376e-05, + "loss": 3.3734, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2732226868706854e-05, + "loss": 3.3705, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2723840921196334e-05, + "loss": 3.3814, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.2715454973685814e-05, + "loss": 3.3808, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2707085404979027e-05, + "loss": 3.3757, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2698699457468505e-05, + "loss": 3.3769, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2690313509957985e-05, + "loss": 3.3761, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2681927562447465e-05, + "loss": 3.3737, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2673557993740676e-05, + "loss": 3.3893, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2665172046230156e-05, + "loss": 3.3871, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2656786098719636e-05, + "loss": 3.3777, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2648400151209117e-05, + "loss": 3.3762, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2640030582502326e-05, + "loss": 3.3824, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2631644634991806e-05, + "loss": 3.3754, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2623258687481288e-05, + "loss": 3.3759, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.2614872739970768e-05, + "loss": 3.3792, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2606519550067711e-05, + "loss": 3.3979, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2598133602557191e-05, + "loss": 3.3778, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2589747655046671e-05, + "loss": 3.3854, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.258136170753615e-05, + "loss": 3.3766, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.257297576002563e-05, + "loss": 3.3869, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.256458981251511e-05, + "loss": 3.3774, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.255620386500459e-05, + "loss": 3.3714, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2547817917494071e-05, + "loss": 3.381, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.253944834878728e-05, + "loss": 3.3676, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.253106240127676e-05, + "loss": 3.3833, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2522676453766242e-05, + "loss": 3.3698, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.8752903938293457, + "eval_runtime": 301.8971, + "eval_samples_per_second": 1263.977, + "eval_steps_per_second": 39.5, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2514290506255722e-05, + "loss": 3.3851, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2505904558745202e-05, + "loss": 3.3762, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.249751861123468e-05, + "loss": 3.374, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2489132663724161e-05, + "loss": 3.3895, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2480763095017372e-05, + "loss": 3.3834, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2472377147506852e-05, + "loss": 3.3888, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2463991199996332e-05, + "loss": 3.374, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2455605252485812e-05, + "loss": 3.3744, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2447235683779023e-05, + "loss": 3.3729, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2438849736268503e-05, + "loss": 3.3833, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2430463788757983e-05, + "loss": 3.3743, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2422077841247463e-05, + "loss": 3.3747, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2413724651344404e-05, + "loss": 3.3879, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2405338703833886e-05, + "loss": 3.3601, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2396952756323366e-05, + "loss": 3.3633, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2388566808812846e-05, + "loss": 3.3652, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2380180861302324e-05, + "loss": 3.3731, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2371794913791806e-05, + "loss": 3.3724, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2363408966281286e-05, + "loss": 3.3732, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2355023018770764e-05, + "loss": 3.3745, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2346653450063977e-05, + "loss": 3.3839, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2338267502553457e-05, + "loss": 3.3793, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2329897933846667e-05, + "loss": 3.3799, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2321511986336147e-05, + "loss": 3.3739, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2313126038825627e-05, + "loss": 3.3881, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2304740091315107e-05, + "loss": 3.3751, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2296354143804587e-05, + "loss": 3.3746, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2287968196294067e-05, + "loss": 3.3741, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2279582248783547e-05, + "loss": 3.3703, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2271196301273025e-05, + "loss": 3.3692, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2262826732566238e-05, + "loss": 3.3725, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2254457163859449e-05, + "loss": 3.3755, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.224607121634893e-05, + "loss": 3.3812, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2237685268838409e-05, + "loss": 3.3828, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2229299321327888e-05, + "loss": 3.3721, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2220913373817368e-05, + "loss": 3.3778, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.221252742630685e-05, + "loss": 3.3766, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2204141478796328e-05, + "loss": 3.3662, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2195771910089541e-05, + "loss": 3.3717, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.218738596257902e-05, + "loss": 3.3598, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2179000015068499e-05, + "loss": 3.368, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2170614067557979e-05, + "loss": 3.3694, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.216222812004746e-05, + "loss": 3.3884, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.215384217253694e-05, + "loss": 3.3683, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2145456225026419e-05, + "loss": 3.3703, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2137070277515899e-05, + "loss": 3.3785, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2128700708809111e-05, + "loss": 3.3744, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.212031476129859e-05, + "loss": 3.3695, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2111928813788071e-05, + "loss": 3.3475, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2103542866277551e-05, + "loss": 3.3733, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2095173297570762e-05, + "loss": 3.3808, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2086787350060242e-05, + "loss": 3.382, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2078401402549722e-05, + "loss": 3.3665, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2070031833842933e-05, + "loss": 3.3621, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2061645886332414e-05, + "loss": 3.3731, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2053259938821893e-05, + "loss": 3.3616, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2044873991311373e-05, + "loss": 3.3841, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2036488043800853e-05, + "loss": 3.3581, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2028102096290332e-05, + "loss": 3.3902, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2019716148779812e-05, + "loss": 3.3749, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2011330201269292e-05, + "loss": 3.3548, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2002960632562505e-05, + "loss": 3.3722, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1994574685051983e-05, + "loss": 3.3749, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1986188737541463e-05, + "loss": 3.3562, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1977802790030945e-05, + "loss": 3.3644, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1969433221324154e-05, + "loss": 3.3847, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1961047273813634e-05, + "loss": 3.3672, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1952661326303115e-05, + "loss": 3.3658, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1944275378792595e-05, + "loss": 3.3515, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1935905810085806e-05, + "loss": 3.3698, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1927519862575286e-05, + "loss": 3.362, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1919150293868497e-05, + "loss": 3.3746, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1910764346357977e-05, + "loss": 3.3637, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1902378398847457e-05, + "loss": 3.3717, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1893992451336937e-05, + "loss": 3.3753, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1885606503826417e-05, + "loss": 3.3707, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1877220556315897e-05, + "loss": 3.37, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1868834608805377e-05, + "loss": 3.3667, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1860448661294857e-05, + "loss": 3.3759, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.1852079092588069e-05, + "loss": 3.3754, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.1843693145077547e-05, + "loss": 3.3692, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1835307197567027e-05, + "loss": 3.3708, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1826921250056507e-05, + "loss": 3.3683, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1818535302545987e-05, + "loss": 3.3696, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1810149355035467e-05, + "loss": 3.3503, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1801763407524947e-05, + "loss": 3.3698, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.179339383881816e-05, + "loss": 3.3676, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1785024270111369e-05, + "loss": 3.3667, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.177663832260085e-05, + "loss": 3.3702, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.176825237509033e-05, + "loss": 3.3682, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1759866427579809e-05, + "loss": 3.3619, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1751480480069289e-05, + "loss": 3.3567, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.174309453255877e-05, + "loss": 3.3626, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1734724963851981e-05, + "loss": 3.3781, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1726339016341461e-05, + "loss": 3.3679, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1717953068830941e-05, + "loss": 3.3763, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1709567121320421e-05, + "loss": 3.3639, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1701181173809899e-05, + "loss": 3.3706, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1692811605103112e-05, + "loss": 3.3622, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1684425657592592e-05, + "loss": 3.3768, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1676039710082072e-05, + "loss": 3.3659, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1667653762571551e-05, + "loss": 3.3757, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1659267815061031e-05, + "loss": 3.3654, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1650881867550511e-05, + "loss": 3.3653, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1642495920039991e-05, + "loss": 3.3825, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1634109972529471e-05, + "loss": 3.3557, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1625740403822682e-05, + "loss": 3.3646, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1617370835115895e-05, + "loss": 3.3722, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1608984887605373e-05, + "loss": 3.3647, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1600598940094853e-05, + "loss": 3.3647, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1592212992584334e-05, + "loss": 3.3665, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1583843423877545e-05, + "loss": 3.3604, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1575457476367023e-05, + "loss": 3.3741, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1567071528856505e-05, + "loss": 3.367, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1558685581345985e-05, + "loss": 3.3669, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1550299633835463e-05, + "loss": 3.3772, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1541913686324943e-05, + "loss": 3.3801, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1533527738814425e-05, + "loss": 3.3693, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1525158170107636e-05, + "loss": 3.3667, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1516772222597116e-05, + "loss": 3.3627, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1508386275086596e-05, + "loss": 3.366, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1500000327576076e-05, + "loss": 3.3613, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1491630758869286e-05, + "loss": 3.3696, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1483244811358766e-05, + "loss": 3.3589, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1474858863848246e-05, + "loss": 3.3744, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1466472916337726e-05, + "loss": 3.3666, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1458086968827206e-05, + "loss": 3.37, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1449701021316686e-05, + "loss": 3.3682, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1441315073806166e-05, + "loss": 3.3653, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1432929126295646e-05, + "loss": 3.361, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1424559557588857e-05, + "loss": 3.3795, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1416173610078337e-05, + "loss": 3.3767, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1407787662567817e-05, + "loss": 3.3705, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1399401715057297e-05, + "loss": 3.3601, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1391032146350508e-05, + "loss": 3.3708, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.138264619883999e-05, + "loss": 3.3677, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1374260251329467e-05, + "loss": 3.3674, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1365874303818947e-05, + "loss": 3.3733, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.135750473511216e-05, + "loss": 3.3857, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.134911878760164e-05, + "loss": 3.3671, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1340732840091118e-05, + "loss": 3.3778, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.13323468925806e-05, + "loss": 3.3681, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.132397732387381e-05, + "loss": 3.3733, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.131559137636329e-05, + "loss": 3.3635, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.130720542885277e-05, + "loss": 3.3642, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.129881948134225e-05, + "loss": 3.3731, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1290449912635461e-05, + "loss": 3.3571, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1282063965124941e-05, + "loss": 3.3713, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1273678017614421e-05, + "loss": 3.3635, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.876488208770752, + "eval_runtime": 305.8275, + "eval_samples_per_second": 1247.733, + "eval_steps_per_second": 38.993, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1265292070103901e-05, + "loss": 3.3685, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1256922501397114e-05, + "loss": 3.3676, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1248536553886592e-05, + "loss": 3.3647, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1240150606376072e-05, + "loss": 3.377, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1231764658865552e-05, + "loss": 3.3743, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1223395090158764e-05, + "loss": 3.3795, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1215009142648242e-05, + "loss": 3.3622, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1206623195137724e-05, + "loss": 3.3686, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1198237247627204e-05, + "loss": 3.3575, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1189867678920415e-05, + "loss": 3.3754, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1181481731409895e-05, + "loss": 3.3651, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1173095783899375e-05, + "loss": 3.3657, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1164709836388855e-05, + "loss": 3.3694, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1156340267682066e-05, + "loss": 3.3591, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1147954320171545e-05, + "loss": 3.3583, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1139568372661025e-05, + "loss": 3.3565, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1131182425150505e-05, + "loss": 3.3549, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1122796477639985e-05, + "loss": 3.3634, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1114410530129465e-05, + "loss": 3.3668, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.1106024582618944e-05, + "loss": 3.3634, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1097655013912156e-05, + "loss": 3.3771, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1089269066401636e-05, + "loss": 3.3688, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.1080883118891116e-05, + "loss": 3.3682, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1072497171380596e-05, + "loss": 3.3653, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1064127602673807e-05, + "loss": 3.3769, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1055741655163288e-05, + "loss": 3.3616, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1047355707652768e-05, + "loss": 3.3673, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1038969760142247e-05, + "loss": 3.3598, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1030600191435459e-05, + "loss": 3.3644, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.1022214243924939e-05, + "loss": 3.3629, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1013828296414417e-05, + "loss": 3.3567, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1005442348903897e-05, + "loss": 3.3714, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.099708915900084e-05, + "loss": 3.3706, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.098870321149032e-05, + "loss": 3.369, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.09803172639798e-05, + "loss": 3.3651, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.097193131646928e-05, + "loss": 3.3678, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.096354536895876e-05, + "loss": 3.3703, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.095515942144824e-05, + "loss": 3.3546, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0946789852741451e-05, + "loss": 3.3632, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0938403905230931e-05, + "loss": 3.3473, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0930017957720413e-05, + "loss": 3.36, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0921632010209891e-05, + "loss": 3.3554, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0913246062699371e-05, + "loss": 3.3808, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0904860115188851e-05, + "loss": 3.3602, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0896474167678333e-05, + "loss": 3.3562, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.088808822016781e-05, + "loss": 3.3664, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0879718651461023e-05, + "loss": 3.3687, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0871332703950503e-05, + "loss": 3.3573, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0862946756439982e-05, + "loss": 3.3399, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0854560808929461e-05, + "loss": 3.3604, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0846191240222674e-05, + "loss": 3.3735, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0837805292712154e-05, + "loss": 3.3704, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0829419345201632e-05, + "loss": 3.3601, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0821033397691114e-05, + "loss": 3.3529, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0812663828984325e-05, + "loss": 3.3665, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0804277881473805e-05, + "loss": 3.3498, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0795891933963285e-05, + "loss": 3.3763, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0787522365256495e-05, + "loss": 3.3488, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0779136417745975e-05, + "loss": 3.3777, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0770750470235455e-05, + "loss": 3.3711, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0762364522724935e-05, + "loss": 3.3454, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0753978575214415e-05, + "loss": 3.3627, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0745592627703897e-05, + "loss": 3.3663, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0737206680193375e-05, + "loss": 3.3422, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0728837111486586e-05, + "loss": 3.3554, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0720451163976067e-05, + "loss": 3.3723, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0712065216465546e-05, + "loss": 3.3585, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0703679268955026e-05, + "loss": 3.354, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0695309700248238e-05, + "loss": 3.3468, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0686923752737718e-05, + "loss": 3.3591, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0678537805227196e-05, + "loss": 3.3484, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0670168236520409e-05, + "loss": 3.3636, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0661782289009889e-05, + "loss": 3.3528, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0653396341499369e-05, + "loss": 3.3633, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0645010393988849e-05, + "loss": 3.3645, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0636624446478329e-05, + "loss": 3.3624, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0628238498967809e-05, + "loss": 3.3587, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0619852551457287e-05, + "loss": 3.3588, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0611466603946769e-05, + "loss": 3.3666, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.060309703523998e-05, + "loss": 3.365, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.059471108772946e-05, + "loss": 3.361, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.058632514021894e-05, + "loss": 3.3582, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.057793919270842e-05, + "loss": 3.3596, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0569569624001632e-05, + "loss": 3.3602, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.056118367649111e-05, + "loss": 3.3435, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.055279772898059e-05, + "loss": 3.3586, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.054441178147007e-05, + "loss": 3.3579, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.0536042212763282e-05, + "loss": 3.3583, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.052765626525276e-05, + "loss": 3.3594, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.051927031774224e-05, + "loss": 3.3567, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0510884370231722e-05, + "loss": 3.3533, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.05024984227212e-05, + "loss": 3.3459, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.049411247521068e-05, + "loss": 3.3533, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.048572652770016e-05, + "loss": 3.3666, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0477356958993373e-05, + "loss": 3.3601, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0468971011482851e-05, + "loss": 3.3673, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0460585063972333e-05, + "loss": 3.3573, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0452199116461813e-05, + "loss": 3.3591, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0443829547755022e-05, + "loss": 3.3544, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0435443600244504e-05, + "loss": 3.3661, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0427057652733983e-05, + "loss": 3.3577, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0418671705223463e-05, + "loss": 3.3676, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0410285757712943e-05, + "loss": 3.3517, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0401899810202423e-05, + "loss": 3.3521, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0393513862691903e-05, + "loss": 3.3731, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0385127915181382e-05, + "loss": 3.3505, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0376758346474594e-05, + "loss": 3.3529, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0368372398964074e-05, + "loss": 3.3596, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0359986451453554e-05, + "loss": 3.3606, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0351600503943034e-05, + "loss": 3.3517, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0343230935236245e-05, + "loss": 3.3577, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0334844987725725e-05, + "loss": 3.3512, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0326475419018937e-05, + "loss": 3.3599, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0318089471508415e-05, + "loss": 3.3591, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.0309703523997895e-05, + "loss": 3.3591, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0301317576487377e-05, + "loss": 3.3637, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0292931628976855e-05, + "loss": 3.3749, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0284545681466335e-05, + "loss": 3.3591, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0276176112759548e-05, + "loss": 3.359, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0267790165249028e-05, + "loss": 3.3534, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0259404217738506e-05, + "loss": 3.3544, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0251018270227988e-05, + "loss": 3.3509, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0242632322717468e-05, + "loss": 3.3579, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0234246375206946e-05, + "loss": 3.3505, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0225860427696426e-05, + "loss": 3.3634, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0217474480185907e-05, + "loss": 3.3583, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0209104911479118e-05, + "loss": 3.3625, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0200718963968598e-05, + "loss": 3.3542, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0192333016458078e-05, + "loss": 3.3565, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0183947068947558e-05, + "loss": 3.3516, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0175577500240769e-05, + "loss": 3.3681, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0167191552730249e-05, + "loss": 3.3699, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.0158805605219729e-05, + "loss": 3.3613, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0150419657709209e-05, + "loss": 3.3508, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.014205008900242e-05, + "loss": 3.3574, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.01336641414919e-05, + "loss": 3.3601, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.012527819398138e-05, + "loss": 3.3582, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.011689224647086e-05, + "loss": 3.3633, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.010852267776407e-05, + "loss": 3.3752, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0100136730253552e-05, + "loss": 3.3568, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0091750782743032e-05, + "loss": 3.3733, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.008336483523251e-05, + "loss": 3.3561, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0074995266525723e-05, + "loss": 3.3647, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0066609319015202e-05, + "loss": 3.3573, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0058223371504682e-05, + "loss": 3.3505, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.004983742399416e-05, + "loss": 3.3648, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0041467855287373e-05, + "loss": 3.3506, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0033081907776853e-05, + "loss": 3.3579, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0024695960266333e-05, + "loss": 3.3562, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0016310012755813e-05, + "loss": 3.3565, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.8772237300872803, + "eval_runtime": 304.243, + "eval_samples_per_second": 1254.231, + "eval_steps_per_second": 39.196, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0007924065245293e-05, + "loss": 3.3572, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 9.999538117734773e-06, + "loss": 3.3572, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.991152170224253e-06, + "loss": 3.3656, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.982782601517464e-06, + "loss": 3.3646, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.974396654006944e-06, + "loss": 3.3728, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.966010706496424e-06, + "loss": 3.3538, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.957624758985904e-06, + "loss": 3.3535, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.949255190279114e-06, + "loss": 3.3519, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.940869242768596e-06, + "loss": 3.3652, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.932483295258074e-06, + "loss": 3.3549, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.924097347747554e-06, + "loss": 3.3581, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.915727779040767e-06, + "loss": 3.3567, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.907358210333977e-06, + "loss": 3.3511, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.898972262823457e-06, + "loss": 3.3537, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.890586315312937e-06, + "loss": 3.3476, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.882200367802417e-06, + "loss": 3.3447, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.873814420291896e-06, + "loss": 3.3559, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.865428472781377e-06, + "loss": 3.3568, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.857042525270857e-06, + "loss": 3.3537, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.848672956564068e-06, + "loss": 3.3696, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.840287009053548e-06, + "loss": 3.3554, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.831901061543028e-06, + "loss": 3.3607, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.823515114032508e-06, + "loss": 3.3556, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.815145545325719e-06, + "loss": 3.3648, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.806759597815199e-06, + "loss": 3.3544, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.798373650304679e-06, + "loss": 3.3592, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.78998770279416e-06, + "loss": 3.3511, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.78161813408737e-06, + "loss": 3.3573, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.77323218657685e-06, + "loss": 3.3477, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.764846239066331e-06, + "loss": 3.3528, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.756476670359542e-06, + "loss": 3.3624, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.748090722849022e-06, + "loss": 3.3578, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.739704775338502e-06, + "loss": 3.3628, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.731318827827982e-06, + "loss": 3.3577, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.72293288031746e-06, + "loss": 3.3539, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.714546932806942e-06, + "loss": 3.3648, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.706160985296421e-06, + "loss": 3.3487, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.6977750377859e-06, + "loss": 3.3533, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.689405469079112e-06, + "loss": 3.3392, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.681019521568592e-06, + "loss": 3.3476, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.672633574058072e-06, + "loss": 3.347, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.664264005351283e-06, + "loss": 3.3682, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.655878057840763e-06, + "loss": 3.3522, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.647492110330243e-06, + "loss": 3.3495, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.639106162819723e-06, + "loss": 3.3595, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.630720215309203e-06, + "loss": 3.3568, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.622334267798683e-06, + "loss": 3.3474, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.613948320288163e-06, + "loss": 3.3339, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.605562372777643e-06, + "loss": 3.3455, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.597192804070853e-06, + "loss": 3.3647, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.588806856560333e-06, + "loss": 3.362, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.580420909049815e-06, + "loss": 3.3495, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.572051340343024e-06, + "loss": 3.3448, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.563665392832504e-06, + "loss": 3.3586, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.555279445321986e-06, + "loss": 3.3437, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.546893497811464e-06, + "loss": 3.3606, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.538507550300944e-06, + "loss": 3.3411, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.530121602790424e-06, + "loss": 3.3681, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.521735655279906e-06, + "loss": 3.3573, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.513349707769384e-06, + "loss": 3.3421, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.504980139062596e-06, + "loss": 3.3481, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.496594191552076e-06, + "loss": 3.3602, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.488208244041554e-06, + "loss": 3.3317, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.479822296531034e-06, + "loss": 3.3439, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.471436349020516e-06, + "loss": 3.3608, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.463050401509996e-06, + "loss": 3.3519, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.454664453999474e-06, + "loss": 3.347, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.446278506488954e-06, + "loss": 3.3372, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.437908937782167e-06, + "loss": 3.3454, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.429522990271645e-06, + "loss": 3.3395, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.421153421564857e-06, + "loss": 3.3579, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.412767474054337e-06, + "loss": 3.3418, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.404381526543817e-06, + "loss": 3.3567, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.395995579033297e-06, + "loss": 3.35, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.387609631522777e-06, + "loss": 3.3573, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.379223684012257e-06, + "loss": 3.3447, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.370837736501736e-06, + "loss": 3.3502, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.362451788991217e-06, + "loss": 3.3559, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.354082220284428e-06, + "loss": 3.3567, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.345696272773908e-06, + "loss": 3.3515, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.337310325263388e-06, + "loss": 3.3498, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.328924377752868e-06, + "loss": 3.352, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.32055480904608e-06, + "loss": 3.3496, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.31216886153556e-06, + "loss": 3.338, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.303782914025039e-06, + "loss": 3.3433, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.295396966514518e-06, + "loss": 3.3509, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.287027397807731e-06, + "loss": 3.3537, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.27864145029721e-06, + "loss": 3.3461, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.27025550278669e-06, + "loss": 3.3472, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.261869555276171e-06, + "loss": 3.3436, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.253483607765649e-06, + "loss": 3.337, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.245097660255129e-06, + "loss": 3.3434, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.236711712744609e-06, + "loss": 3.3533, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.22832576523409e-06, + "loss": 3.351, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.2199561965273e-06, + "loss": 3.3608, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.211570249016781e-06, + "loss": 3.3551, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.203184301506261e-06, + "loss": 3.3428, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.194814732799472e-06, + "loss": 3.3453, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.186428785288952e-06, + "loss": 3.3521, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.178042837778432e-06, + "loss": 3.3529, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.169656890267912e-06, + "loss": 3.3571, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.161270942757392e-06, + "loss": 3.3445, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.152884995246872e-06, + "loss": 3.3426, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.144499047736352e-06, + "loss": 3.3653, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.13611310022583e-06, + "loss": 3.3389, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.127743531519043e-06, + "loss": 3.347, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.119357584008523e-06, + "loss": 3.3479, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.110971636498003e-06, + "loss": 3.3514, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.102585688987483e-06, + "loss": 3.3395, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.094216120280693e-06, + "loss": 3.3462, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.085830172770173e-06, + "loss": 3.3437, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.077460604063386e-06, + "loss": 3.3512, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.069074656552864e-06, + "loss": 3.3483, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.060688709042344e-06, + "loss": 3.3468, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.052302761531826e-06, + "loss": 3.356, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.043916814021304e-06, + "loss": 3.3652, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.035530866510784e-06, + "loss": 3.3532, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.027144919000265e-06, + "loss": 3.3447, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.018775350293476e-06, + "loss": 3.3444, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.010389402782955e-06, + "loss": 3.3451, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 9.002003455272436e-06, + "loss": 3.3465, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.993617507761916e-06, + "loss": 3.348, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.985231560251394e-06, + "loss": 3.343, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.976845612740874e-06, + "loss": 3.348, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.968459665230356e-06, + "loss": 3.3516, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.960090096523567e-06, + "loss": 3.3508, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.951704149013047e-06, + "loss": 3.346, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.943318201502527e-06, + "loss": 3.3456, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.934932253992007e-06, + "loss": 3.3446, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.926562685285217e-06, + "loss": 3.3583, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.918176737774697e-06, + "loss": 3.3582, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.909790790264177e-06, + "loss": 3.3535, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.901404842753657e-06, + "loss": 3.3389, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.893035274046868e-06, + "loss": 3.3524, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.884649326536348e-06, + "loss": 3.3493, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.876263379025828e-06, + "loss": 3.3513, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.86787743151531e-06, + "loss": 3.3468, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.859507862808519e-06, + "loss": 3.3657, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.851121915298e-06, + "loss": 3.3456, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.84273596778748e-06, + "loss": 3.3661, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.834350020276959e-06, + "loss": 3.3453, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.825980451570171e-06, + "loss": 3.3568, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.817594504059651e-06, + "loss": 3.3465, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.809208556549131e-06, + "loss": 3.345, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.80082260903861e-06, + "loss": 3.3528, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.792453040331822e-06, + "loss": 3.3423, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.784067092821302e-06, + "loss": 3.3487, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.775681145310782e-06, + "loss": 3.3461, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.767311576603992e-06, + "loss": 3.347, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.8769681453704834, + "eval_runtime": 302.8293, + "eval_samples_per_second": 1260.086, + "eval_steps_per_second": 39.379, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.758925629093472e-06, + "loss": 3.3507, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.750539681582952e-06, + "loss": 3.348, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.742153734072432e-06, + "loss": 3.3583, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.733767786561912e-06, + "loss": 3.3528, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.725381839051392e-06, + "loss": 3.3641, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.716995891540874e-06, + "loss": 3.343, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.708609944030352e-06, + "loss": 3.3465, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.700240375323563e-06, + "loss": 3.3408, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.691854427813045e-06, + "loss": 3.356, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.683468480302523e-06, + "loss": 3.344, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.675082532792003e-06, + "loss": 3.3452, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.666712964085215e-06, + "loss": 3.3489, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.658343395378426e-06, + "loss": 3.3381, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.649957447867906e-06, + "loss": 3.3457, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.641571500357386e-06, + "loss": 3.3378, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.633185552846866e-06, + "loss": 3.3398, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.624799605336344e-06, + "loss": 3.3425, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.616413657825826e-06, + "loss": 3.3442, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.608027710315306e-06, + "loss": 3.3435, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.599658141608517e-06, + "loss": 3.3642, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.591272194097997e-06, + "loss": 3.3467, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.582886246587477e-06, + "loss": 3.3459, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.574500299076956e-06, + "loss": 3.351, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.566130730370169e-06, + "loss": 3.3528, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.557744782859647e-06, + "loss": 3.348, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.549358835349127e-06, + "loss": 3.3525, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.540972887838609e-06, + "loss": 3.3393, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.532603319131818e-06, + "loss": 3.3486, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.524217371621298e-06, + "loss": 3.3358, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.51583142411078e-06, + "loss": 3.3483, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.50746185540399e-06, + "loss": 3.3502, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.49907590789347e-06, + "loss": 3.3491, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.49068996038295e-06, + "loss": 3.354, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.48230401287243e-06, + "loss": 3.3432, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.473918065361908e-06, + "loss": 3.3476, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.46553211785139e-06, + "loss": 3.3516, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.45714617034087e-06, + "loss": 3.3411, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.448776601634081e-06, + "loss": 3.342, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.44039065412356e-06, + "loss": 3.3302, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.43200470661304e-06, + "loss": 3.3385, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.42361875910252e-06, + "loss": 3.3416, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.415232811592e-06, + "loss": 3.3579, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.40684686408148e-06, + "loss": 3.3434, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.39846091657096e-06, + "loss": 3.3389, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.39007496906044e-06, + "loss": 3.3505, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.381705400353651e-06, + "loss": 3.3423, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.373319452843131e-06, + "loss": 3.3426, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.364933505332611e-06, + "loss": 3.3304, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.356547557822091e-06, + "loss": 3.3316, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.348177989115302e-06, + "loss": 3.3557, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.339792041604782e-06, + "loss": 3.3543, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.331406094094264e-06, + "loss": 3.3363, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.323020146583742e-06, + "loss": 3.3379, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.314650577876953e-06, + "loss": 3.3473, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.306264630366434e-06, + "loss": 3.3333, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.297878682855914e-06, + "loss": 3.3501, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.289509114149125e-06, + "loss": 3.3309, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.281123166638605e-06, + "loss": 3.3567, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.272737219128085e-06, + "loss": 3.3508, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.264351271617563e-06, + "loss": 3.3342, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.255965324107045e-06, + "loss": 3.3385, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.247579376596525e-06, + "loss": 3.3493, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.239193429086005e-06, + "loss": 3.3193, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.230823860379216e-06, + "loss": 3.339, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.222437912868696e-06, + "loss": 3.3514, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.214051965358175e-06, + "loss": 3.3448, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.205666017847655e-06, + "loss": 3.3341, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.197296449140866e-06, + "loss": 3.3278, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.188910501630346e-06, + "loss": 3.3382, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.180524554119826e-06, + "loss": 3.335, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.172154985413037e-06, + "loss": 3.3431, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.163769037902517e-06, + "loss": 3.3345, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.155383090391999e-06, + "loss": 3.3478, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.146997142881478e-06, + "loss": 3.3417, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.138611195370957e-06, + "loss": 3.3495, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.130225247860437e-06, + "loss": 3.3345, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.121839300349918e-06, + "loss": 3.3426, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.113453352839397e-06, + "loss": 3.3451, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.105083784132609e-06, + "loss": 3.346, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.096697836622089e-06, + "loss": 3.3459, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.088311889111569e-06, + "loss": 3.3409, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.079925941601047e-06, + "loss": 3.3441, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.07155637289426e-06, + "loss": 3.3391, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.06317042538374e-06, + "loss": 3.3275, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.054784477873218e-06, + "loss": 3.335, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.0463985303627e-06, + "loss": 3.3392, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.03802896165591e-06, + "loss": 3.3484, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.02964301414539e-06, + "loss": 3.3398, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.02125706663487e-06, + "loss": 3.3378, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.01287111912435e-06, + "loss": 3.3331, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.00448517161383e-06, + "loss": 3.3285, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.99609922410331e-06, + "loss": 3.3321, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.98771327659279e-06, + "loss": 3.3448, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.97932732908227e-06, + "loss": 3.343, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.970957760375483e-06, + "loss": 3.3498, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.962571812864961e-06, + "loss": 3.3451, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.95418586535444e-06, + "loss": 3.3341, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.945816296647653e-06, + "loss": 3.3386, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.937430349137132e-06, + "loss": 3.338, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.929044401626612e-06, + "loss": 3.3456, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.920658454116091e-06, + "loss": 3.3447, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.912272506605573e-06, + "loss": 3.3369, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.903886559095051e-06, + "loss": 3.3326, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.895500611584531e-06, + "loss": 3.3538, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.887114664074011e-06, + "loss": 3.3293, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.878745095367222e-06, + "loss": 3.3389, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.870375526660435e-06, + "loss": 3.3403, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.861989579149915e-06, + "loss": 3.3396, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.853603631639394e-06, + "loss": 3.332, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.845217684128873e-06, + "loss": 3.3416, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.836831736618354e-06, + "loss": 3.3295, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.828462167911565e-06, + "loss": 3.3404, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.820076220401045e-06, + "loss": 3.3407, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.811690272890525e-06, + "loss": 3.3343, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.803304325380005e-06, + "loss": 3.3493, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.794918377869485e-06, + "loss": 3.3554, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.786532430358965e-06, + "loss": 3.3429, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.778146482848445e-06, + "loss": 3.3387, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.769776914141656e-06, + "loss": 3.3332, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.761390966631137e-06, + "loss": 3.3382, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.753005019120616e-06, + "loss": 3.3319, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.744619071610096e-06, + "loss": 3.3446, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.736233124099576e-06, + "loss": 3.33, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.727863555392786e-06, + "loss": 3.338, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.719477607882266e-06, + "loss": 3.3438, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.711091660371746e-06, + "loss": 3.3458, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.702705712861228e-06, + "loss": 3.3321, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.694319765350706e-06, + "loss": 3.3368, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.685933817840186e-06, + "loss": 3.342, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.677547870329666e-06, + "loss": 3.3408, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.669161922819146e-06, + "loss": 3.35, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.660792354112357e-06, + "loss": 3.3453, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.652406406601838e-06, + "loss": 3.3315, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.644020459091318e-06, + "loss": 3.3406, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.635634511580797e-06, + "loss": 3.3417, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.627264942874008e-06, + "loss": 3.3403, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.618878995363489e-06, + "loss": 3.34, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.610493047852968e-06, + "loss": 3.3506, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.602107100342448e-06, + "loss": 3.3388, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.59373753163566e-06, + "loss": 3.357, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.585351584125141e-06, + "loss": 3.3376, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.576965636614619e-06, + "loss": 3.3454, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.5685796891041e-06, + "loss": 3.3402, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.560210120397311e-06, + "loss": 3.337, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.551840551690523e-06, + "loss": 3.3421, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.543454604180002e-06, + "loss": 3.3375, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.535068656669482e-06, + "loss": 3.3381, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.526682709158962e-06, + "loss": 3.3321, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.518296761648441e-06, + "loss": 3.3347, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.8783507347106934, + "eval_runtime": 303.115, + "eval_samples_per_second": 1258.898, + "eval_steps_per_second": 39.341, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.509910814137922e-06, + "loss": 3.3402, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.501524866627402e-06, + "loss": 3.3392, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.493138919116882e-06, + "loss": 3.3479, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.484752971606361e-06, + "loss": 3.3418, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.4763834028995725e-06, + "loss": 3.3608, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.467997455389053e-06, + "loss": 3.3331, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.459611507878532e-06, + "loss": 3.3398, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.451241939171743e-06, + "loss": 3.3287, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.442855991661224e-06, + "loss": 3.3472, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.434470044150704e-06, + "loss": 3.3373, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.426084096640183e-06, + "loss": 3.3356, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.417714527933395e-06, + "loss": 3.3444, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.409344959226606e-06, + "loss": 3.3277, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.400959011716087e-06, + "loss": 3.3391, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.3925730642055654e-06, + "loss": 3.3267, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.384187116695046e-06, + "loss": 3.329, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.375801169184526e-06, + "loss": 3.3282, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.367415221674005e-06, + "loss": 3.3385, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.359029274163485e-06, + "loss": 3.3343, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.350643326652966e-06, + "loss": 3.3526, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.342273757946178e-06, + "loss": 3.3402, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.333887810435657e-06, + "loss": 3.3397, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.325501862925137e-06, + "loss": 3.3398, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.317132294218348e-06, + "loss": 3.3454, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.3087463467078275e-06, + "loss": 3.3368, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.3003603991973075e-06, + "loss": 3.3458, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.291974451686788e-06, + "loss": 3.3312, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.28360488298e-06, + "loss": 3.3379, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.275218935469478e-06, + "loss": 3.3248, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.266832987958959e-06, + "loss": 3.3397, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.258463419252171e-06, + "loss": 3.3415, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.2500774717416506e-06, + "loss": 3.3382, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.24169152423113e-06, + "loss": 3.3471, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.2333055767206105e-06, + "loss": 3.3373, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.2249196292100904e-06, + "loss": 3.3344, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.2165336816995695e-06, + "loss": 3.3438, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.2081477341890495e-06, + "loss": 3.3332, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.199778165482261e-06, + "loss": 3.3312, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.191392217971742e-06, + "loss": 3.322, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.18300627046122e-06, + "loss": 3.3295, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.174620322950701e-06, + "loss": 3.3305, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.166234375440181e-06, + "loss": 3.3477, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.15784842792966e-06, + "loss": 3.339, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.14946248041914e-06, + "loss": 3.3262, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.141076532908621e-06, + "loss": 3.3441, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.1327069642018325e-06, + "loss": 3.3369, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.1243210166913116e-06, + "loss": 3.3313, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.1159350691807915e-06, + "loss": 3.3227, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.107549121670272e-06, + "loss": 3.32, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.099179552963482e-06, + "loss": 3.3456, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.090793605452962e-06, + "loss": 3.3432, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.082407657942443e-06, + "loss": 3.33, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.074021710431923e-06, + "loss": 3.3284, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.065652141725134e-06, + "loss": 3.3399, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.057266194214614e-06, + "loss": 3.3215, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.048880246704094e-06, + "loss": 3.3427, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.040494299193573e-06, + "loss": 3.3241, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.0321247304867844e-06, + "loss": 3.3421, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.023738782976265e-06, + "loss": 3.3479, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.015352835465745e-06, + "loss": 3.3278, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.006983266758955e-06, + "loss": 3.3252, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.998597319248436e-06, + "loss": 3.3424, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.990211371737916e-06, + "loss": 3.3144, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.981825424227397e-06, + "loss": 3.3313, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.973439476716875e-06, + "loss": 3.3407, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.965053529206356e-06, + "loss": 3.34, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.956667581695836e-06, + "loss": 3.3277, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.948281634185315e-06, + "loss": 3.3184, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.9399120654785265e-06, + "loss": 3.3251, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.931526117968007e-06, + "loss": 3.3228, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.923140170457487e-06, + "loss": 3.3325, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.914770601750697e-06, + "loss": 3.3242, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.906384654240178e-06, + "loss": 3.339, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.897998706729658e-06, + "loss": 3.3334, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.889612759219137e-06, + "loss": 3.3392, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.881226811708617e-06, + "loss": 3.3225, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.872840864198098e-06, + "loss": 3.3311, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.864454916687578e-06, + "loss": 3.3409, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.8560853479807885e-06, + "loss": 3.3338, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.8476994004702685e-06, + "loss": 3.3365, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.8393134529597485e-06, + "loss": 3.334, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.8309275054492276e-06, + "loss": 3.3311, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.822557936742439e-06, + "loss": 3.3331, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.81417198923192e-06, + "loss": 3.3168, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.8057860417214e-06, + "loss": 3.3284, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.797400094210879e-06, + "loss": 3.328, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.789030525504091e-06, + "loss": 3.3375, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.780644577993571e-06, + "loss": 3.3289, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.77225863048305e-06, + "loss": 3.3272, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.7638726829725306e-06, + "loss": 3.3232, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.7554867354620105e-06, + "loss": 3.3222, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.7471007879514905e-06, + "loss": 3.3211, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.738731219244701e-06, + "loss": 3.3309, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.730345271734181e-06, + "loss": 3.3438, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.721959324223662e-06, + "loss": 3.3354, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.71357337671314e-06, + "loss": 3.3329, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.705187429202621e-06, + "loss": 3.3274, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.696817860495833e-06, + "loss": 3.3326, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.688431912985313e-06, + "loss": 3.3264, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.680045965474792e-06, + "loss": 3.3383, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.671660017964272e-06, + "loss": 3.3344, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.6632740704537526e-06, + "loss": 3.3276, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.654888122943232e-06, + "loss": 3.3222, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.646502175432712e-06, + "loss": 3.3447, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.638116227922192e-06, + "loss": 3.322, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.629746659215404e-06, + "loss": 3.333, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.621360711704882e-06, + "loss": 3.3243, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.612974764194363e-06, + "loss": 3.3335, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.604605195487575e-06, + "loss": 3.323, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.596219247977055e-06, + "loss": 3.3346, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.587833300466534e-06, + "loss": 3.3239, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.579447352956014e-06, + "loss": 3.3271, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.571061405445495e-06, + "loss": 3.3339, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.562675457934974e-06, + "loss": 3.324, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.554289510424454e-06, + "loss": 3.3424, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.545919941717665e-06, + "loss": 3.3441, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.537533994207145e-06, + "loss": 3.3323, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.529148046696624e-06, + "loss": 3.328, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.520762099186105e-06, + "loss": 3.3271, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.512392530479317e-06, + "loss": 3.3279, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.504006582968795e-06, + "loss": 3.326, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.495620635458276e-06, + "loss": 3.3349, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.487234687947756e-06, + "loss": 3.3223, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.4788651192409674e-06, + "loss": 3.3293, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.4704791717304466e-06, + "loss": 3.3353, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.462109603023658e-06, + "loss": 3.335, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.453723655513139e-06, + "loss": 3.3247, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.445337708002619e-06, + "loss": 3.3277, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.436951760492098e-06, + "loss": 3.3339, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.428565812981578e-06, + "loss": 3.3331, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.420179865471059e-06, + "loss": 3.3337, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.411793917960537e-06, + "loss": 3.3399, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.403407970450018e-06, + "loss": 3.3222, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.3950384017432295e-06, + "loss": 3.333, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.3866524542327095e-06, + "loss": 3.3322, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.378266506722189e-06, + "loss": 3.3305, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.3698805592116685e-06, + "loss": 3.3295, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.36151099050488e-06, + "loss": 3.3421, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.353141421798093e-06, + "loss": 3.3305, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.344755474287571e-06, + "loss": 3.3472, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.336369526777052e-06, + "loss": 3.3266, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.327983579266532e-06, + "loss": 3.333, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.319597631756011e-06, + "loss": 3.3315, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.311211684245491e-06, + "loss": 3.329, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.3028257367349716e-06, + "loss": 3.3305, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.294456168028183e-06, + "loss": 3.3294, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.286070220517662e-06, + "loss": 3.3274, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.277684273007142e-06, + "loss": 3.3257, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.269298325496622e-06, + "loss": 3.3296, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.8781917095184326, + "eval_runtime": 304.4964, + "eval_samples_per_second": 1253.187, + "eval_steps_per_second": 39.163, + "step": 2671200 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.8241013735978342e+18, + "trial_name": null, + "trial_params": null +}