diff --git "a/checkpoint-3052726/trainer_state.json" "b/checkpoint-3052726/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-3052726/trainer_state.json" @@ -0,0 +1,36117 @@ +{ + "best_metric": 3.843822956085205, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sent-neg/transformer/1/checkpoints/checkpoint-992160", + "epoch": 1.0249763653862154, + "eval_steps": 10, + "global_step": 3052726, + "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": 11.0158, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8308, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1835, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9727, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8165, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7111, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6025, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5321, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4577, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4022, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3542, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3085, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2658, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1988, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1714, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1299, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1047, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0759, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0489, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0143, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0067, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9731, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9478, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9308, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9206, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8882, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8658, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8532, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8284, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8217, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8044, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.8004, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7723, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7672, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.755, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7438, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7267, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.6968, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.6992, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6746, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6789, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6655, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6616, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.645, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6423, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6379, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.624, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6268, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5959, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5888, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5966, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5853, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5772, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5512, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5668, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5433, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5676, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5221, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5389, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5212, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5063, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.517, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5026, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4821, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4858, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5003, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4768, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4708, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.467, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.453, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4656, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4634, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4527, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4634, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4493, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4455, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4261, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4312, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4243, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4156, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4133, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4194, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4175, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4082, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3838, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.4004, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4015, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.4016, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 4.3853, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3937, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3812, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3734, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3736, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3715, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3616, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.373, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3522, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3493, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3472, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3588, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3519, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3356, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3363, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.328, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.337, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3114, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3234, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3226, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3178, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.323, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3165, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.2989, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3118, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3114, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3066, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3072, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3032, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2976, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2886, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.291, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2893, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2767, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.28, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.2788, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2868, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2667, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2733, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2644, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2711, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2607, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2764, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2618, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2572, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2574, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2598, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.2635, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2628, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.254, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.2558, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.2511, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2458, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2349, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2437, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2356, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2292, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2339, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2292, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2337, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.233, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2248, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.193797588348389, + "eval_runtime": 302.9559, + "eval_samples_per_second": 1259.56, + "eval_steps_per_second": 39.362, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2105, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2099, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2226, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2139, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2165, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2027, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2004, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.2004, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2077, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2035, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2082, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.178, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1877, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.186, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1734, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.188, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.179, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1754, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.2007, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.1804, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1761, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1766, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1864, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.1675, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1654, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.1671, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1615, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1646, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1549, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1765, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1604, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1591, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1568, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.16, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.1534, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844077064237013e-05, + "loss": 4.1383, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.1441, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842399874734909e-05, + "loss": 4.1334, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.1482, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.1371, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.1457, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.1364, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.1374, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.1431, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.1337, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.1383, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.1244, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.1224, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.1304, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.1293, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.133, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306660997416735e-05, + "loss": 4.1052, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.1284, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.1067, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.1376, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.1047, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826474763866787e-05, + "loss": 4.1212, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825636169115735e-05, + "loss": 4.1144, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824797574364683e-05, + "loss": 4.1004, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823958979613631e-05, + "loss": 4.1094, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823122022742952e-05, + "loss": 4.1068, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222834279919e-05, + "loss": 4.0913, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821444833240848e-05, + "loss": 4.0963, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820606238489796e-05, + "loss": 4.1125, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.0997, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.0979, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818092092117013e-05, + "loss": 4.0957, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817253497365961e-05, + "loss": 4.085, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.1018, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.1012, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.0997, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.1091, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.0974, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.0991, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113866098693434e-05, + "loss": 4.0789, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.0939, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.0861, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.0799, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.085, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807196911874829e-05, + "loss": 4.0908, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.0954, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0894, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.0684, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803842532870622e-05, + "loss": 4.0752, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.80300393811957e-05, + "loss": 4.0921, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802165343368518e-05, + "loss": 4.0879, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.0821, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800489791746787e-05, + "loss": 4.0869, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996528348761076e-05, + "loss": 4.083, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988142401250556e-05, + "loss": 4.0689, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979756453740036e-05, + "loss": 4.074, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971370506229516e-05, + "loss": 4.0786, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.0673, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795461499001221e-05, + "loss": 4.0861, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794622904250169e-05, + "loss": 4.0655, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793784309499117e-05, + "loss": 4.0635, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792945714748065e-05, + "loss": 4.0658, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792107119997013e-05, + "loss": 4.0757, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912685252459605e-05, + "loss": 4.0731, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904299304949085e-05, + "loss": 4.0617, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895913357438565e-05, + "loss": 4.0593, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.0548, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.0715, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.0443, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.0513, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785401637749343e-05, + "loss": 4.0661, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784563042998291e-05, + "loss": 4.0561, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.0542, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.0576, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.0464, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.0569, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780371707123404e-05, + "loss": 4.0529, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779533112372352e-05, + "loss": 4.0556, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786945176213e-05, + "loss": 4.0575, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777855922870248e-05, + "loss": 4.0589, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.0476, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.0436, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0496, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774504819626786e-05, + "loss": 4.047, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.0334, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0434, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.0394, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.0503, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0339, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0419, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0258, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767797699498743e-05, + "loss": 4.0439, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.0322, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.0484, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0393, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0359, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76360800150423e-05, + "loss": 4.0272, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.0331, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.0432, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.0457, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602552603803946e-05, + "loss": 4.0371, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594166656293426e-05, + "loss": 4.0374, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585780708782906e-05, + "loss": 4.0311, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577394761272386e-05, + "loss": 4.0324, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569025192565595e-05, + "loss": 4.0243, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0323, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552253297544555e-05, + "loss": 4.0286, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0166, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753549778132725e-05, + "loss": 4.0276, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752711183381673e-05, + "loss": 4.0217, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751872588630621e-05, + "loss": 4.028, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751033993879569e-05, + "loss": 4.0253, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750195399128517e-05, + "loss": 4.0218, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.026120662689209, + "eval_runtime": 303.0751, + "eval_samples_per_second": 1259.064, + "eval_steps_per_second": 39.347, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 4.005, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0106, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.0205, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.0179, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0231, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 4.0018, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.0116, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 4.0064, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742649684249422e-05, + "loss": 4.0159, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.74181108949837e-05, + "loss": 4.0131, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740972494747318e-05, + "loss": 4.0114, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.0145, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 3.9934, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 3.9982, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 4.0027, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 3.9929, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735942564121379e-05, + "loss": 4.001, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735103969370327e-05, + "loss": 3.997, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734265374619275e-05, + "loss": 3.9941, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733426779868223e-05, + "loss": 4.0244, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732588185117171e-05, + "loss": 3.9986, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731749590366119e-05, + "loss": 4.0031, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309109956150674e-05, + "loss": 3.999, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300724008640154e-05, + "loss": 4.0103, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292354439933364e-05, + "loss": 3.9896, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283968492422844e-05, + "loss": 3.992, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 3.9963, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726721297620553e-05, + "loss": 3.9947, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725882702869501e-05, + "loss": 3.9858, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725044108118449e-05, + "loss": 3.9898, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 4.004, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723368556496718e-05, + "loss": 3.9925, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722529961745666e-05, + "loss": 3.9907, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721691366994614e-05, + "loss": 3.9944, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720852772243563e-05, + "loss": 3.9914, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.72001417749251e-05, + "loss": 3.9886, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719177220621832e-05, + "loss": 3.9742, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833862587078e-05, + "loss": 3.9874, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717500031119727e-05, + "loss": 3.9708, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716661436368675e-05, + "loss": 3.9831, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715822841617623e-05, + "loss": 3.9764, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714984246866571e-05, + "loss": 3.9873, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714145652115519e-05, + "loss": 3.9799, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71330869524484e-05, + "loss": 3.9773, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712470100493788e-05, + "loss": 3.9836, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116315057427366e-05, + "loss": 3.9814, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107929109916846e-05, + "loss": 3.9829, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099559541210055e-05, + "loss": 3.968, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091173593699535e-05, + "loss": 3.9663, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082787646189015e-05, + "loss": 3.9785, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074401698678495e-05, + "loss": 3.9742, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7066015751167975e-05, + "loss": 3.9753, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057629803657455e-05, + "loss": 3.9573, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049260234950664e-05, + "loss": 3.9792, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040874287440144e-05, + "loss": 3.9544, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032488339929624e-05, + "loss": 3.9851, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024102392419104e-05, + "loss": 3.9505, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015716444908584e-05, + "loss": 3.9756, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007330497398064e-05, + "loss": 3.9659, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998944549887544e-05, + "loss": 3.961, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699057498118076e-05, + "loss": 3.9597, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698218903367024e-05, + "loss": 3.9624, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697380308615972e-05, + "loss": 3.9466, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696543351745293e-05, + "loss": 3.9535, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695704756994241e-05, + "loss": 3.9637, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694866162243189e-05, + "loss": 3.9616, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694027567492137e-05, + "loss": 3.9515, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693188972741085e-05, + "loss": 3.9536, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692350377990033e-05, + "loss": 3.9502, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691513421119354e-05, + "loss": 3.9567, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690674826368302e-05, + "loss": 3.9589, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.68983623161725e-05, + "loss": 3.9586, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6889976368661984e-05, + "loss": 3.9691, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688159042115146e-05, + "loss": 3.963, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687320447364094e-05, + "loss": 3.9622, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686481852613042e-05, + "loss": 3.9399, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685644895742363e-05, + "loss": 3.955, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848063009913106e-05, + "loss": 3.9572, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839677062402586e-05, + "loss": 3.9434, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831291114892066e-05, + "loss": 3.9531, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822905167381546e-05, + "loss": 3.9534, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814519219871026e-05, + "loss": 3.9621, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806149651164235e-05, + "loss": 3.952, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679776370365372e-05, + "loss": 3.9343, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.67893777561432e-05, + "loss": 3.9447, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678099180863268e-05, + "loss": 3.9552, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677260586112216e-05, + "loss": 3.9564, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676421991361164e-05, + "loss": 3.9516, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675583396610112e-05, + "loss": 3.9565, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674746439739433e-05, + "loss": 3.9554, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673907844988381e-05, + "loss": 3.9372, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673069250237329e-05, + "loss": 3.9501, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672230655486277e-05, + "loss": 3.9462, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671392060735225e-05, + "loss": 3.9396, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670555103864546e-05, + "loss": 3.9601, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669716509113494e-05, + "loss": 3.94, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668877914362442e-05, + "loss": 3.9329, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680393196113906e-05, + "loss": 3.9392, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672007248603386e-05, + "loss": 3.9502, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663621301092866e-05, + "loss": 3.9463, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655235353582346e-05, + "loss": 3.9399, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.6646865784875555e-05, + "loss": 3.9301, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.6638479837365035e-05, + "loss": 3.9297, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.6630093889854515e-05, + "loss": 3.9492, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621707942343995e-05, + "loss": 3.9211, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661332199483347e-05, + "loss": 3.9349, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660493604732295e-05, + "loss": 3.9449, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659655009981243e-05, + "loss": 3.9334, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588180531105644e-05, + "loss": 3.9317, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579794583595124e-05, + "loss": 3.9358, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571408636084604e-05, + "loss": 3.9288, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6563022688574084e-05, + "loss": 3.9354, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655465311986729e-05, + "loss": 3.9331, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654626717235677e-05, + "loss": 3.9334, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653788122484625e-05, + "loss": 3.9397, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652949527733573e-05, + "loss": 3.9398, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652112570862894e-05, + "loss": 3.9363, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651273976111842e-05, + "loss": 3.9236, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.65043538136079e-05, + "loss": 3.9308, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649596786609738e-05, + "loss": 3.9271, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.64875982973906e-05, + "loss": 3.9166, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647921234988008e-05, + "loss": 3.9319, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647082640236956e-05, + "loss": 3.9188, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646244045485904e-05, + "loss": 3.9365, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645405450734852e-05, + "loss": 3.9208, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644568493864173e-05, + "loss": 3.9265, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437298991131207e-05, + "loss": 3.913, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428913043620687e-05, + "loss": 3.9264, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420527096110166e-05, + "loss": 3.9175, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412157527403376e-05, + "loss": 3.9366, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403771579892856e-05, + "loss": 3.9302, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395385632382335e-05, + "loss": 3.9228, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6386999684871815e-05, + "loss": 3.9125, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637863011616503e-05, + "loss": 3.9218, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637024416865451e-05, + "loss": 3.9305, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636185822114399e-05, + "loss": 3.9351, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635347227363347e-05, + "loss": 3.9227, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634508632612295e-05, + "loss": 3.9291, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633671675741616e-05, + "loss": 3.9219, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632833080990564e-05, + "loss": 3.9251, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631994486239512e-05, + "loss": 3.9153, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.63115589148846e-05, + "loss": 3.918, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630318934617781e-05, + "loss": 3.9219, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629480339866729e-05, + "loss": 3.9091, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628641745115677e-05, + "loss": 3.9175, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627803150364625e-05, + "loss": 3.9183, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269661934939465e-05, + "loss": 3.9144, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261275987428945e-05, + "loss": 3.9166, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252890039918425e-05, + "loss": 3.9131, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9529712200164795, + "eval_runtime": 305.1254, + "eval_samples_per_second": 1250.604, + "eval_steps_per_second": 39.082, + "step": 228960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6244504092407905e-05, + "loss": 3.9019, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.6236118144897385e-05, + "loss": 3.9039, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.6227732197386865e-05, + "loss": 3.9196, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.6219346249876345e-05, + "loss": 3.9091, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.6210960302365825e-05, + "loss": 3.9205, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.6202574354855305e-05, + "loss": 3.8978, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619418840734478e-05, + "loss": 3.9082, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618580245983426e-05, + "loss": 3.8992, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6177432891127474e-05, + "loss": 3.9144, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.6169046943616954e-05, + "loss": 3.9102, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.6160660996106434e-05, + "loss": 3.909, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.6152275048595913e-05, + "loss": 3.9101, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614390547988913e-05, + "loss": 3.8923, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.61355195323786e-05, + "loss": 3.8986, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612713358486808e-05, + "loss": 3.901, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611874763735756e-05, + "loss": 3.8955, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611037806865078e-05, + "loss": 3.897, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610199212114025e-05, + "loss": 3.9007, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609360617362973e-05, + "loss": 3.8908, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.608522022611921e-05, + "loss": 3.9275, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607685065741242e-05, + "loss": 3.9005, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.606846470990191e-05, + "loss": 3.9013, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.606007876239139e-05, + "loss": 3.9039, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605169281488087e-05, + "loss": 3.909, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.6043323246174076e-05, + "loss": 3.8912, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.6034937298663556e-05, + "loss": 3.901, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.6026551351153036e-05, + "loss": 3.8964, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018165403642516e-05, + "loss": 3.8969, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009795834935725e-05, + "loss": 3.8855, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.6001409887425205e-05, + "loss": 3.8952, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.5993023939914685e-05, + "loss": 3.906, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.5984654371207894e-05, + "loss": 3.8978, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.5976268423697374e-05, + "loss": 3.8999, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596788247618686e-05, + "loss": 3.8976, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.595949652867634e-05, + "loss": 3.8934, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.595111058116582e-05, + "loss": 3.8978, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.59427246336553e-05, + "loss": 3.8786, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593433868614478e-05, + "loss": 3.8932, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592596911743799e-05, + "loss": 3.8758, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591758316992747e-05, + "loss": 3.8922, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590919722241695e-05, + "loss": 3.8847, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590081127490643e-05, + "loss": 3.8957, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589244170619964e-05, + "loss": 3.8893, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588405575868912e-05, + "loss": 3.8835, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.58756698111786e-05, + "loss": 3.893, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586728386366808e-05, + "loss": 3.889, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.5858914294961295e-05, + "loss": 3.8885, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.5850528347450774e-05, + "loss": 3.8838, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.5842142399940254e-05, + "loss": 3.87, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.5833756452429734e-05, + "loss": 3.8889, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.5825386883722943e-05, + "loss": 3.8812, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.5817000936212423e-05, + "loss": 3.885, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.58086149887019e-05, + "loss": 3.8703, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580022904119138e-05, + "loss": 3.8917, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579184309368086e-05, + "loss": 3.8613, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.578347352497407e-05, + "loss": 3.8972, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577508757746355e-05, + "loss": 3.8641, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576670162995303e-05, + "loss": 3.8825, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575831568244251e-05, + "loss": 3.8782, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.574994611373573e-05, + "loss": 3.8744, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.574156016622521e-05, + "loss": 3.8703, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.573317421871469e-05, + "loss": 3.8812, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.57248046500079e-05, + "loss": 3.8582, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571641870249738e-05, + "loss": 3.8639, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570803275498686e-05, + "loss": 3.8804, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569964680747634e-05, + "loss": 3.8749, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.5691277238769546e-05, + "loss": 3.8675, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.5682891291259026e-05, + "loss": 3.8688, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.5674505343748506e-05, + "loss": 3.8583, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.5666119396237986e-05, + "loss": 3.8695, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.56577498275312e-05, + "loss": 3.8752, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564936388002068e-05, + "loss": 3.8729, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564097793251016e-05, + "loss": 3.885, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563259198499964e-05, + "loss": 3.8774, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.562422241629285e-05, + "loss": 3.8793, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561583646878233e-05, + "loss": 3.8564, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560745052127181e-05, + "loss": 3.8701, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559906457376129e-05, + "loss": 3.8751, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.55906950050545e-05, + "loss": 3.8579, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558230905754398e-05, + "loss": 3.8721, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557392311003346e-05, + "loss": 3.8663, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556553716252294e-05, + "loss": 3.8756, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557167593816156e-05, + "loss": 3.8692, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548781646305635e-05, + "loss": 3.8531, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.5540395698795115e-05, + "loss": 3.8644, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.5532009751284595e-05, + "loss": 3.8687, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.5523640182577804e-05, + "loss": 3.8758, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.5515254235067284e-05, + "loss": 3.8689, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.5506868287556764e-05, + "loss": 3.8712, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.5498482340046244e-05, + "loss": 3.8773, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.5490112771339453e-05, + "loss": 3.8548, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.5481726823828933e-05, + "loss": 3.87, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547334087631841e-05, + "loss": 3.8613, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546495492880789e-05, + "loss": 3.8606, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545658536010111e-05, + "loss": 3.8787, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544819941259059e-05, + "loss": 3.8617, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543981346508007e-05, + "loss": 3.8516, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543142751756955e-05, + "loss": 3.8607, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542305794886276e-05, + "loss": 3.8682, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541467200135224e-05, + "loss": 3.867, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.540628605384172e-05, + "loss": 3.8599, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.53979001063312e-05, + "loss": 3.8527, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.538953053762441e-05, + "loss": 3.8514, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538114459011389e-05, + "loss": 3.8708, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.537275864260337e-05, + "loss": 3.8415, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536437269509285e-05, + "loss": 3.8562, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535600312638606e-05, + "loss": 3.8652, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.534761717887554e-05, + "loss": 3.859, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533923123136502e-05, + "loss": 3.8495, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.53308452838545e-05, + "loss": 3.8614, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532247571514771e-05, + "loss": 3.8545, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531408976763719e-05, + "loss": 3.8548, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.530570382012667e-05, + "loss": 3.8582, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529731787261615e-05, + "loss": 3.8548, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528894830390936e-05, + "loss": 3.8677, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528056235639884e-05, + "loss": 3.8576, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527219278769205e-05, + "loss": 3.8607, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526380684018153e-05, + "loss": 3.8483, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255420892671017e-05, + "loss": 3.8546, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5247034945160496e-05, + "loss": 3.8553, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.5238648997649976e-05, + "loss": 3.8413, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523026305013945e-05, + "loss": 3.8545, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522187710262893e-05, + "loss": 3.8463, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521349115511841e-05, + "loss": 3.8572, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.5205121586411625e-05, + "loss": 3.8448, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.51967356389011e-05, + "loss": 3.8536, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518834969139058e-05, + "loss": 3.832, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.517996374388006e-05, + "loss": 3.8531, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.5171594175173274e-05, + "loss": 3.8452, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.5163208227662754e-05, + "loss": 3.8577, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.5154822280152234e-05, + "loss": 3.8542, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.5146436332641714e-05, + "loss": 3.8541, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513806676393492e-05, + "loss": 3.8358, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.51296808164244e-05, + "loss": 3.8525, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512129486891388e-05, + "loss": 3.8549, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511290892140336e-05, + "loss": 3.8602, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510453935269657e-05, + "loss": 3.8514, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509615340518605e-05, + "loss": 3.853, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508776745767553e-05, + "loss": 3.85, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507938151016501e-05, + "loss": 3.8554, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507101194145822e-05, + "loss": 3.8405, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506262599394771e-05, + "loss": 3.8471, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505424004643719e-05, + "loss": 3.8479, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504585409892667e-05, + "loss": 3.8381, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503748453021988e-05, + "loss": 3.842, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502909858270936e-05, + "loss": 3.8485, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502071263519884e-05, + "loss": 3.8414, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501232668768832e-05, + "loss": 3.8413, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.5003957118981526e-05, + "loss": 3.8486, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9122109413146973, + "eval_runtime": 304.2137, + "eval_samples_per_second": 1254.352, + "eval_steps_per_second": 39.199, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995571171471006e-05, + "loss": 3.8285, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987185223960486e-05, + "loss": 3.8335, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978799276449966e-05, + "loss": 3.8448, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970413328939446e-05, + "loss": 3.8415, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962027381428926e-05, + "loss": 3.8521, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953641433918406e-05, + "loss": 3.8288, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945255486407886e-05, + "loss": 3.8365, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493686953889737e-05, + "loss": 3.8303, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492849997019058e-05, + "loss": 3.8434, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492011402268006e-05, + "loss": 3.842, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491172807516954e-05, + "loss": 3.8327, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490334212765902e-05, + "loss": 3.8477, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489498893775596e-05, + "loss": 3.8196, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488660299024544e-05, + "loss": 3.8308, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487821704273492e-05, + "loss": 3.8337, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698310952244e-05, + "loss": 3.8264, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486144514771388e-05, + "loss": 3.8279, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485305920020336e-05, + "loss": 3.8319, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484467325269284e-05, + "loss": 3.826, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836287305182326e-05, + "loss": 3.8566, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827917736475535e-05, + "loss": 3.8338, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819531788965015e-05, + "loss": 3.8313, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811145841454495e-05, + "loss": 3.8389, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802759893943975e-05, + "loss": 3.8409, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794390325237184e-05, + "loss": 3.822, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.4786004377726664e-05, + "loss": 3.8335, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.8287, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476924886150935e-05, + "loss": 3.8287, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476086291399883e-05, + "loss": 3.8207, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475247696648831e-05, + "loss": 3.8289, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474409101897779e-05, + "loss": 3.8432, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473572145027101e-05, + "loss": 3.8311, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472733550276049e-05, + "loss": 3.8332, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471894955524997e-05, + "loss": 3.8337, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471056360773945e-05, + "loss": 3.828, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470217766022893e-05, + "loss": 3.8315, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469380809152214e-05, + "loss": 3.8147, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468542214401162e-05, + "loss": 3.8253, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.46770361965011e-05, + "loss": 3.8151, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466865024899058e-05, + "loss": 3.8226, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466026430148005e-05, + "loss": 3.8223, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465187835396953e-05, + "loss": 3.8306, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464349240645902e-05, + "loss": 3.8249, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.46351064589485e-05, + "loss": 3.8227, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626736890241707e-05, + "loss": 3.8271, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618350942731186e-05, + "loss": 3.823, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609964995220666e-05, + "loss": 3.8253, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601579047710146e-05, + "loss": 3.8186, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593209479003356e-05, + "loss": 3.8065, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584823531492835e-05, + "loss": 3.8274, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576437583982315e-05, + "loss": 3.8144, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568051636471795e-05, + "loss": 3.8242, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559682067765004e-05, + "loss": 3.8102, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551296120254484e-05, + "loss": 3.8224, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454291017274397e-05, + "loss": 3.8013, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453454060403718e-05, + "loss": 3.8327, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452615465652666e-05, + "loss": 3.8012, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451776870901614e-05, + "loss": 3.8139, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450938276150562e-05, + "loss": 3.8222, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450101319279883e-05, + "loss": 3.8104, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492643624092045e-05, + "loss": 3.8122, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8148, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.8039, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446748578156048e-05, + "loss": 3.7985, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459116212853694e-05, + "loss": 3.8179, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.8133, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.8035, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433958370322134e-05, + "loss": 3.8112, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425572422811614e-05, + "loss": 3.7972, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417186475301094e-05, + "loss": 3.8073, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408800527790574e-05, + "loss": 3.814, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440043095908378e-05, + "loss": 3.8101, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439204501157326e-05, + "loss": 3.8215, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438365906406274e-05, + "loss": 3.8155, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437527311655222e-05, + "loss": 3.8245, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436690354784543e-05, + "loss": 3.7974, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435851760033491e-05, + "loss": 3.8094, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435013165282439e-05, + "loss": 3.8127, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434174570531388e-05, + "loss": 3.7947, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433337613660709e-05, + "loss": 3.8156, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432499018909657e-05, + "loss": 3.8085, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431660424158605e-05, + "loss": 3.8138, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308234672879257e-05, + "loss": 3.8107, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299848725368737e-05, + "loss": 3.7938, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291462777858217e-05, + "loss": 3.8077, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283076830347696e-05, + "loss": 3.8075, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274690882837176e-05, + "loss": 3.8147, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266304935326656e-05, + "loss": 3.8113, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257918987816136e-05, + "loss": 3.8149, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249533040305616e-05, + "loss": 3.8128, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424116347159883e-05, + "loss": 3.7996, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423277752408831e-05, + "loss": 3.8098, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422439157657779e-05, + "loss": 3.7996, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421600562906727e-05, + "loss": 3.8091, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420763606036048e-05, + "loss": 3.8197, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419925011284996e-05, + "loss": 3.8018, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419086416533944e-05, + "loss": 3.7976, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418247821782892e-05, + "loss": 3.7998, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417410864912213e-05, + "loss": 3.8081, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416572270161161e-05, + "loss": 3.8152, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415733675410109e-05, + "loss": 3.7986, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41489671853943e-05, + "loss": 3.7974, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414058123788378e-05, + "loss": 3.7936, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132195290373266e-05, + "loss": 3.8132, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123809342862746e-05, + "loss": 3.7862, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115423395352226e-05, + "loss": 3.798, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107037447841706e-05, + "loss": 3.8065, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098651500331186e-05, + "loss": 3.801, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090281931624395e-05, + "loss": 3.7937, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081895984113875e-05, + "loss": 3.8059, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073510036603355e-05, + "loss": 3.7978, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065124089092835e-05, + "loss": 3.7953, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405673814158231e-05, + "loss": 3.803, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404835219407179e-05, + "loss": 3.8005, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403996624656127e-05, + "loss": 3.8088, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403158029905075e-05, + "loss": 3.8031, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.40232271091477e-05, + "loss": 3.8011, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401484116163718e-05, + "loss": 3.7911, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400645521412666e-05, + "loss": 3.8003, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399806926661613e-05, + "loss": 3.7963, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398968331910561e-05, + "loss": 3.7838, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398131375039883e-05, + "loss": 3.8001, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397292780288831e-05, + "loss": 3.7889, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396454185537778e-05, + "loss": 3.8021, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395615590786726e-05, + "loss": 3.7939, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394776996035674e-05, + "loss": 3.7979, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393938401284622e-05, + "loss": 3.7783, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.39309980653357e-05, + "loss": 3.7947, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392261211782519e-05, + "loss": 3.7949, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.39142425491184e-05, + "loss": 3.7978, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390585660160788e-05, + "loss": 3.7982, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389747065409736e-05, + "loss": 3.8016, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388908470658684e-05, + "loss": 3.7791, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388069875907632e-05, + "loss": 3.7993, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872329190369526e-05, + "loss": 3.8019, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863943242859006e-05, + "loss": 3.7998, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855557295348486e-05, + "loss": 3.7985, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847171347837966e-05, + "loss": 3.8029, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838801779131175e-05, + "loss": 3.7938, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830415831620655e-05, + "loss": 3.8011, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382202988411014e-05, + "loss": 3.7847, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381364393659962e-05, + "loss": 3.7958, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.38052579890891e-05, + "loss": 3.7883, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379687204157858e-05, + "loss": 3.7882, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378850247287179e-05, + "loss": 3.7902, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378011652536127e-05, + "loss": 3.7898, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377173057785075e-05, + "loss": 3.7933, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376334463034023e-05, + "loss": 3.7835, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375495868282971e-05, + "loss": 3.7965, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8872458934783936, + "eval_runtime": 304.9488, + "eval_samples_per_second": 1251.328, + "eval_steps_per_second": 39.105, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374657273531919e-05, + "loss": 3.7841, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373818678780867e-05, + "loss": 3.7787, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729800840298144e-05, + "loss": 3.7916, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372143127159136e-05, + "loss": 3.791, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371304532408084e-05, + "loss": 3.7925, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370465937657032e-05, + "loss": 3.7811, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.3696289807863535e-05, + "loss": 3.781, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.3687903860353015e-05, + "loss": 3.7794, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679517912842495e-05, + "loss": 3.7875, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367113196533197e-05, + "loss": 3.792, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366274601782145e-05, + "loss": 3.7797, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365436007031093e-05, + "loss": 3.7917, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3645990501604144e-05, + "loss": 3.7735, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363760455409362e-05, + "loss": 3.7774, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.36292186065831e-05, + "loss": 3.7819, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362083265907258e-05, + "loss": 3.7729, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612446711562064e-05, + "loss": 3.7769, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604060764051544e-05, + "loss": 3.781, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359569119534475e-05, + "loss": 3.7726, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358730524783423e-05, + "loss": 3.8029, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357891930032371e-05, + "loss": 3.7861, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357053335281319e-05, + "loss": 3.7815, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356214740530267e-05, + "loss": 3.784, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355377783659588e-05, + "loss": 3.792, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354539188908536e-05, + "loss": 3.7713, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353700594157484e-05, + "loss": 3.7809, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352861999406432e-05, + "loss": 3.7811, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.35202340465538e-05, + "loss": 3.7737, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351184809904328e-05, + "loss": 3.7695, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350346215153276e-05, + "loss": 3.7802, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349509258282598e-05, + "loss": 3.7911, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348670663531546e-05, + "loss": 3.7818, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347832068780494e-05, + "loss": 3.7863, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.346993474029442e-05, + "loss": 3.7809, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.34615487927839e-05, + "loss": 3.7761, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453179224077106e-05, + "loss": 3.7808, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444793276566586e-05, + "loss": 3.771, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436407329056066e-05, + "loss": 3.7713, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428021381545546e-05, + "loss": 3.7662, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419635434035026e-05, + "loss": 3.7723, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411249486524506e-05, + "loss": 3.7718, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402879917817715e-05, + "loss": 3.7792, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394493970307195e-05, + "loss": 3.7741, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338610802279668e-05, + "loss": 3.7739, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377722075286155e-05, + "loss": 3.7796, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369336127775635e-05, + "loss": 3.7739, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360950180265115e-05, + "loss": 3.777, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352564232754595e-05, + "loss": 3.7702, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344194664047804e-05, + "loss": 3.7563, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335808716537284e-05, + "loss": 3.7783, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.33274391478305e-05, + "loss": 3.7676, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331905320031998e-05, + "loss": 3.7748, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331066725280945e-05, + "loss": 3.7614, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330228130529893e-05, + "loss": 3.7726, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329389535778842e-05, + "loss": 3.751, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328552578908163e-05, + "loss": 3.7825, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327713984157111e-05, + "loss": 3.7564, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326875389406059e-05, + "loss": 3.7698, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326036794655007e-05, + "loss": 3.7738, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325198199903955e-05, + "loss": 3.7604, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324361243033276e-05, + "loss": 3.7606, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323522648282224e-05, + "loss": 3.7731, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322684053531172e-05, + "loss": 3.7521, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.32184545878012e-05, + "loss": 3.7513, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321008501909441e-05, + "loss": 3.7689, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320169907158389e-05, + "loss": 3.7689, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193313124073373e-05, + "loss": 3.753, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318492717656285e-05, + "loss": 3.7673, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317654122905233e-05, + "loss": 3.7483, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316815528154181e-05, + "loss": 3.758, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315976933403129e-05, + "loss": 3.768, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.31513997653245e-05, + "loss": 3.7644, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314301381781398e-05, + "loss": 3.7702, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313464424910719e-05, + "loss": 3.7686, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312625830159667e-05, + "loss": 3.7798, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311787235408615e-05, + "loss": 3.7511, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310948640657563e-05, + "loss": 3.7675, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310110045906511e-05, + "loss": 3.768, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309273089035833e-05, + "loss": 3.7462, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308434494284781e-05, + "loss": 3.7671, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307595899533729e-05, + "loss": 3.7635, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306757304782677e-05, + "loss": 3.7646, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3059203479119976e-05, + "loss": 3.7651, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050817531609456e-05, + "loss": 3.7516, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042431584098936e-05, + "loss": 3.7548, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034045636588416e-05, + "loss": 3.7613, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025676067881625e-05, + "loss": 3.7712, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017290120371105e-05, + "loss": 3.7594, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008904172860585e-05, + "loss": 3.7694, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000518225350065e-05, + "loss": 3.7712, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299214865664328e-05, + "loss": 3.754, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298376270913276e-05, + "loss": 3.762, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297537676162224e-05, + "loss": 3.7531, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296699081411172e-05, + "loss": 3.763, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295862124540493e-05, + "loss": 3.7791, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295023529789441e-05, + "loss": 3.751, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294184935038389e-05, + "loss": 3.754, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293346340287337e-05, + "loss": 3.7498, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292507745536285e-05, + "loss": 3.7632, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291669150785233e-05, + "loss": 3.7719, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290832193914554e-05, + "loss": 3.7545, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289993599163502e-05, + "loss": 3.7535, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.28915500441245e-05, + "loss": 3.7428, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288316409661398e-05, + "loss": 3.769, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287477814910346e-05, + "loss": 3.7381, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286639220159294e-05, + "loss": 3.7557, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285800625408242e-05, + "loss": 3.7573, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849636685375634e-05, + "loss": 3.7591, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841250737865114e-05, + "loss": 3.7495, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283286479035459e-05, + "loss": 3.7578, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282447884284407e-05, + "loss": 3.7561, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281609289533355e-05, + "loss": 3.7513, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807723326626756e-05, + "loss": 3.7603, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799337379116236e-05, + "loss": 3.7557, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2790951431605716e-05, + "loss": 3.7631, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782565484095196e-05, + "loss": 3.7623, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277419591538841e-05, + "loss": 3.755, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276580996787789e-05, + "loss": 3.7481, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275742402036737e-05, + "loss": 3.7546, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274903807285685e-05, + "loss": 3.7547, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274066850415006e-05, + "loss": 3.7424, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273228255663954e-05, + "loss": 3.7546, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272389660912902e-05, + "loss": 3.7426, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.27155106616185e-05, + "loss": 3.7569, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270712471410798e-05, + "loss": 3.7504, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269875514540119e-05, + "loss": 3.7509, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269036919789067e-05, + "loss": 3.7421, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268198325038015e-05, + "loss": 3.747, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267359730286964e-05, + "loss": 3.7512, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2665227734162846e-05, + "loss": 3.7576, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656841786652326e-05, + "loss": 3.7486, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648455839141806e-05, + "loss": 3.7564, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640069891631286e-05, + "loss": 3.7403, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631683944120766e-05, + "loss": 3.7543, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623314375413975e-05, + "loss": 3.7597, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614928427903455e-05, + "loss": 3.7566, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606542480392935e-05, + "loss": 3.7532, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598156532882414e-05, + "loss": 3.7618, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589786964175624e-05, + "loss": 3.7463, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581401016665104e-05, + "loss": 3.7604, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257301506915459e-05, + "loss": 3.7405, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256462912164407e-05, + "loss": 3.7529, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255625955293728e-05, + "loss": 3.7469, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254787360542676e-05, + "loss": 3.745, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253948765791624e-05, + "loss": 3.7483, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253110171040572e-05, + "loss": 3.7436, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252273214169893e-05, + "loss": 3.7575, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251434619418841e-05, + "loss": 3.7341, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250596024667789e-05, + "loss": 3.759, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8707971572875977, + "eval_runtime": 305.2584, + "eval_samples_per_second": 1250.059, + "eval_steps_per_second": 39.065, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249757429916737e-05, + "loss": 3.7363, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248918835165685e-05, + "loss": 3.7347, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248080240414633e-05, + "loss": 3.7503, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247241645663581e-05, + "loss": 3.7505, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464046887929024e-05, + "loss": 3.7499, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455660940418504e-05, + "loss": 3.7384, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447274992907984e-05, + "loss": 3.7344, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438889045397464e-05, + "loss": 3.7415, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243051947669067e-05, + "loss": 3.7449, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242213352918015e-05, + "loss": 3.7496, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241374758166963e-05, + "loss": 3.7424, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240536163415911e-05, + "loss": 3.7464, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239699206545232e-05, + "loss": 3.7357, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.23886061179418e-05, + "loss": 3.7339, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238022017043128e-05, + "loss": 3.7395, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237183422292076e-05, + "loss": 3.7323, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236346465421398e-05, + "loss": 3.7335, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235507870670346e-05, + "loss": 3.7413, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234669275919294e-05, + "loss": 3.7328, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233830681168242e-05, + "loss": 3.7579, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2329937242975627e-05, + "loss": 3.7474, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321551295465106e-05, + "loss": 3.7385, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313165347954586e-05, + "loss": 3.7434, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304779400444066e-05, + "loss": 3.7529, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229639345293354e-05, + "loss": 3.7275, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288023884226755e-05, + "loss": 3.7417, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279637936716235e-05, + "loss": 3.7365, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271251989205715e-05, + "loss": 3.7351, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262866041695195e-05, + "loss": 3.7288, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254480094184675e-05, + "loss": 3.7393, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224611052547789e-05, + "loss": 3.7494, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237724577967364e-05, + "loss": 3.7396, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229338630456844e-05, + "loss": 3.7472, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220952682946324e-05, + "loss": 3.7421, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212566735435804e-05, + "loss": 3.734, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220419716672901e-05, + "loss": 3.7393, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219581121921849e-05, + "loss": 3.7333, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218742527170797e-05, + "loss": 3.7289, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217903932419745e-05, + "loss": 3.7265, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217066975549067e-05, + "loss": 3.73, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216228380798015e-05, + "loss": 3.7313, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215389786046963e-05, + "loss": 3.7394, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214551191295911e-05, + "loss": 3.7339, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213714234425232e-05, + "loss": 3.734, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.21287563967418e-05, + "loss": 3.7395, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212037044923128e-05, + "loss": 3.7317, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211198450172076e-05, + "loss": 3.7382, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210361493301397e-05, + "loss": 3.7307, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209522898550345e-05, + "loss": 3.713, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208684303799293e-05, + "loss": 3.7406, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207845709048241e-05, + "loss": 3.7265, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207008752177562e-05, + "loss": 3.7372, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.20617015742651e-05, + "loss": 3.726, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205331562675458e-05, + "loss": 3.7267, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204492967924406e-05, + "loss": 3.7171, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203656011053727e-05, + "loss": 3.7359, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202817416302675e-05, + "loss": 3.7213, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201978821551623e-05, + "loss": 3.7289, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201140226800571e-05, + "loss": 3.7381, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200303269929892e-05, + "loss": 3.7174, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.19946467517884e-05, + "loss": 3.7184, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198626080427788e-05, + "loss": 3.7394, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197787485676736e-05, + "loss": 3.7078, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969505288060576e-05, + "loss": 3.7137, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961119340550056e-05, + "loss": 3.728, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952733393039536e-05, + "loss": 3.7284, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944347445529016e-05, + "loss": 3.7167, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1935961498018496e-05, + "loss": 3.7299, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927591929311705e-05, + "loss": 3.7108, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919205981801185e-05, + "loss": 3.7167, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910820034290665e-05, + "loss": 3.7313, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902434086780145e-05, + "loss": 3.724, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894064518073354e-05, + "loss": 3.731, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885678570562834e-05, + "loss": 3.7313, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877292623052314e-05, + "loss": 3.7388, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868906675541794e-05, + "loss": 3.7135, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186053710683501e-05, + "loss": 3.7258, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185215115932449e-05, + "loss": 3.7286, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184376521181397e-05, + "loss": 3.7097, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183537926430345e-05, + "loss": 3.7284, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182700969559666e-05, + "loss": 3.7272, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181862374808614e-05, + "loss": 3.728, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181023780057562e-05, + "loss": 3.7252, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.18018518530651e-05, + "loss": 3.715, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179348228435831e-05, + "loss": 3.7142, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178509633684779e-05, + "loss": 3.7255, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177671038933727e-05, + "loss": 3.7285, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176832444182675e-05, + "loss": 3.7252, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175993849431623e-05, + "loss": 3.7314, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751568925609444e-05, + "loss": 3.7317, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743182978098924e-05, + "loss": 3.7195, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734797030588404e-05, + "loss": 3.7246, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726411083077883e-05, + "loss": 3.7137, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171804151437109e-05, + "loss": 3.7293, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170965556686057e-05, + "loss": 3.7365, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170126961935005e-05, + "loss": 3.7169, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169288367183953e-05, + "loss": 3.7132, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168451410313274e-05, + "loss": 3.7113, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167612815562222e-05, + "loss": 3.7249, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.16677422081117e-05, + "loss": 3.7342, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165935626060118e-05, + "loss": 3.7176, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.16509866918944e-05, + "loss": 3.7185, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164260074438388e-05, + "loss": 3.711, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163421479687336e-05, + "loss": 3.7273, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162582884936284e-05, + "loss": 3.7053, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617459280656046e-05, + "loss": 3.7197, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609073333145526e-05, + "loss": 3.7144, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600687385635006e-05, + "loss": 3.7266, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592301438124486e-05, + "loss": 3.7114, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1583931869417695e-05, + "loss": 3.7194, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575545921907175e-05, + "loss": 3.7194, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567159974396655e-05, + "loss": 3.7119, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558774026886135e-05, + "loss": 3.7247, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1550388079375615e-05, + "loss": 3.7201, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154201851066883e-05, + "loss": 3.7254, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153363256315831e-05, + "loss": 3.7264, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152524661564779e-05, + "loss": 3.7124, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151686066813727e-05, + "loss": 3.7211, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150849109943048e-05, + "loss": 3.7146, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150010515191996e-05, + "loss": 3.7208, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149171920440944e-05, + "loss": 3.7134, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148333325689891e-05, + "loss": 3.7129, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147496368819213e-05, + "loss": 3.7036, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146657774068161e-05, + "loss": 3.7204, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145819179317109e-05, + "loss": 3.7118, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144980584566057e-05, + "loss": 3.7177, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441436276953785e-05, + "loss": 3.7038, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433050329443265e-05, + "loss": 3.7138, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424664381932744e-05, + "loss": 3.7128, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141627843442222e-05, + "loss": 3.7236, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407908865715434e-05, + "loss": 3.7121, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399522918204913e-05, + "loss": 3.7205, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139113697069439e-05, + "loss": 3.703, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138275102318387e-05, + "loss": 3.7206, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137438145447708e-05, + "loss": 3.7229, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136599550696656e-05, + "loss": 3.7189, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135760955945604e-05, + "loss": 3.7179, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134922361194552e-05, + "loss": 3.7245, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134085404323874e-05, + "loss": 3.7122, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133246809572821e-05, + "loss": 3.7261, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132408214821769e-05, + "loss": 3.706, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131569620070717e-05, + "loss": 3.7181, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130732663200039e-05, + "loss": 3.711, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129894068448986e-05, + "loss": 3.7103, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129055473697934e-05, + "loss": 3.7084, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128216878946882e-05, + "loss": 3.7066, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273799220762036e-05, + "loss": 3.7189, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265413273251516e-05, + "loss": 3.7022, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1257027325740996e-05, + "loss": 3.7248, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8602747917175293, + "eval_runtime": 315.2674, + "eval_samples_per_second": 1210.372, + "eval_steps_per_second": 37.825, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248641378230476e-05, + "loss": 3.7043, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240255430719956e-05, + "loss": 3.6986, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231885862013165e-05, + "loss": 3.7135, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223499914502645e-05, + "loss": 3.7134, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1215113966992125e-05, + "loss": 3.7121, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206728019481605e-05, + "loss": 3.707, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1198358450774814e-05, + "loss": 3.7036, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1189972503264294e-05, + "loss": 3.7029, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1181586555753774e-05, + "loss": 3.7123, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1173200608243254e-05, + "loss": 3.7161, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116483103953647e-05, + "loss": 3.7074, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115644509202595e-05, + "loss": 3.706, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114805914451543e-05, + "loss": 3.7037, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113967319700491e-05, + "loss": 3.6996, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113130362829812e-05, + "loss": 3.7038, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.11229176807876e-05, + "loss": 3.6952, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111453173327708e-05, + "loss": 3.703, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110614578576656e-05, + "loss": 3.7068, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109777621705977e-05, + "loss": 3.6982, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108939026954925e-05, + "loss": 3.7199, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108100432203873e-05, + "loss": 3.7166, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107261837452821e-05, + "loss": 3.7031, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064248805821423e-05, + "loss": 3.7097, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055862858310903e-05, + "loss": 3.7156, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104747691080038e-05, + "loss": 3.694, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103909096328986e-05, + "loss": 3.7072, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103072139458307e-05, + "loss": 3.7061, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102233544707255e-05, + "loss": 3.6986, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101394949956203e-05, + "loss": 3.6947, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100556355205151e-05, + "loss": 3.7084, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099719398334472e-05, + "loss": 3.7135, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.09888080358342e-05, + "loss": 3.7093, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098042208832368e-05, + "loss": 3.7136, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097203614081316e-05, + "loss": 3.7045, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096366657210638e-05, + "loss": 3.7004, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095528062459586e-05, + "loss": 3.7071, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094689467708534e-05, + "loss": 3.7023, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093850872957482e-05, + "loss": 3.6917, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930139160868026e-05, + "loss": 3.6924, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921753213357506e-05, + "loss": 3.6967, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913367265846986e-05, + "loss": 3.6974, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0904981318336466e-05, + "loss": 3.7066, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896611749629675e-05, + "loss": 3.7023, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888225802119155e-05, + "loss": 3.6984, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879839854608635e-05, + "loss": 3.7067, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871453907098115e-05, + "loss": 3.7014, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086308433839133e-05, + "loss": 3.7041, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085469839088081e-05, + "loss": 3.6991, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084631244337029e-05, + "loss": 3.6756, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083792649585977e-05, + "loss": 3.7114, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082954054834925e-05, + "loss": 3.6932, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082117097964246e-05, + "loss": 3.7055, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081278503213194e-05, + "loss": 3.6921, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080439908462142e-05, + "loss": 3.6963, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079602951591463e-05, + "loss": 3.6852, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078764356840411e-05, + "loss": 3.7001, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077925762089359e-05, + "loss": 3.6904, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077087167338307e-05, + "loss": 3.6932, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076248572587255e-05, + "loss": 3.7073, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754116157165764e-05, + "loss": 3.6872, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745730209655244e-05, + "loss": 3.6845, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737344262144724e-05, + "loss": 3.7045, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728958314634204e-05, + "loss": 3.6793, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072058874592741e-05, + "loss": 3.6797, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071220279841689e-05, + "loss": 3.696, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070381685090637e-05, + "loss": 3.6942, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069543090339585e-05, + "loss": 3.6865, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068706133468906e-05, + "loss": 3.6963, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067867538717854e-05, + "loss": 3.6769, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067028943966802e-05, + "loss": 3.6888, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.06619034921575e-05, + "loss": 3.698, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065353392345072e-05, + "loss": 3.6925, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.06451479759402e-05, + "loss": 3.6996, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063676202842968e-05, + "loss": 3.6967, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062837608091916e-05, + "loss": 3.7039, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062000651221237e-05, + "loss": 3.6808, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061162056470185e-05, + "loss": 3.6972, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060323461719133e-05, + "loss": 3.6941, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059484866968081e-05, + "loss": 3.6796, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058646272217029e-05, + "loss": 3.6958, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578093153463496e-05, + "loss": 3.695, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569707205952976e-05, + "loss": 3.6945, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561321258442456e-05, + "loss": 3.6997, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552935310931936e-05, + "loss": 3.6809, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054456574222515e-05, + "loss": 3.6814, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053617979471463e-05, + "loss": 3.6951, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052779384720411e-05, + "loss": 3.6947, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051940789969359e-05, + "loss": 3.6949, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.05110383309868e-05, + "loss": 3.696, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050265238347628e-05, + "loss": 3.6997, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049426643596576e-05, + "loss": 3.691, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.0485880488455234e-05, + "loss": 3.6893, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047751091974845e-05, + "loss": 3.6837, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046912497223793e-05, + "loss": 3.6966, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046073902472741e-05, + "loss": 3.7014, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045235307721689e-05, + "loss": 3.6892, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0443983508510105e-05, + "loss": 3.6807, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435597560999585e-05, + "loss": 3.681, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427211613489065e-05, + "loss": 3.6907, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041882566597854e-05, + "loss": 3.7047, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410456097271754e-05, + "loss": 3.686, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0402070149761234e-05, + "loss": 3.6878, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039368420225071e-05, + "loss": 3.6823, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038529825474019e-05, + "loss": 3.6907, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.03769286860334e-05, + "loss": 3.6773, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036854273852288e-05, + "loss": 3.6882, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036015679101236e-05, + "loss": 3.6778, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035177084350184e-05, + "loss": 3.695, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034340127479506e-05, + "loss": 3.685, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033501532728454e-05, + "loss": 3.6856, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032662937977401e-05, + "loss": 3.6871, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031824343226349e-05, + "loss": 3.6892, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030987386355671e-05, + "loss": 3.6905, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030148791604618e-05, + "loss": 3.688, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029310196853566e-05, + "loss": 3.6924, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028471602102514e-05, + "loss": 3.6976, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027634645231836e-05, + "loss": 3.6825, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026796050480783e-05, + "loss": 3.6893, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025957455729732e-05, + "loss": 3.6839, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.02511886097868e-05, + "loss": 3.6862, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024281904108001e-05, + "loss": 3.6843, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234433093569486e-05, + "loss": 3.6828, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226047146058966e-05, + "loss": 3.6757, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217661198548446e-05, + "loss": 3.686, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209291629841655e-05, + "loss": 3.6853, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200905682331135e-05, + "loss": 3.6855, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192519734820615e-05, + "loss": 3.6702, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184133787310095e-05, + "loss": 3.6874, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175764218603304e-05, + "loss": 3.6804, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167378271092784e-05, + "loss": 3.6923, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015899232358227e-05, + "loss": 3.6835, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015060637607175e-05, + "loss": 3.6904, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014223680736496e-05, + "loss": 3.6715, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013385085985444e-05, + "loss": 3.6927, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012546491234392e-05, + "loss": 3.69, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.01170789648334e-05, + "loss": 3.6885, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010870939612661e-05, + "loss": 3.6902, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010032344861609e-05, + "loss": 3.6927, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009193750110557e-05, + "loss": 3.6825, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008355155359505e-05, + "loss": 3.6936, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007518198488826e-05, + "loss": 3.6757, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006679603737774e-05, + "loss": 3.6894, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0058410089867224e-05, + "loss": 3.6791, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0050024142356704e-05, + "loss": 3.6848, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004165457364991e-05, + "loss": 3.6733, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003326862613939e-05, + "loss": 3.6768, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002488267862887e-05, + "loss": 3.6863, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001649673111835e-05, + "loss": 3.6741, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000812716241156e-05, + "loss": 3.6946, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.853907585144043, + "eval_runtime": 313.3897, + "eval_samples_per_second": 1217.625, + "eval_steps_per_second": 38.052, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999974121490104e-05, + "loss": 3.6706, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999135526739052e-05, + "loss": 3.6713, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998296931988e-05, + "loss": 3.6785, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997458337236948e-05, + "loss": 3.686, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996621380366269e-05, + "loss": 3.6851, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995782785615218e-05, + "loss": 3.6744, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994944190864166e-05, + "loss": 3.6805, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994105596113114e-05, + "loss": 3.6752, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993268639242435e-05, + "loss": 3.6759, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992430044491383e-05, + "loss": 3.6899, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991591449740331e-05, + "loss": 3.6747, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990752854989279e-05, + "loss": 3.6777, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899158981185996e-05, + "loss": 3.6747, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890773033675476e-05, + "loss": 3.6678, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882387086164956e-05, + "loss": 3.6766, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874001138654436e-05, + "loss": 3.6654, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865631569947645e-05, + "loss": 3.6731, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985724562243713e-05, + "loss": 3.6781, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984885967492661e-05, + "loss": 3.6662, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984047372741609e-05, + "loss": 3.6892, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.98321041587093e-05, + "loss": 3.6884, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982371821119878e-05, + "loss": 3.6747, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981533226368826e-05, + "loss": 3.6752, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980694631617774e-05, + "loss": 3.6851, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979857674747095e-05, + "loss": 3.6716, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979019079996043e-05, + "loss": 3.6743, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978180485244991e-05, + "loss": 3.6768, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977341890493939e-05, + "loss": 3.6721, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97650493362326e-05, + "loss": 3.6693, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756663388722085e-05, + "loss": 3.6741, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748277441211565e-05, + "loss": 3.6805, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739891493701045e-05, + "loss": 3.6837, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731521924994254e-05, + "loss": 3.6818, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723135977483734e-05, + "loss": 3.6741, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714750029973214e-05, + "loss": 3.6696, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706364082462694e-05, + "loss": 3.6797, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.96979945137559e-05, + "loss": 3.6735, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968960856624538e-05, + "loss": 3.6649, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968122261873486e-05, + "loss": 3.6655, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967283667122434e-05, + "loss": 3.6655, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966446710251755e-05, + "loss": 3.6683, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965608115500703e-05, + "loss": 3.6757, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964769520749652e-05, + "loss": 3.6766, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639309259986e-05, + "loss": 3.6734, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963093969127921e-05, + "loss": 3.6734, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962255374376869e-05, + "loss": 3.675, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961416779625817e-05, + "loss": 3.6718, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960578184874765e-05, + "loss": 3.6734, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959741228004086e-05, + "loss": 3.6472, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958902633253034e-05, + "loss": 3.6811, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958064038501982e-05, + "loss": 3.6638, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95722544375093e-05, + "loss": 3.6777, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9563884868802506e-05, + "loss": 3.6641, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555498921291986e-05, + "loss": 3.6646, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954711297378147e-05, + "loss": 3.656, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953872702627095e-05, + "loss": 3.6718, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953035745756416e-05, + "loss": 3.6661, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952197151005364e-05, + "loss": 3.663, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951358556254312e-05, + "loss": 3.6755, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.95051996150326e-05, + "loss": 3.6626, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949683004632581e-05, + "loss": 3.6514, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948844409881529e-05, + "loss": 3.6769, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948005815130477e-05, + "loss": 3.6528, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947167220379425e-05, + "loss": 3.6493, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946330263508746e-05, + "loss": 3.6685, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945491668757694e-05, + "loss": 3.6653, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446530740066426e-05, + "loss": 3.6589, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438144792555906e-05, + "loss": 3.6649, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429775223849115e-05, + "loss": 3.649, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421389276338595e-05, + "loss": 3.6591, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413003328828075e-05, + "loss": 3.6703, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404617381317555e-05, + "loss": 3.6611, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396247812610764e-05, + "loss": 3.6738, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387861865100244e-05, + "loss": 3.6657, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9379475917589724e-05, + "loss": 3.6773, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9371089970079204e-05, + "loss": 3.6536, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936272040137241e-05, + "loss": 3.6701, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935433445386189e-05, + "loss": 3.664, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934594850635138e-05, + "loss": 3.6547, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933756255884086e-05, + "loss": 3.6663, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932919299013407e-05, + "loss": 3.6705, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932080704262355e-05, + "loss": 3.6639, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931242109511303e-05, + "loss": 3.6722, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.93040351476025e-05, + "loss": 3.6503, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929566557889572e-05, + "loss": 3.6524, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.92872796313852e-05, + "loss": 3.6685, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927889368387468e-05, + "loss": 3.6676, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927050773636415e-05, + "loss": 3.6656, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926213816765737e-05, + "loss": 3.6701, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925375222014685e-05, + "loss": 3.6674, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245366272636333e-05, + "loss": 3.6663, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923698032512581e-05, + "loss": 3.6629, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922861075641902e-05, + "loss": 3.6563, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.6704, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211838861397976e-05, + "loss": 3.6684, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203452913887456e-05, + "loss": 3.6645, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919508334518067e-05, + "loss": 3.6565, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918669739767015e-05, + "loss": 3.6535, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178311450159625e-05, + "loss": 3.6603, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169925502649105e-05, + "loss": 3.6768, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916155593394232e-05, + "loss": 3.66, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.91531699864318e-05, + "loss": 3.6612, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914478403892128e-05, + "loss": 3.6546, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913639809141076e-05, + "loss": 3.659, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128028522703976e-05, + "loss": 3.6577, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911964257519345e-05, + "loss": 3.6569, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911125662768293e-05, + "loss": 3.6529, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910287068017241e-05, + "loss": 3.6685, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094501111465625e-05, + "loss": 3.6585, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.90861151639551e-05, + "loss": 3.6595, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907772921644458e-05, + "loss": 3.6536, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906934326893406e-05, + "loss": 3.6637, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060973700227274e-05, + "loss": 3.665, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052587752716754e-05, + "loss": 3.6608, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044201805206234e-05, + "loss": 3.6651, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035815857695714e-05, + "loss": 3.6688, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902744628898892e-05, + "loss": 3.6528, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.90190603414784e-05, + "loss": 3.6659, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901067439396788e-05, + "loss": 3.6544, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900228844645736e-05, + "loss": 3.6605, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899391887775057e-05, + "loss": 3.6555, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898553293024005e-05, + "loss": 3.6529, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897714698272953e-05, + "loss": 3.6517, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896876103521901e-05, + "loss": 3.658, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896039146651223e-05, + "loss": 3.6586, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895200551900171e-05, + "loss": 3.6575, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894361957149119e-05, + "loss": 3.6459, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893523362398067e-05, + "loss": 3.6585, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892686405527388e-05, + "loss": 3.654, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891847810776336e-05, + "loss": 3.6659, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891009216025284e-05, + "loss": 3.6602, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890170621274232e-05, + "loss": 3.659, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893336644035526e-05, + "loss": 3.6469, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8884950696525006e-05, + "loss": 3.6655, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876564749014486e-05, + "loss": 3.6632, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868178801503966e-05, + "loss": 3.6617, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885980923279718e-05, + "loss": 3.6629, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885142328528666e-05, + "loss": 3.6656, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884303733777614e-05, + "loss": 3.6579, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883465139026562e-05, + "loss": 3.6677, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882628182155883e-05, + "loss": 3.6493, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881789587404831e-05, + "loss": 3.6636, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880950992653779e-05, + "loss": 3.6548, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880112397902727e-05, + "loss": 3.6555, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879275441032048e-05, + "loss": 3.6481, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878436846280996e-05, + "loss": 3.6509, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877598251529944e-05, + "loss": 3.6593, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876759656778892e-05, + "loss": 3.653, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759226999082135e-05, + "loss": 3.6656, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.849987030029297, + "eval_runtime": 302.6998, + "eval_samples_per_second": 1260.625, + "eval_steps_per_second": 39.395, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750841051571615e-05, + "loss": 3.6437, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742455104061095e-05, + "loss": 3.6443, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734069156550575e-05, + "loss": 3.6481, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725699587843784e-05, + "loss": 3.6631, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8717313640333264e-05, + "loss": 3.6587, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708927692822744e-05, + "loss": 3.6461, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8700541745312224e-05, + "loss": 3.6578, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869217217660543e-05, + "loss": 3.648, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868378622909491e-05, + "loss": 3.6499, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867540028158439e-05, + "loss": 3.6656, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866701433407387e-05, + "loss": 3.6499, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865864476536709e-05, + "loss": 3.6498, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865025881785657e-05, + "loss": 3.6588, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864187287034605e-05, + "loss": 3.6376, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863348692283553e-05, + "loss": 3.65, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862511735412874e-05, + "loss": 3.6405, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861673140661822e-05, + "loss": 3.6498, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.86083454591077e-05, + "loss": 3.6487, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859995951159718e-05, + "loss": 3.6385, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859158994289039e-05, + "loss": 3.6616, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858320399537987e-05, + "loss": 3.6627, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857481804786935e-05, + "loss": 3.6532, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566432100358827e-05, + "loss": 3.6541, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855806253165204e-05, + "loss": 3.6553, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854967658414152e-05, + "loss": 3.6483, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541290636631e-05, + "loss": 3.6434, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853290468912048e-05, + "loss": 3.6541, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852453512041369e-05, + "loss": 3.6486, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851614917290317e-05, + "loss": 3.6409, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850776322539265e-05, + "loss": 3.6481, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849937727788213e-05, + "loss": 3.6529, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849100770917534e-05, + "loss": 3.6617, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848262176166482e-05, + "loss": 3.6577, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.84742358141543e-05, + "loss": 3.6532, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846584986664378e-05, + "loss": 3.6431, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457480297936996e-05, + "loss": 3.6481, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449094350426476e-05, + "loss": 3.6522, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440708402915956e-05, + "loss": 3.6409, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432322455405436e-05, + "loss": 3.6389, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423952886698645e-05, + "loss": 3.6396, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415566939188125e-05, + "loss": 3.6453, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407180991677605e-05, + "loss": 3.6443, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398795044167085e-05, + "loss": 3.6515, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390425475460294e-05, + "loss": 3.6492, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8382039527949774e-05, + "loss": 3.649, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373653580439254e-05, + "loss": 3.6472, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365267632928734e-05, + "loss": 3.6456, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835689806422195e-05, + "loss": 3.6551, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834851211671143e-05, + "loss": 3.6211, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834012616920091e-05, + "loss": 3.6506, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833174022169039e-05, + "loss": 3.6419, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.83233706529836e-05, + "loss": 3.6544, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831498470547308e-05, + "loss": 3.6395, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830659875796256e-05, + "loss": 3.6417, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829821281045204e-05, + "loss": 3.6286, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828984324174525e-05, + "loss": 3.6463, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828145729423473e-05, + "loss": 3.6453, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827307134672421e-05, + "loss": 3.6349, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826468539921369e-05, + "loss": 3.6522, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8256315830506903e-05, + "loss": 3.6415, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247929882996383e-05, + "loss": 3.6223, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823954393548586e-05, + "loss": 3.6518, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823115798797534e-05, + "loss": 3.6315, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822278841926855e-05, + "loss": 3.6258, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821440247175803e-05, + "loss": 3.6424, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820601652424751e-05, + "loss": 3.6424, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819763057673699e-05, + "loss": 3.6272, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.81892610080302e-05, + "loss": 3.6486, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818087506051968e-05, + "loss": 3.626, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817248911300916e-05, + "loss": 3.6311, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816410316549864e-05, + "loss": 3.6471, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815573359679186e-05, + "loss": 3.6355, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814734764928134e-05, + "loss": 3.6522, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813896170177082e-05, + "loss": 3.6377, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81305757542603e-05, + "loss": 3.6522, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8122206185553506e-05, + "loss": 3.6323, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8113820238042986e-05, + "loss": 3.6498, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.8105434290532466e-05, + "loss": 3.6338, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8097048343021946e-05, + "loss": 3.6349, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8088678774315155e-05, + "loss": 3.6391, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.8080292826804635e-05, + "loss": 3.643, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071906879294115e-05, + "loss": 3.6396, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063520931783595e-05, + "loss": 3.6511, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805515136307681e-05, + "loss": 3.6244, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804676541556629e-05, + "loss": 3.6277, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803837946805577e-05, + "loss": 3.642, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029993520545244e-05, + "loss": 3.6451, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802162395183846e-05, + "loss": 3.6392, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801323800432794e-05, + "loss": 3.6483, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800485205681742e-05, + "loss": 3.6417, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799646610930689e-05, + "loss": 3.6434, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798809654060011e-05, + "loss": 3.6417, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797971059308959e-05, + "loss": 3.6334, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797132464557907e-05, + "loss": 3.643, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796293869806855e-05, + "loss": 3.6472, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954569129361764e-05, + "loss": 3.6391, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946183181851244e-05, + "loss": 3.6354, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793779723434072e-05, + "loss": 3.6241, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.79294112868302e-05, + "loss": 3.6372, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7921041718123413e-05, + "loss": 3.6514, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912655770612893e-05, + "loss": 3.6366, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904269823102367e-05, + "loss": 3.6372, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895883875591847e-05, + "loss": 3.6293, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788751430688506e-05, + "loss": 3.634, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787912835937454e-05, + "loss": 3.6348, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870742411864016e-05, + "loss": 3.6308, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.78623564643535e-05, + "loss": 3.6305, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785398689564671e-05, + "loss": 3.6444, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784560094813619e-05, + "loss": 3.6394, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783721500062567e-05, + "loss": 3.6286, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782884543191889e-05, + "loss": 3.6352, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782045948440837e-05, + "loss": 3.6349, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781207353689784e-05, + "loss": 3.6435, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780368758938732e-05, + "loss": 3.6348, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.77953016418768e-05, + "loss": 3.6432, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786932073170016e-05, + "loss": 3.6442, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777854612565949e-05, + "loss": 3.6295, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777016017814897e-05, + "loss": 3.6416, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776177423063845e-05, + "loss": 3.6313, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7753404661931665e-05, + "loss": 3.6354, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7745018714421145e-05, + "loss": 3.6367, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736632766910625e-05, + "loss": 3.6268, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728246819400105e-05, + "loss": 3.6266, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719877250693314e-05, + "loss": 3.6378, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711491303182794e-05, + "loss": 3.6353, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7703105355672274e-05, + "loss": 3.6341, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7694719408161754e-05, + "loss": 3.6231, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768634983945496e-05, + "loss": 3.6308, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767796389194444e-05, + "loss": 3.6307, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766957794443392e-05, + "loss": 3.6413, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.76611919969234e-05, + "loss": 3.6369, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765282242821662e-05, + "loss": 3.6346, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.76444364807061e-05, + "loss": 3.6222, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763605053319558e-05, + "loss": 3.6463, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762766458568506e-05, + "loss": 3.636, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761929501697827e-05, + "loss": 3.6421, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761090906946775e-05, + "loss": 3.6352, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760252312195723e-05, + "loss": 3.6418, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759413717444671e-05, + "loss": 3.6344, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758576760573992e-05, + "loss": 3.6476, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577381658229397e-05, + "loss": 3.6222, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568995710718877e-05, + "loss": 3.6422, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7560609763208356e-05, + "loss": 3.6289, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755224019450157e-05, + "loss": 3.6319, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754385424699105e-05, + "loss": 3.6272, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753546829948053e-05, + "loss": 3.6276, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752709873077374e-05, + "loss": 3.6326, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751871278326322e-05, + "loss": 3.6329, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.75103268357527e-05, + "loss": 3.6385, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8463985919952393, + "eval_runtime": 303.3041, + "eval_samples_per_second": 1258.114, + "eval_steps_per_second": 39.317, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750194088824218e-05, + "loss": 3.6217, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749355494073166e-05, + "loss": 3.6227, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748516899322114e-05, + "loss": 3.6233, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747678304571062e-05, + "loss": 3.6389, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746841347700383e-05, + "loss": 3.6404, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.746002752949331e-05, + "loss": 3.6197, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74516415819828e-05, + "loss": 3.63, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744325563447228e-05, + "loss": 3.6245, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7434886065765486e-05, + "loss": 3.628, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7426500118254966e-05, + "loss": 3.6397, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7418114170744446e-05, + "loss": 3.625, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409728223233926e-05, + "loss": 3.6283, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401358654527135e-05, + "loss": 3.6348, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392972707016615e-05, + "loss": 3.6148, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384586759506095e-05, + "loss": 3.6254, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376200811995575e-05, + "loss": 3.6141, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367831243288784e-05, + "loss": 3.6271, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359445295778264e-05, + "loss": 3.6278, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735105934826775e-05, + "loss": 3.6172, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734267340075723e-05, + "loss": 3.6352, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733430383205044e-05, + "loss": 3.6388, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732591788453992e-05, + "loss": 3.6277, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.73175319370294e-05, + "loss": 3.6327, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730914598951888e-05, + "loss": 3.6309, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730077642081209e-05, + "loss": 3.6298, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729239047330157e-05, + "loss": 3.6223, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728400452579105e-05, + "loss": 3.6288, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727561857828053e-05, + "loss": 3.6297, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726724900957374e-05, + "loss": 3.6171, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725886306206322e-05, + "loss": 3.6246, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250477114552704e-05, + "loss": 3.6317, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7242091167042184e-05, + "loss": 3.6317, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723372159833539e-05, + "loss": 3.6397, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722533565082487e-05, + "loss": 3.6284, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721694970331435e-05, + "loss": 3.6221, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720856375580383e-05, + "loss": 3.6274, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720019418709704e-05, + "loss": 3.6289, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719180823958652e-05, + "loss": 3.6166, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183422292076e-05, + "loss": 3.617, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717503634456548e-05, + "loss": 3.6205, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716666677585869e-05, + "loss": 3.6183, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715828082834817e-05, + "loss": 3.6268, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714989488083766e-05, + "loss": 3.6279, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714150893332714e-05, + "loss": 3.6288, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713313936462035e-05, + "loss": 3.621, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712475341710983e-05, + "loss": 3.6281, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711636746959931e-05, + "loss": 3.6218, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710798152208879e-05, + "loss": 3.6318, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7099611953381996e-05, + "loss": 3.5994, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7091226005871476e-05, + "loss": 3.6263, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7082840058360956e-05, + "loss": 3.6201, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074454110850436e-05, + "loss": 3.6316, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7066084542143645e-05, + "loss": 3.6167, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057698594633125e-05, + "loss": 3.6166, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704931264712261e-05, + "loss": 3.6113, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704092669961209e-05, + "loss": 3.6183, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.70325571309053e-05, + "loss": 3.6284, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702417118339478e-05, + "loss": 3.6064, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701578523588426e-05, + "loss": 3.633, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700739928837374e-05, + "loss": 3.6185, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699902971966695e-05, + "loss": 3.5977, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699064377215643e-05, + "loss": 3.6283, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698225782464591e-05, + "loss": 3.6104, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697387187713539e-05, + "loss": 3.6032, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.69655023084286e-05, + "loss": 3.6212, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695711636091808e-05, + "loss": 3.6185, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694873041340756e-05, + "loss": 3.6042, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940344465897045e-05, + "loss": 3.6273, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6931974897190254e-05, + "loss": 3.6025, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923588949679734e-05, + "loss": 3.6082, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915203002169214e-05, + "loss": 3.6238, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690681705465869e-05, + "loss": 3.617, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.68984474859519e-05, + "loss": 3.6241, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.689006153844138e-05, + "loss": 3.6172, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688167559093086e-05, + "loss": 3.6284, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873289643420336e-05, + "loss": 3.6121, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686492007471355e-05, + "loss": 3.6278, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685653412720303e-05, + "loss": 3.608, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684814817969251e-05, + "loss": 3.612, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683976223218199e-05, + "loss": 3.6183, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683139266347521e-05, + "loss": 3.6167, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682300671596469e-05, + "loss": 3.6221, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681462076845416e-05, + "loss": 3.6252, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680623482094364e-05, + "loss": 3.6086, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679786525223686e-05, + "loss": 3.6048, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678947930472634e-05, + "loss": 3.6148, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678109335721581e-05, + "loss": 3.626, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677270740970529e-05, + "loss": 3.6158, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764337840998506e-05, + "loss": 3.6257, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755951893487986e-05, + "loss": 3.6206, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747565945977466e-05, + "loss": 3.6214, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6739179998466946e-05, + "loss": 3.6169, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673081042976016e-05, + "loss": 3.6115, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722424482249635e-05, + "loss": 3.6213, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6714038534739115e-05, + "loss": 3.6219, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6705652587228595e-05, + "loss": 3.6225, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669728301852181e-05, + "loss": 3.6104, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6688897071011284e-05, + "loss": 3.603, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680511123500764e-05, + "loss": 3.6154, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6672125175990244e-05, + "loss": 3.628, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666375560728346e-05, + "loss": 3.6167, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665536965977294e-05, + "loss": 3.6173, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664698371226242e-05, + "loss": 3.6092, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.66385977647519e-05, + "loss": 3.6104, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663022819604511e-05, + "loss": 3.6184, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662184224853459e-05, + "loss": 3.6057, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661345630102407e-05, + "loss": 3.6104, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660507035351355e-05, + "loss": 3.6195, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659670078480676e-05, + "loss": 3.6178, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658831483729624e-05, + "loss": 3.612, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657992888978572e-05, + "loss": 3.6106, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.65715429422752e-05, + "loss": 3.6103, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656317337356841e-05, + "loss": 3.6249, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655478742605789e-05, + "loss": 3.6114, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654640147854737e-05, + "loss": 3.624, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653801553103685e-05, + "loss": 3.6229, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652964596233006e-05, + "loss": 3.6114, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652126001481954e-05, + "loss": 3.6158, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651287406730902e-05, + "loss": 3.6119, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.65044881197985e-05, + "loss": 3.6144, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649611855109171e-05, + "loss": 3.6178, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648773260358119e-05, + "loss": 3.6035, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647934665607067e-05, + "loss": 3.6056, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647096070856015e-05, + "loss": 3.6139, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646259113985337e-05, + "loss": 3.6148, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645420519234285e-05, + "loss": 3.6107, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644581924483233e-05, + "loss": 3.6043, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643743329732181e-05, + "loss": 3.6117, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6429063728615016e-05, + "loss": 3.605, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420677781104496e-05, + "loss": 3.6217, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412291833593976e-05, + "loss": 3.6129, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403905886083456e-05, + "loss": 3.6163, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395536317376665e-05, + "loss": 3.6015, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6387150369866145e-05, + "loss": 3.6212, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6378764422355625e-05, + "loss": 3.6132, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6370378474845105e-05, + "loss": 3.6216, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636200890613832e-05, + "loss": 3.6179, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.63536229586278e-05, + "loss": 3.6166, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634523701111728e-05, + "loss": 3.6114, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633685106360676e-05, + "loss": 3.6287, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632848149489997e-05, + "loss": 3.6023, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.632009554738945e-05, + "loss": 3.6185, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631170959987893e-05, + "loss": 3.6092, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630332365236841e-05, + "loss": 3.6108, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629495408366162e-05, + "loss": 3.6053, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.62865681361511e-05, + "loss": 3.6056, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627818218864058e-05, + "loss": 3.6081, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626979624113006e-05, + "loss": 3.6168, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261426672423274e-05, + "loss": 3.6117, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.844646453857422, + "eval_runtime": 306.1539, + "eval_samples_per_second": 1246.402, + "eval_steps_per_second": 38.951, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6253040724912754e-05, + "loss": 3.606, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244654777402234e-05, + "loss": 3.5999, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236268829891714e-05, + "loss": 3.6025, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622789926118492e-05, + "loss": 3.6179, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.62195133136744e-05, + "loss": 3.6163, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621112736616388e-05, + "loss": 3.602, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620275779745709e-05, + "loss": 3.6109, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619437184994657e-05, + "loss": 3.6041, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618598590243605e-05, + "loss": 3.608, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617759995492553e-05, + "loss": 3.6136, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616923038621874e-05, + "loss": 3.6094, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616084443870823e-05, + "loss": 3.6045, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615245849119771e-05, + "loss": 3.6153, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614407254368719e-05, + "loss": 3.5949, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613568659617667e-05, + "loss": 3.6046, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612731702746988e-05, + "loss": 3.5913, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611893107995936e-05, + "loss": 3.6102, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611054513244884e-05, + "loss": 3.6091, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610215918493832e-05, + "loss": 3.5915, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093789616231526e-05, + "loss": 3.6133, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085403668721006e-05, + "loss": 3.6208, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6077017721210486e-05, + "loss": 3.6066, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068648152503695e-05, + "loss": 3.6114, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606026220499318e-05, + "loss": 3.6108, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605187625748266e-05, + "loss": 3.607, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604349030997214e-05, + "loss": 3.6017, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603510436246162e-05, + "loss": 3.6024, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602673479375483e-05, + "loss": 3.6081, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601834884624431e-05, + "loss": 3.5979, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600996289873379e-05, + "loss": 3.6059, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001593330027e-05, + "loss": 3.6113, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599320738251648e-05, + "loss": 3.6147, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598482143500596e-05, + "loss": 3.6084, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597643548749544e-05, + "loss": 3.6144, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596806591878865e-05, + "loss": 3.5971, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595967997127813e-05, + "loss": 3.6073, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5951294023767615e-05, + "loss": 3.6126, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942908076257095e-05, + "loss": 3.5908, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934538507550304e-05, + "loss": 3.5991, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5926152560039784e-05, + "loss": 3.6009, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917766612529264e-05, + "loss": 3.5985, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909380665018744e-05, + "loss": 3.6022, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590101109631195e-05, + "loss": 3.6088, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589262514880143e-05, + "loss": 3.6071, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588423920129091e-05, + "loss": 3.6029, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587585325378039e-05, + "loss": 3.6058, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.58674836850736e-05, + "loss": 3.5982, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585909773756308e-05, + "loss": 3.6092, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585071179005257e-05, + "loss": 3.5848, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584232584254205e-05, + "loss": 3.6047, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583395627383526e-05, + "loss": 3.5973, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582557032632474e-05, + "loss": 3.6104, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581718437881422e-05, + "loss": 3.598, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.58087984313037e-05, + "loss": 3.5934, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580042886259691e-05, + "loss": 3.5907, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579204291508639e-05, + "loss": 3.6019, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578365696757587e-05, + "loss": 3.6084, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577527102006535e-05, + "loss": 3.5874, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766901451358556e-05, + "loss": 3.6108, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758515503848036e-05, + "loss": 3.6009, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.575012955633752e-05, + "loss": 3.5772, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741743608827e-05, + "loss": 3.6073, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573337404012021e-05, + "loss": 3.59, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572498809260969e-05, + "loss": 3.5848, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571660214509917e-05, + "loss": 3.5967, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570821619758865e-05, + "loss": 3.5971, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569984662888186e-05, + "loss": 3.5886, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569146068137134e-05, + "loss": 3.6079, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568307473386082e-05, + "loss": 3.5775, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.56746887863503e-05, + "loss": 3.5888, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566631921764351e-05, + "loss": 3.6034, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565793327013299e-05, + "loss": 3.5991, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649547322622476e-05, + "loss": 3.6031, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5641161375111956e-05, + "loss": 3.6007, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632791806405165e-05, + "loss": 3.6056, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624405858894645e-05, + "loss": 3.5934, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5616019911384125e-05, + "loss": 3.608, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607633963873605e-05, + "loss": 3.5902, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599264395166814e-05, + "loss": 3.5906, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590878447656294e-05, + "loss": 3.596, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582492500145774e-05, + "loss": 3.5984, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5574106552635254e-05, + "loss": 3.6001, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556573698392846e-05, + "loss": 3.6067, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555735103641794e-05, + "loss": 3.5921, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554896508890743e-05, + "loss": 3.5825, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.55405791413969e-05, + "loss": 3.5974, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553220957269012e-05, + "loss": 3.6067, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.55238236251796e-05, + "loss": 3.5936, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551543767766908e-05, + "loss": 3.603, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550705173015855e-05, + "loss": 3.6056, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549868216145177e-05, + "loss": 3.6007, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549029621394125e-05, + "loss": 3.597, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548191026643072e-05, + "loss": 3.591, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.54735243189202e-05, + "loss": 3.6017, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546515475021342e-05, + "loss": 3.6033, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.54567688027029e-05, + "loss": 3.5976, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544838285519238e-05, + "loss": 3.5935, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543999690768186e-05, + "loss": 3.5835, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543162733897507e-05, + "loss": 3.5962, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542324139146455e-05, + "loss": 3.6073, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414855443954026e-05, + "loss": 3.5937, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406469496443506e-05, + "loss": 3.5971, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539809992773672e-05, + "loss": 3.5911, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389713980226195e-05, + "loss": 3.5934, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5381328032715675e-05, + "loss": 3.5965, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372942085205155e-05, + "loss": 3.5908, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536457251649837e-05, + "loss": 3.5888, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535618656898785e-05, + "loss": 3.5988, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534780062147733e-05, + "loss": 3.5958, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533941467396681e-05, + "loss": 3.5915, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5331045105260026e-05, + "loss": 3.5951, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.53226591577495e-05, + "loss": 3.5892, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531427321023898e-05, + "loss": 3.6045, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530588726272846e-05, + "loss": 3.5936, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529751769402167e-05, + "loss": 3.6014, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528913174651115e-05, + "loss": 3.6023, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528074579900063e-05, + "loss": 3.5928, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5272376230293844e-05, + "loss": 3.5964, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5263990282783324e-05, + "loss": 3.5932, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5255604335272804e-05, + "loss": 3.5927, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5247218387762284e-05, + "loss": 3.5968, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.52388488190555e-05, + "loss": 3.5854, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523046287154497e-05, + "loss": 3.588, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522207692403445e-05, + "loss": 3.5959, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521369097652393e-05, + "loss": 3.5927, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520532140781714e-05, + "loss": 3.5906, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519693546030662e-05, + "loss": 3.585, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.51885495127961e-05, + "loss": 3.5882, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.518016356528558e-05, + "loss": 3.5882, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.51717939965788e-05, + "loss": 3.6033, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516340804906828e-05, + "loss": 3.5908, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515502210155776e-05, + "loss": 3.6014, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514663615404724e-05, + "loss": 3.5821, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513826658534045e-05, + "loss": 3.5983, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512988063782993e-05, + "loss": 3.5953, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512149469031941e-05, + "loss": 3.6001, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511310874280889e-05, + "loss": 3.6021, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104739174102096e-05, + "loss": 3.5969, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096353226591576e-05, + "loss": 3.5966, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5087967279081056e-05, + "loss": 3.6018, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079581331570536e-05, + "loss": 3.5875, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507121176286375e-05, + "loss": 3.5975, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506282581535323e-05, + "loss": 3.5913, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505443986784271e-05, + "loss": 3.5896, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504605392033219e-05, + "loss": 3.5849, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.50376843516254e-05, + "loss": 3.5897, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502929840411488e-05, + "loss": 3.5861, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502091245660436e-05, + "loss": 3.5923, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501252650909384e-05, + "loss": 3.5963, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.844787120819092, + "eval_runtime": 310.198, + "eval_samples_per_second": 1230.153, + "eval_steps_per_second": 38.443, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500415694038705e-05, + "loss": 3.6006, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499577099287653e-05, + "loss": 3.5769, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498738504536601e-05, + "loss": 3.5856, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497899909785549e-05, + "loss": 3.5974, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970629529148705e-05, + "loss": 3.5948, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4962243581638185e-05, + "loss": 3.5856, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953857634127665e-05, + "loss": 3.5941, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945471686617145e-05, + "loss": 3.585, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4937102117910354e-05, + "loss": 3.5861, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928716170399834e-05, + "loss": 3.5916, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920330222889314e-05, + "loss": 3.5969, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911944275378794e-05, + "loss": 3.5851, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903574706672e-05, + "loss": 3.597, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489518875916148e-05, + "loss": 3.5705, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488680281165096e-05, + "loss": 3.5866, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487841686414044e-05, + "loss": 3.5743, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.487004729543365e-05, + "loss": 3.5895, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486166134792314e-05, + "loss": 3.5882, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485327540041262e-05, + "loss": 3.5737, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.48448894529021e-05, + "loss": 3.5931, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483651988419531e-05, + "loss": 3.6013, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482813393668479e-05, + "loss": 3.5865, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481974798917427e-05, + "loss": 3.5931, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481136204166375e-05, + "loss": 3.5916, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480299247295696e-05, + "loss": 3.5924, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479460652544644e-05, + "loss": 3.5831, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478622057793592e-05, + "loss": 3.5819, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.47778346304254e-05, + "loss": 3.5935, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769465061718606e-05, + "loss": 3.5799, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476107911420809e-05, + "loss": 3.5851, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475269316669757e-05, + "loss": 3.5958, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474430721918705e-05, + "loss": 3.5935, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473593765048026e-05, + "loss": 3.5886, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472755170296974e-05, + "loss": 3.5975, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471916575545922e-05, + "loss": 3.5813, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.47107798079487e-05, + "loss": 3.5887, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470241023924191e-05, + "loss": 3.5888, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469402429173139e-05, + "loss": 3.5753, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468563834422087e-05, + "loss": 3.5819, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467725239671035e-05, + "loss": 3.5834, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466888282800356e-05, + "loss": 3.5776, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660496880493046e-05, + "loss": 3.583, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4652110932982526e-05, + "loss": 3.5918, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4643724985472006e-05, + "loss": 3.5869, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4635355416765215e-05, + "loss": 3.5844, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626969469254695e-05, + "loss": 3.5915, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618583521744175e-05, + "loss": 3.5774, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4610197574233655e-05, + "loss": 3.5893, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601828005526864e-05, + "loss": 3.5696, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593442058016344e-05, + "loss": 3.5836, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4585056110505824e-05, + "loss": 3.5795, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576670162995304e-05, + "loss": 3.5932, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456830059428851e-05, + "loss": 3.5787, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559914646778e-05, + "loss": 3.5747, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455152869926748e-05, + "loss": 3.5758, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454315913056069e-05, + "loss": 3.5803, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453477318305017e-05, + "loss": 3.592, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452638723553965e-05, + "loss": 3.5652, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451800128802913e-05, + "loss": 3.5947, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450963171932234e-05, + "loss": 3.5803, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450124577181182e-05, + "loss": 3.5613, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.44928598243013e-05, + "loss": 3.5874, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448447387679078e-05, + "loss": 3.5695, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447610430808399e-05, + "loss": 3.5672, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446771836057347e-05, + "loss": 3.5759, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459332413062953e-05, + "loss": 3.582, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450946465552433e-05, + "loss": 3.5746, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444257689684564e-05, + "loss": 3.5802, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443419094933512e-05, + "loss": 3.565, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.44258050018246e-05, + "loss": 3.5688, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441741905431408e-05, + "loss": 3.5832, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440904948560729e-05, + "loss": 3.5843, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440066353809677e-05, + "loss": 3.5851, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439227759058625e-05, + "loss": 3.5799, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438389164307573e-05, + "loss": 3.5887, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437552207436894e-05, + "loss": 3.575, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436713612685842e-05, + "loss": 3.5847, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435875017934791e-05, + "loss": 3.5744, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435036423183739e-05, + "loss": 3.5727, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4341994663130596e-05, + "loss": 3.5808, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4333608715620076e-05, + "loss": 3.5739, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4325222768109556e-05, + "loss": 3.5846, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316836820599036e-05, + "loss": 3.5893, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308467251892245e-05, + "loss": 3.5775, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4300081304381725e-05, + "loss": 3.5582, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291695356871205e-05, + "loss": 3.5788, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4283309409360685e-05, + "loss": 3.5841, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274939840653894e-05, + "loss": 3.5792, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266553893143374e-05, + "loss": 3.5852, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425816794563286e-05, + "loss": 3.5906, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424978199812234e-05, + "loss": 3.5779, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424141242941555e-05, + "loss": 3.5811, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423302648190503e-05, + "loss": 3.573, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422464053439451e-05, + "loss": 3.5865, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421625458688399e-05, + "loss": 3.5821, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.42078850181772e-05, + "loss": 3.5813, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419949907066668e-05, + "loss": 3.575, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419111312315616e-05, + "loss": 3.5649, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418272717564564e-05, + "loss": 3.5744, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417435760693885e-05, + "loss": 3.5908, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416597165942833e-05, + "loss": 3.5804, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157602090721544e-05, + "loss": 3.5735, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4149216143211024e-05, + "loss": 3.5756, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140830195700504e-05, + "loss": 3.5736, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132444248189983e-05, + "loss": 3.578, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4124058300679463e-05, + "loss": 3.5756, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411567235316894e-05, + "loss": 3.5727, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4107286405658417e-05, + "loss": 3.5783, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098900458147897e-05, + "loss": 3.5792, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409053088944111e-05, + "loss": 3.5751, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4082144941930586e-05, + "loss": 3.5731, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073758994420066e-05, + "loss": 3.572, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406537304690955e-05, + "loss": 3.5844, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405700347820276e-05, + "loss": 3.5778, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404861753069224e-05, + "loss": 3.5789, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404023158318172e-05, + "loss": 3.5807, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.40318456356712e-05, + "loss": 3.5812, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402347606696441e-05, + "loss": 3.5776, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401509011945389e-05, + "loss": 3.5761, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400670417194337e-05, + "loss": 3.5764, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399831822443285e-05, + "loss": 3.5774, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398994865572606e-05, + "loss": 3.5639, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398156270821554e-05, + "loss": 3.5737, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397317676070502e-05, + "loss": 3.5723, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.39647908131945e-05, + "loss": 3.5783, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3956421244487715e-05, + "loss": 3.5755, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3948035296977195e-05, + "loss": 3.567, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939649349466675e-05, + "loss": 3.5661, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931263401956155e-05, + "loss": 3.5713, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922893833249364e-05, + "loss": 3.585, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914507885738844e-05, + "loss": 3.5743, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3906121938228324e-05, + "loss": 3.581, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897735990717804e-05, + "loss": 3.5643, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388936642201101e-05, + "loss": 3.5812, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388098047450049e-05, + "loss": 3.5787, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387259452698997e-05, + "loss": 3.58, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386420857947945e-05, + "loss": 3.5816, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385583901077267e-05, + "loss": 3.5778, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384745306326215e-05, + "loss": 3.5848, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383906711575163e-05, + "loss": 3.5849, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383068116824111e-05, + "loss": 3.5673, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382231159953432e-05, + "loss": 3.5818, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.38139256520238e-05, + "loss": 3.574, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380553970451328e-05, + "loss": 3.5745, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379715375700276e-05, + "loss": 3.5669, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378878418829597e-05, + "loss": 3.574, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780398240785447e-05, + "loss": 3.568, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3772012293274927e-05, + "loss": 3.5733, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376364272456814e-05, + "loss": 3.5749, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.843822956085205, + "eval_runtime": 349.9757, + "eval_samples_per_second": 1090.336, + "eval_steps_per_second": 34.074, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375525677705762e-05, + "loss": 3.5778, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.37468708295471e-05, + "loss": 3.5595, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373848488203658e-05, + "loss": 3.5688, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.373011531332979e-05, + "loss": 3.5804, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372172936581927e-05, + "loss": 3.5756, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371334341830875e-05, + "loss": 3.5712, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370495747079823e-05, + "loss": 3.5753, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369658790209144e-05, + "loss": 3.5672, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368820195458092e-05, + "loss": 3.5688, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.36798160070704e-05, + "loss": 3.5781, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367143005955988e-05, + "loss": 3.5739, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3663060490853096e-05, + "loss": 3.5698, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654674543342576e-05, + "loss": 3.582, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3646288595832056e-05, + "loss": 3.5502, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637902648321536e-05, + "loss": 3.5673, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629533079614745e-05, + "loss": 3.5571, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3621147132104225e-05, + "loss": 3.5745, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3612761184593705e-05, + "loss": 3.5686, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3604375237083185e-05, + "loss": 3.5615, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3596005668376394e-05, + "loss": 3.5685, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587619720865874e-05, + "loss": 3.5883, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3579233773355354e-05, + "loss": 3.5697, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3570847825844834e-05, + "loss": 3.5743, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356247825713805e-05, + "loss": 3.5766, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355409230962753e-05, + "loss": 3.5764, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354570636211701e-05, + "loss": 3.5637, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353732041460649e-05, + "loss": 3.5661, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.35289508458997e-05, + "loss": 3.5738, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352056489838918e-05, + "loss": 3.5602, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351217895087866e-05, + "loss": 3.5673, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350379300336814e-05, + "loss": 3.5776, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349542343466135e-05, + "loss": 3.5776, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348703748715083e-05, + "loss": 3.574, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347865153964031e-05, + "loss": 3.5797, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347026559212979e-05, + "loss": 3.564, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461896023423003e-05, + "loss": 3.5702, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345351007591248e-05, + "loss": 3.5733, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344512412840196e-05, + "loss": 3.5547, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343673818089144e-05, + "loss": 3.568, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342836861218465e-05, + "loss": 3.5635, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341998266467413e-05, + "loss": 3.5582, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341159671716361e-05, + "loss": 3.5659, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340321076965309e-05, + "loss": 3.5807, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.33948412009463e-05, + "loss": 3.5636, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338645525343578e-05, + "loss": 3.5688, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337806930592526e-05, + "loss": 3.5705, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336968335841474e-05, + "loss": 3.5612, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336131378970796e-05, + "loss": 3.572, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335292784219744e-05, + "loss": 3.5539, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334454189468692e-05, + "loss": 3.5654, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.33361559471764e-05, + "loss": 3.5639, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3327786378469606e-05, + "loss": 3.5734, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3319400430959086e-05, + "loss": 3.5665, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3311014483448566e-05, + "loss": 3.5561, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302628535938046e-05, + "loss": 3.5564, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3294258967231255e-05, + "loss": 3.5628, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285873019720735e-05, + "loss": 3.5739, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277487072210215e-05, + "loss": 3.5511, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3269101124699695e-05, + "loss": 3.5729, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326073155599291e-05, + "loss": 3.5638, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325234560848239e-05, + "loss": 3.5493, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324395966097187e-05, + "loss": 3.5703, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323557371346135e-05, + "loss": 3.5548, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322720414475456e-05, + "loss": 3.5494, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321881819724404e-05, + "loss": 3.555, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321043224973352e-05, + "loss": 3.5669, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3202046302223e-05, + "loss": 3.5613, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319367673351621e-05, + "loss": 3.5571, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318529078600569e-05, + "loss": 3.5534, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317690483849517e-05, + "loss": 3.5522, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316851889098465e-05, + "loss": 3.5629, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3160149322277864e-05, + "loss": 3.5659, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3151763374767344e-05, + "loss": 3.5657, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3143377427256824e-05, + "loss": 3.5701, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3134991479746304e-05, + "loss": 3.5669, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126621911039513e-05, + "loss": 3.5594, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311823596352899e-05, + "loss": 3.5667, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310985001601847e-05, + "loss": 3.5608, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310148044731168e-05, + "loss": 3.5606, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309309449980116e-05, + "loss": 3.5561, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308470855229064e-05, + "loss": 3.5607, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307632260478012e-05, + "loss": 3.5697, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306795303607333e-05, + "loss": 3.5703, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305956708856282e-05, + "loss": 3.5642, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.30511811410523e-05, + "loss": 3.5419, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304279519354178e-05, + "loss": 3.5632, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303442562483499e-05, + "loss": 3.5668, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302603967732447e-05, + "loss": 3.5652, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301765372981395e-05, + "loss": 3.5628, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300926778230343e-05, + "loss": 3.5729, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000898213596636e-05, + "loss": 3.5622, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2992512266086116e-05, + "loss": 3.5638, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2984126318575596e-05, + "loss": 3.558, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975740371065076e-05, + "loss": 3.567, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2967370802358285e-05, + "loss": 3.5653, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295898485484777e-05, + "loss": 3.5682, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295059890733725e-05, + "loss": 3.5538, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294221295982673e-05, + "loss": 3.5523, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293384339111994e-05, + "loss": 3.5584, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292545744360942e-05, + "loss": 3.5716, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.29170714960989e-05, + "loss": 3.5653, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290868554858838e-05, + "loss": 3.559, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290031597988159e-05, + "loss": 3.5582, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289193003237107e-05, + "loss": 3.5561, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288354408486055e-05, + "loss": 3.5624, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287515813735003e-05, + "loss": 3.556, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286678856864324e-05, + "loss": 3.5572, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.2858402621132725e-05, + "loss": 3.5631, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2850016673622205e-05, + "loss": 3.5626, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284163072611168e-05, + "loss": 3.5544, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2833261157404894e-05, + "loss": 3.5579, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824875209894374e-05, + "loss": 3.5549, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2816489262383854e-05, + "loss": 3.5694, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280810331487333e-05, + "loss": 3.5629, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799733746166543e-05, + "loss": 3.5631, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279134779865602e-05, + "loss": 3.5618, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.27829618511455e-05, + "loss": 3.5661, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774575903634976e-05, + "loss": 3.5613, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276620633492819e-05, + "loss": 3.5582, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275782038741768e-05, + "loss": 3.5633, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274943443990715e-05, + "loss": 3.5578, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274104849239663e-05, + "loss": 3.5494, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273267892368985e-05, + "loss": 3.5567, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272429297617933e-05, + "loss": 3.5555, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.27159070286688e-05, + "loss": 3.5608, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270752108115828e-05, + "loss": 3.5542, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.26991515124515e-05, + "loss": 3.5537, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269076556494098e-05, + "loss": 3.5526, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268237961743045e-05, + "loss": 3.555, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267399366991993e-05, + "loss": 3.5673, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2665624101213146e-05, + "loss": 3.5597, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2657238153702626e-05, + "loss": 3.5657, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2648852206192106e-05, + "loss": 3.5468, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2640466258681586e-05, + "loss": 3.5646, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.26320966899748e-05, + "loss": 3.5621, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2623710742464275e-05, + "loss": 3.5647, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2615324794953755e-05, + "loss": 3.5606, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2606938847443235e-05, + "loss": 3.5614, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259856927873645e-05, + "loss": 3.5696, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2590183331225924e-05, + "loss": 3.5664, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581797383715404e-05, + "loss": 3.5523, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257342781500862e-05, + "loss": 3.56, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.25650418674981e-05, + "loss": 3.5598, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255665591998758e-05, + "loss": 3.5577, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254826997247706e-05, + "loss": 3.5499, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539900403770275e-05, + "loss": 3.5611, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253151445625975e-05, + "loss": 3.5475, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252312850874923e-05, + "loss": 3.5645, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251474256123871e-05, + "loss": 3.5527, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8452048301696777, + "eval_runtime": 356.4759, + "eval_samples_per_second": 1070.454, + "eval_steps_per_second": 33.452, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2506372992531924e-05, + "loss": 3.5672, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.24979870450214e-05, + "loss": 3.5465, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248960109751088e-05, + "loss": 3.5512, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248121515000036e-05, + "loss": 3.5663, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472845581293573e-05, + "loss": 3.559, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246445963378305e-05, + "loss": 3.5565, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245607368627253e-05, + "loss": 3.5534, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244768773876201e-05, + "loss": 3.5497, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243931817005522e-05, + "loss": 3.5516, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.24309322225447e-05, + "loss": 3.5639, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242254627503418e-05, + "loss": 3.5595, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241416032752366e-05, + "loss": 3.5565, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240579075881687e-05, + "loss": 3.5624, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239740481130635e-05, + "loss": 3.5383, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238901886379583e-05, + "loss": 3.5489, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238063291628531e-05, + "loss": 3.5417, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237226334757853e-05, + "loss": 3.5557, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236387740006801e-05, + "loss": 3.5474, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235549145255749e-05, + "loss": 3.5484, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234710550504697e-05, + "loss": 3.5537, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338735936340176e-05, + "loss": 3.5695, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330349988829656e-05, + "loss": 3.5554, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321964041319136e-05, + "loss": 3.5554, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313578093808616e-05, + "loss": 3.5574, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2305208525101825e-05, + "loss": 3.5667, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296822577591305e-05, + "loss": 3.5416, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288436630080785e-05, + "loss": 3.5512, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2280050682570265e-05, + "loss": 3.5601, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227168111386348e-05, + "loss": 3.5424, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226329516635296e-05, + "loss": 3.5523, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225490921884244e-05, + "loss": 3.5592, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224652327133192e-05, + "loss": 3.5612, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223815370262513e-05, + "loss": 3.5575, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222976775511461e-05, + "loss": 3.5627, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222138180760409e-05, + "loss": 3.5467, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221299586009357e-05, + "loss": 3.5579, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220462629138678e-05, + "loss": 3.5523, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219624034387626e-05, + "loss": 3.5419, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218785439636574e-05, + "loss": 3.5546, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217946844885522e-05, + "loss": 3.5436, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2171098880148434e-05, + "loss": 3.5443, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162712932637914e-05, + "loss": 3.5502, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2154326985127394e-05, + "loss": 3.5636, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145941037616874e-05, + "loss": 3.5463, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213757146891008e-05, + "loss": 3.5561, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212918552139956e-05, + "loss": 3.5535, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212079957388904e-05, + "loss": 3.5499, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211241362637852e-05, + "loss": 3.5533, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210404405767173e-05, + "loss": 3.5379, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209565811016121e-05, + "loss": 3.5517, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208727216265069e-05, + "loss": 3.5488, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207888621514017e-05, + "loss": 3.5551, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207051664643339e-05, + "loss": 3.5511, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206213069892287e-05, + "loss": 3.5377, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205374475141235e-05, + "loss": 3.5386, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204535880390183e-05, + "loss": 3.5459, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203698923519504e-05, + "loss": 3.5646, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202860328768452e-05, + "loss": 3.5351, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2020217340174e-05, + "loss": 3.5559, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201183139266348e-05, + "loss": 3.5489, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2003461823956686e-05, + "loss": 3.5315, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1995075876446166e-05, + "loss": 3.5535, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986689928935646e-05, + "loss": 3.5443, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1978303981425126e-05, + "loss": 3.5357, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196993441271834e-05, + "loss": 3.5362, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196154846520782e-05, + "loss": 3.5564, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.19531625176973e-05, + "loss": 3.5437, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194477657018678e-05, + "loss": 3.5391, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193640700147999e-05, + "loss": 3.5351, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192802105396947e-05, + "loss": 3.539, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191963510645895e-05, + "loss": 3.5467, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191124915894843e-05, + "loss": 3.5503, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190287959024164e-05, + "loss": 3.5478, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189449364273112e-05, + "loss": 3.5525, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.18861076952206e-05, + "loss": 3.5492, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187772174771008e-05, + "loss": 3.55, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1869352179003295e-05, + "loss": 3.5475, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860966231492775e-05, + "loss": 3.5434, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852580283982255e-05, + "loss": 3.5431, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1844210715275464e-05, + "loss": 3.5452, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835824767764944e-05, + "loss": 3.5455, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1827438820254424e-05, + "loss": 3.5491, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1819052872743904e-05, + "loss": 3.5584, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181068330403711e-05, + "loss": 3.546, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180229735652659e-05, + "loss": 3.5274, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179391140901607e-05, + "loss": 3.5447, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178552546150555e-05, + "loss": 3.5501, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177715589279876e-05, + "loss": 3.5529, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176876994528825e-05, + "loss": 3.5434, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176038399777773e-05, + "loss": 3.5577, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175199805026721e-05, + "loss": 3.5502, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174362848156042e-05, + "loss": 3.5449, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.17352425340499e-05, + "loss": 3.5431, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172685658653938e-05, + "loss": 3.5526, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171847063902886e-05, + "loss": 3.5471, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.171010107032207e-05, + "loss": 3.5525, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170171512281155e-05, + "loss": 3.5399, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169332917530103e-05, + "loss": 3.5389, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168494322779051e-05, + "loss": 3.5415, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676573659083716e-05, + "loss": 3.556, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.16681877115732e-05, + "loss": 3.5477, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165980176406268e-05, + "loss": 3.5457, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165141581655216e-05, + "loss": 3.5396, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164304624784537e-05, + "loss": 3.5389, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163466030033485e-05, + "loss": 3.5513, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162627435282433e-05, + "loss": 3.5379, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161788840531381e-05, + "loss": 3.5412, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160951883660702e-05, + "loss": 3.5471, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.16011328890965e-05, + "loss": 3.5484, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159274694158598e-05, + "loss": 3.5422, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158436099407546e-05, + "loss": 3.5449, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157599142536867e-05, + "loss": 3.5359, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567605477858156e-05, + "loss": 3.5527, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1559219530347636e-05, + "loss": 3.5481, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1550833582837116e-05, + "loss": 3.5444, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1542464014130325e-05, + "loss": 3.5525, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1534078066619805e-05, + "loss": 3.5516, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525692119109285e-05, + "loss": 3.543, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1517306171598765e-05, + "loss": 3.5424, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508936602891974e-05, + "loss": 3.5483, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500550655381454e-05, + "loss": 3.5409, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1492164707870934e-05, + "loss": 3.5351, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483778760360414e-05, + "loss": 3.5431, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147540919165362e-05, + "loss": 3.5403, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146702324414311e-05, + "loss": 3.5492, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145863729663259e-05, + "loss": 3.5338, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.145025134912207e-05, + "loss": 3.546, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144188178041528e-05, + "loss": 3.5376, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143349583290476e-05, + "loss": 3.5397, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142510988539424e-05, + "loss": 3.5456, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141672393788372e-05, + "loss": 3.5496, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140835436917693e-05, + "loss": 3.5479, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139996842166641e-05, + "loss": 3.5313, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139158247415589e-05, + "loss": 3.5498, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138319652664536e-05, + "loss": 3.5485, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137482695793858e-05, + "loss": 3.549, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1366441010428064e-05, + "loss": 3.5479, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1358055062917544e-05, + "loss": 3.5463, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134966911540702e-05, + "loss": 3.5574, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134129954670023e-05, + "loss": 3.5508, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133291359918971e-05, + "loss": 3.5385, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132452765167919e-05, + "loss": 3.5453, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1316141704168666e-05, + "loss": 3.5429, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130777213546188e-05, + "loss": 3.5398, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129938618795136e-05, + "loss": 3.5382, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1291000240440835e-05, + "loss": 3.5443, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128263067173405e-05, + "loss": 3.5333, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127424472422353e-05, + "loss": 3.5488, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126585877671301e-05, + "loss": 3.5389, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8447935581207275, + "eval_runtime": 305.8162, + "eval_samples_per_second": 1247.779, + "eval_steps_per_second": 38.994, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125747282920249e-05, + "loss": 3.5175, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124908688169197e-05, + "loss": 3.5367, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.124070093418145e-05, + "loss": 3.5324, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123231498667093e-05, + "loss": 3.5488, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122394541796414e-05, + "loss": 3.5451, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121555947045362e-05, + "loss": 3.5418, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.12071735229431e-05, + "loss": 3.5365, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119878757543258e-05, + "loss": 3.5334, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.119041800672579e-05, + "loss": 3.5422, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118203205921527e-05, + "loss": 3.544, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117364611170475e-05, + "loss": 3.5434, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.1165260164194235e-05, + "loss": 3.5391, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115690697429118e-05, + "loss": 3.5485, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114852102678066e-05, + "loss": 3.5245, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.114013507927014e-05, + "loss": 3.5348, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113174913175961e-05, + "loss": 3.5275, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112336318424909e-05, + "loss": 3.5401, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111497723673857e-05, + "loss": 3.5331, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110659128922805e-05, + "loss": 3.5351, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109820534171753e-05, + "loss": 3.5361, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108983577301074e-05, + "loss": 3.5574, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108144982550022e-05, + "loss": 3.5397, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.10730638779897e-05, + "loss": 3.5361, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106467793047919e-05, + "loss": 3.5459, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.10563083617724e-05, + "loss": 3.5499, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104792241426188e-05, + "loss": 3.5299, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103953646675136e-05, + "loss": 3.532, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.103115051924084e-05, + "loss": 3.5469, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102278095053405e-05, + "loss": 3.5268, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101439500302353e-05, + "loss": 3.5366, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100600905551301e-05, + "loss": 3.5399, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099762310800249e-05, + "loss": 3.5485, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.0989253539295696e-05, + "loss": 3.5428, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0980867591785176e-05, + "loss": 3.5421, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0972481644274656e-05, + "loss": 3.5373, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096409569676414e-05, + "loss": 3.5455, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095572612805735e-05, + "loss": 3.5416, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094734018054683e-05, + "loss": 3.5247, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093895423303631e-05, + "loss": 3.5391, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.093056828552579e-05, + "loss": 3.5281, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0922198716819e-05, + "loss": 3.5343, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091382914811221e-05, + "loss": 3.5316, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090544320060169e-05, + "loss": 3.5485, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089705725309117e-05, + "loss": 3.5343, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088867130558065e-05, + "loss": 3.5371, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.088028535807013e-05, + "loss": 3.5433, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087189941055961e-05, + "loss": 3.5283, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0863513463049096e-05, + "loss": 3.5435, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.0855127515538576e-05, + "loss": 3.524, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.0846757946831785e-05, + "loss": 3.5294, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.0838371999321265e-05, + "loss": 3.5384, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.0829986051810745e-05, + "loss": 3.5394, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.0821600104300225e-05, + "loss": 3.5393, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0813230535593434e-05, + "loss": 3.5232, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0804844588082914e-05, + "loss": 3.5306, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0796458640572394e-05, + "loss": 3.5272, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0788072693061874e-05, + "loss": 3.55, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077970312435508e-05, + "loss": 3.5181, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077131717684456e-05, + "loss": 3.5409, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076293122933405e-05, + "loss": 3.5343, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075454528182353e-05, + "loss": 3.5187, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074617571311674e-05, + "loss": 3.5387, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073778976560622e-05, + "loss": 3.5298, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.07294038180957e-05, + "loss": 3.5164, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072101787058518e-05, + "loss": 3.5228, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071264830187839e-05, + "loss": 3.5433, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070426235436787e-05, + "loss": 3.5282, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069587640685735e-05, + "loss": 3.5272, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068749045934683e-05, + "loss": 3.5213, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067912089064004e-05, + "loss": 3.5216, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067073494312952e-05, + "loss": 3.5321, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.0662348995619003e-05, + "loss": 3.5343, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.0653963048108483e-05, + "loss": 3.531, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064559347940169e-05, + "loss": 3.5399, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063720753189117e-05, + "loss": 3.5356, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062882158438065e-05, + "loss": 3.5333, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.062043563687013e-05, + "loss": 3.5314, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061206606816334e-05, + "loss": 3.5296, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060368012065282e-05, + "loss": 3.5293, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.05952941731423e-05, + "loss": 3.5331, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058692460443551e-05, + "loss": 3.5263, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057853865692499e-05, + "loss": 3.5386, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.057015270941447e-05, + "loss": 3.537, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056176676190396e-05, + "loss": 3.5354, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0553397193197166e-05, + "loss": 3.5154, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.0545011245686646e-05, + "loss": 3.5259, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.0536625298176126e-05, + "loss": 3.5412, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0528239350665606e-05, + "loss": 3.5348, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.0519869781958815e-05, + "loss": 3.5303, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511483834448295e-05, + "loss": 3.5442, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0503097886937775e-05, + "loss": 3.5337, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494711939427255e-05, + "loss": 3.5305, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0486342370720468e-05, + "loss": 3.5297, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477956423209948e-05, + "loss": 3.5371, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469570475699427e-05, + "loss": 3.5305, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0461184528188907e-05, + "loss": 3.5431, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452814959482117e-05, + "loss": 3.5179, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0444429011971596e-05, + "loss": 3.5308, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.043604306446108e-05, + "loss": 3.5262, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.042765711695056e-05, + "loss": 3.5361, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.041928754824377e-05, + "loss": 3.5395, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.041090160073325e-05, + "loss": 3.5266, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.040251565322273e-05, + "loss": 3.5298, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.039412970571221e-05, + "loss": 3.5253, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.038576013700542e-05, + "loss": 3.5369, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.03773741894949e-05, + "loss": 3.5193, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036898824198438e-05, + "loss": 3.5309, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.036060229447386e-05, + "loss": 3.5327, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.035223272576707e-05, + "loss": 3.5284, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.034384677825655e-05, + "loss": 3.5302, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0335460830746034e-05, + "loss": 3.5332, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0327074883235513e-05, + "loss": 3.5192, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318705314528723e-05, + "loss": 3.5395, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0310319367018203e-05, + "loss": 3.5306, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0301933419507682e-05, + "loss": 3.5292, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0293547471997162e-05, + "loss": 3.5384, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0285177903290375e-05, + "loss": 3.5373, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276791955779855e-05, + "loss": 3.5283, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0268406008269335e-05, + "loss": 3.5281, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0260020060758808e-05, + "loss": 3.5326, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251650492052024e-05, + "loss": 3.5259, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0243264544541504e-05, + "loss": 3.5206, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234878597030987e-05, + "loss": 3.5256, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.022649264952046e-05, + "loss": 3.5281, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0218123080813676e-05, + "loss": 3.529, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209737133303156e-05, + "loss": 3.5228, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0201351185792633e-05, + "loss": 3.5308, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192965238282113e-05, + "loss": 3.5222, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.018459566957533e-05, + "loss": 3.5288, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.017620972206481e-05, + "loss": 3.527, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167823774554282e-05, + "loss": 3.5327, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015943782704376e-05, + "loss": 3.5326, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0151068258336978e-05, + "loss": 3.5206, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142682310826457e-05, + "loss": 3.5298, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0134296363315934e-05, + "loss": 3.5335, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125910415805414e-05, + "loss": 3.5355, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.011754084709863e-05, + "loss": 3.5337, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0109154899588103e-05, + "loss": 3.5296, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100768952077586e-05, + "loss": 3.5438, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0092383004567066e-05, + "loss": 3.5318, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0084013435860282e-05, + "loss": 3.5285, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0075627488349755e-05, + "loss": 3.5287, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0067241540839235e-05, + "loss": 3.5266, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.005887197213245e-05, + "loss": 3.5257, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.005048602462193e-05, + "loss": 3.5195, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0042100077111408e-05, + "loss": 3.5353, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033714129600888e-05, + "loss": 3.5182, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0025344560894104e-05, + "loss": 3.5337, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016958613383577e-05, + "loss": 3.5257, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0008572665873057e-05, + "loss": 3.5297, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.845808744430542, + "eval_runtime": 319.6336, + "eval_samples_per_second": 1193.839, + "eval_steps_per_second": 37.308, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 3.000018671836254e-05, + "loss": 3.5192, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991817149655756e-05, + "loss": 3.5184, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.998343120214523e-05, + "loss": 3.5318, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.997504525463471e-05, + "loss": 3.5336, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.996665930712419e-05, + "loss": 3.5285, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9958289738417405e-05, + "loss": 3.5225, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.994990379090688e-05, + "loss": 3.5197, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.994151784339636e-05, + "loss": 3.5223, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.993313189588584e-05, + "loss": 3.534, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.992476232717905e-05, + "loss": 3.526, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.991637637966853e-05, + "loss": 3.5312, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990799043215801e-05, + "loss": 3.5343, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899604484647494e-05, + "loss": 3.5127, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9891234915940703e-05, + "loss": 3.5153, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882848968430183e-05, + "loss": 3.5139, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9874463020919663e-05, + "loss": 3.5258, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9866077073409143e-05, + "loss": 3.5198, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9857707504702355e-05, + "loss": 3.5235, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9849321557191835e-05, + "loss": 3.5177, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840935609681315e-05, + "loss": 3.5426, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832549662170795e-05, + "loss": 3.5244, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9824180093464004e-05, + "loss": 3.5237, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815794145953484e-05, + "loss": 3.5261, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9807408198442964e-05, + "loss": 3.5402, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9799022250932444e-05, + "loss": 3.5162, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790652682225657e-05, + "loss": 3.5218, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9782266734715136e-05, + "loss": 3.5292, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773880787204616e-05, + "loss": 3.5152, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765494839694096e-05, + "loss": 3.5228, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.975712527098731e-05, + "loss": 3.5242, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.974873932347679e-05, + "loss": 3.5371, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.974035337596627e-05, + "loss": 3.5274, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.973196742845575e-05, + "loss": 3.5285, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723597859748958e-05, + "loss": 3.5261, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9715211912238438e-05, + "loss": 3.5263, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706825964727918e-05, + "loss": 3.5273, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698440017217398e-05, + "loss": 3.5122, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.969007044851061e-05, + "loss": 3.522, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.968168450100009e-05, + "loss": 3.5138, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.967329855348957e-05, + "loss": 3.5215, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.966491260597905e-05, + "loss": 3.519, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.965654303727226e-05, + "loss": 3.5317, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9648157089761742e-05, + "loss": 3.5201, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639771142251222e-05, + "loss": 3.5212, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.963140157354443e-05, + "loss": 3.5288, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962301562603391e-05, + "loss": 3.5165, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961462967852339e-05, + "loss": 3.5298, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960624373101287e-05, + "loss": 3.5071, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.9597874162306084e-05, + "loss": 3.5167, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9589488214795564e-05, + "loss": 3.5238, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9581102267285044e-05, + "loss": 3.5243, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572716319774524e-05, + "loss": 3.5223, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9564346751067733e-05, + "loss": 3.504, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555960803557213e-05, + "loss": 3.5211, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9547574856046696e-05, + "loss": 3.5103, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9539205287339905e-05, + "loss": 3.5369, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530819339829385e-05, + "loss": 3.5092, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9522433392318865e-05, + "loss": 3.5272, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9514047444808345e-05, + "loss": 3.5165, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505661497297825e-05, + "loss": 3.505, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9497275549787305e-05, + "loss": 3.5245, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.948888960227679e-05, + "loss": 3.5149, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.948050365476627e-05, + "loss": 3.5021, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9472134086059477e-05, + "loss": 3.5088, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463748138548957e-05, + "loss": 3.5264, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9455362191038437e-05, + "loss": 3.5169, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446976243527917e-05, + "loss": 3.5125, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.943860667482113e-05, + "loss": 3.5113, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.943022072731061e-05, + "loss": 3.5085, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.942183477980009e-05, + "loss": 3.516, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.941344883228957e-05, + "loss": 3.5244, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.940507926358278e-05, + "loss": 3.5175, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.939669331607226e-05, + "loss": 3.528, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9388307368561742e-05, + "loss": 3.5202, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379921421051222e-05, + "loss": 3.5219, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.937155185234443e-05, + "loss": 3.5133, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.936316590483391e-05, + "loss": 3.5178, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.935477995732339e-05, + "loss": 3.5194, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.934639400981287e-05, + "loss": 3.5128, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9338024441106083e-05, + "loss": 3.5133, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329638493595563e-05, + "loss": 3.5239, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9321252546085043e-05, + "loss": 3.5263, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312866598574523e-05, + "loss": 3.5179, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9304497029867732e-05, + "loss": 3.5022, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9296111082357212e-05, + "loss": 3.5154, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287725134846696e-05, + "loss": 3.5254, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9279355566139905e-05, + "loss": 3.5239, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270969618629385e-05, + "loss": 3.5162, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262583671118865e-05, + "loss": 3.5293, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9254197723608345e-05, + "loss": 3.5215, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245828154901557e-05, + "loss": 3.5122, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9237442207391037e-05, + "loss": 3.5171, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9229056259880517e-05, + "loss": 3.5239, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220670312369997e-05, + "loss": 3.515, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9212300743663206e-05, + "loss": 3.5296, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203914796152686e-05, + "loss": 3.5076, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195528848642166e-05, + "loss": 3.511, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918714290113165e-05, + "loss": 3.5131, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.917877333242486e-05, + "loss": 3.5247, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.917038738491434e-05, + "loss": 3.5232, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916200143740382e-05, + "loss": 3.5161, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.91536154898933e-05, + "loss": 3.5125, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914524592118651e-05, + "loss": 3.5115, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.913685997367599e-05, + "loss": 3.5245, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.912847402616547e-05, + "loss": 3.5012, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.912008807865495e-05, + "loss": 3.5162, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.911171850994816e-05, + "loss": 3.5216, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.910333256243764e-05, + "loss": 3.5167, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.909494661492712e-05, + "loss": 3.5164, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086560667416603e-05, + "loss": 3.5192, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9078191098709812e-05, + "loss": 3.5069, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069805151199292e-05, + "loss": 3.5208, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9061419203688772e-05, + "loss": 3.5188, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9053033256178252e-05, + "loss": 3.5146, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044663687471464e-05, + "loss": 3.5213, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9036277739960944e-05, + "loss": 3.5218, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027891792450424e-05, + "loss": 3.518, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9019505844939904e-05, + "loss": 3.5162, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9011136276233113e-05, + "loss": 3.5181, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002750328722593e-05, + "loss": 3.5142, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8994364381212073e-05, + "loss": 3.5042, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.898597843370155e-05, + "loss": 3.5124, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977608864994766e-05, + "loss": 3.5119, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8969222917484246e-05, + "loss": 3.521, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960836969973726e-05, + "loss": 3.5083, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8952451022463202e-05, + "loss": 3.5164, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8944081453756415e-05, + "loss": 3.508, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935695506245898e-05, + "loss": 3.5145, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8927309558735378e-05, + "loss": 3.51, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.891892361122485e-05, + "loss": 3.526, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8910554042518067e-05, + "loss": 3.5156, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8902168095007547e-05, + "loss": 3.5117, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893782147497024e-05, + "loss": 3.512, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8885396199986504e-05, + "loss": 3.5156, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887702663127972e-05, + "loss": 3.5239, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.88686406837692e-05, + "loss": 3.5205, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8860254736258673e-05, + "loss": 3.5196, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8851868788748153e-05, + "loss": 3.5277, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.884349922004137e-05, + "loss": 3.5179, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8835113272530845e-05, + "loss": 3.516, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826727325020325e-05, + "loss": 3.5126, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8818341377509805e-05, + "loss": 3.5194, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.880997180880302e-05, + "loss": 3.5135, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8801585861292497e-05, + "loss": 3.5041, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8793199913781977e-05, + "loss": 3.5195, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784813966271457e-05, + "loss": 3.5086, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8776444397564673e-05, + "loss": 3.5198, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8768058450054146e-05, + "loss": 3.5115, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759672502543626e-05, + "loss": 3.5136, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.848397731781006, + "eval_runtime": 313.7127, + "eval_samples_per_second": 1216.371, + "eval_steps_per_second": 38.012, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8751286555033106e-05, + "loss": 3.5037, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.874290060752259e-05, + "loss": 3.5071, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.873451466001207e-05, + "loss": 3.5198, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.872614509130528e-05, + "loss": 3.5164, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.871775914379476e-05, + "loss": 3.517, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.870937319628424e-05, + "loss": 3.5098, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.870098724877372e-05, + "loss": 3.5062, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.869261768006693e-05, + "loss": 3.5092, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.868423173255641e-05, + "loss": 3.5185, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.867584578504589e-05, + "loss": 3.5158, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866745983753537e-05, + "loss": 3.5116, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865909026882858e-05, + "loss": 3.5194, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.865070432131806e-05, + "loss": 3.4994, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8642318373807543e-05, + "loss": 3.5057, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633932426297023e-05, + "loss": 3.5081, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8625562857590232e-05, + "loss": 3.4996, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8617176910079712e-05, + "loss": 3.5086, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608790962569192e-05, + "loss": 3.5084, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8600405015058672e-05, + "loss": 3.5052, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8592035446351885e-05, + "loss": 3.534, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583649498841365e-05, + "loss": 3.5122, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8575263551330845e-05, + "loss": 3.5099, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566877603820325e-05, + "loss": 3.5141, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8558508035113534e-05, + "loss": 3.5228, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8550122087603014e-05, + "loss": 3.5021, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541736140092497e-05, + "loss": 3.507, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8533350192581977e-05, + "loss": 3.5113, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524980623875186e-05, + "loss": 3.5081, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516594676364666e-05, + "loss": 3.5075, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8508208728854146e-05, + "loss": 3.506, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499822781343626e-05, + "loss": 3.5278, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.849145321263684e-05, + "loss": 3.5151, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8483067265126318e-05, + "loss": 3.5138, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474681317615798e-05, + "loss": 3.5128, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8466295370105278e-05, + "loss": 3.5146, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457925801398487e-05, + "loss": 3.5123, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449539853887967e-05, + "loss": 3.5005, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.844115390637745e-05, + "loss": 3.5078, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843276795886693e-05, + "loss": 3.498, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842439839016014e-05, + "loss": 3.5124, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.841601244264962e-05, + "loss": 3.5021, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.84076264951391e-05, + "loss": 3.518, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839924054762858e-05, + "loss": 3.5087, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390870978921792e-05, + "loss": 3.5074, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382485031411272e-05, + "loss": 3.5153, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8374099083900752e-05, + "loss": 3.5048, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365713136390232e-05, + "loss": 3.5121, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835734356768344e-05, + "loss": 3.4979, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834895762017292e-05, + "loss": 3.5039, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340571672662404e-05, + "loss": 3.5093, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8332185725151884e-05, + "loss": 3.5091, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323816156445093e-05, + "loss": 3.5153, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8315430208934573e-05, + "loss": 3.487, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8307044261424053e-05, + "loss": 3.5089, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298658313913533e-05, + "loss": 3.4928, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8290305124010475e-05, + "loss": 3.5238, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281919176499955e-05, + "loss": 3.4965, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273533228989435e-05, + "loss": 3.5142, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8265147281478915e-05, + "loss": 3.5072, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256761333968395e-05, + "loss": 3.4958, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8248375386457875e-05, + "loss": 3.5045, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239989438947358e-05, + "loss": 3.503, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231603491436838e-05, + "loss": 3.4895, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8223233922730047e-05, + "loss": 3.4954, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214847975219527e-05, + "loss": 3.5115, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206462027709007e-05, + "loss": 3.5055, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8198076080198487e-05, + "loss": 3.5007, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.81897065114917e-05, + "loss": 3.4982, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.818132056398118e-05, + "loss": 3.4921, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.817293461647066e-05, + "loss": 3.5035, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.816454866896014e-05, + "loss": 3.5067, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8156179100253348e-05, + "loss": 3.5067, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147793152742828e-05, + "loss": 3.5174, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.813940720523231e-05, + "loss": 3.5057, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.813102125772179e-05, + "loss": 3.5119, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122651689015e-05, + "loss": 3.497, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811426574150448e-05, + "loss": 3.5106, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810587979399396e-05, + "loss": 3.5024, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809749384648344e-05, + "loss": 3.4983, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8089124277776653e-05, + "loss": 3.5031, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080738330266133e-05, + "loss": 3.5063, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8072352382755613e-05, + "loss": 3.5131, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063966435245093e-05, + "loss": 3.5054, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055596866538302e-05, + "loss": 3.4893, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8047210919027782e-05, + "loss": 3.4948, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038824971517262e-05, + "loss": 3.515, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8030439024006745e-05, + "loss": 3.5081, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8022069455299954e-05, + "loss": 3.5053, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013683507789434e-05, + "loss": 3.5123, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8005297560278914e-05, + "loss": 3.5125, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996927991572123e-05, + "loss": 3.4957, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988542044061607e-05, + "loss": 3.5017, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7980156096551087e-05, + "loss": 3.5114, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971770149040567e-05, + "loss": 3.5007, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7963400580333776e-05, + "loss": 3.5157, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7955014632823256e-05, + "loss": 3.4967, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946628685312736e-05, + "loss": 3.4975, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7938242737802216e-05, + "loss": 3.501, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929873169095428e-05, + "loss": 3.5097, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7921487221584908e-05, + "loss": 3.5092, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7913101274074388e-05, + "loss": 3.5031, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7904715326563868e-05, + "loss": 3.4983, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7896345757857077e-05, + "loss": 3.4967, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.788795981034656e-05, + "loss": 3.5143, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787957386283604e-05, + "loss": 3.4918, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.787118791532552e-05, + "loss": 3.496, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.786281834661873e-05, + "loss": 3.5132, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785443239910821e-05, + "loss": 3.504, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784604645159769e-05, + "loss": 3.4992, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783766050408717e-05, + "loss": 3.5051, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.782929093538038e-05, + "loss": 3.4965, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.782090498786986e-05, + "loss": 3.5093, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.781251904035934e-05, + "loss": 3.5019, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7804133092848815e-05, + "loss": 3.5036, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.779576352414203e-05, + "loss": 3.5115, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787377576631514e-05, + "loss": 3.5124, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778991629120994e-05, + "loss": 3.502, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770605681610467e-05, + "loss": 3.5026, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7762236112903683e-05, + "loss": 3.506, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753850165393163e-05, + "loss": 3.5, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745464217882643e-05, + "loss": 3.4918, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.773707827037212e-05, + "loss": 3.4997, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728708701665335e-05, + "loss": 3.4972, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7720322754154815e-05, + "loss": 3.5087, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.771193680664429e-05, + "loss": 3.4959, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.770355085913377e-05, + "loss": 3.5053, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7695181290426984e-05, + "loss": 3.4882, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686795342916468e-05, + "loss": 3.5032, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767840939540594e-05, + "loss": 3.4981, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.767002344789542e-05, + "loss": 3.5114, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7661653879188637e-05, + "loss": 3.505, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7653267931678117e-05, + "loss": 3.5037, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644881984167593e-05, + "loss": 3.4944, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7636496036657073e-05, + "loss": 3.5004, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.762812646795029e-05, + "loss": 3.5104, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619740520439762e-05, + "loss": 3.5103, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7611354572929242e-05, + "loss": 3.5075, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602968625418722e-05, + "loss": 3.5131, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.7594599056711938e-05, + "loss": 3.4996, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7586213109201415e-05, + "loss": 3.5058, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577827161690894e-05, + "loss": 3.4987, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569441214180374e-05, + "loss": 3.5078, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7561071645473584e-05, + "loss": 3.5031, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552685697963067e-05, + "loss": 3.4866, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7544299750452547e-05, + "loss": 3.5081, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535913802942027e-05, + "loss": 3.4979, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527544234235236e-05, + "loss": 3.5064, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7519158286724716e-05, + "loss": 3.498, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510772339214196e-05, + "loss": 3.502, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.850377082824707, + "eval_runtime": 307.4766, + "eval_samples_per_second": 1241.041, + "eval_steps_per_second": 38.783, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502386391703676e-05, + "loss": 3.4923, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7494016822996888e-05, + "loss": 3.4962, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485630875486368e-05, + "loss": 3.5058, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7477244927975848e-05, + "loss": 3.5031, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468858980465328e-05, + "loss": 3.5089, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7460489411758537e-05, + "loss": 3.4929, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.745210346424802e-05, + "loss": 3.4978, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.74437175167375e-05, + "loss": 3.4946, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743534794803071e-05, + "loss": 3.5038, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742696200052019e-05, + "loss": 3.505, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741857605300967e-05, + "loss": 3.5003, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.741019010549915e-05, + "loss": 3.5021, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401820536792362e-05, + "loss": 3.4894, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7393434589281842e-05, + "loss": 3.4896, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7385048641771322e-05, + "loss": 3.4977, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376662694260802e-05, + "loss": 3.491, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.736829312555401e-05, + "loss": 3.4933, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735990717804349e-05, + "loss": 3.4934, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7351521230532974e-05, + "loss": 3.4898, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7343135283022454e-05, + "loss": 3.5229, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334765714315663e-05, + "loss": 3.4978, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7326379766805143e-05, + "loss": 3.5, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317993819294623e-05, + "loss": 3.4993, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309607871784103e-05, + "loss": 3.5076, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7301238303077316e-05, + "loss": 3.4902, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292852355566796e-05, + "loss": 3.4956, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7284466408056276e-05, + "loss": 3.4993, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7276080460545755e-05, + "loss": 3.4986, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267710891838965e-05, + "loss": 3.4907, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7259324944328445e-05, + "loss": 3.4958, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250938996817928e-05, + "loss": 3.5122, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242553049307408e-05, + "loss": 3.5015, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7234183480600617e-05, + "loss": 3.4982, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225797533090097e-05, + "loss": 3.5039, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7217411585579577e-05, + "loss": 3.4993, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7209025638069057e-05, + "loss": 3.4986, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.720065606936227e-05, + "loss": 3.4868, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.719227012185175e-05, + "loss": 3.4986, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718388417434123e-05, + "loss": 3.4852, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717549822683071e-05, + "loss": 3.4962, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7167128658123918e-05, + "loss": 3.492, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158742710613398e-05, + "loss": 3.5058, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.715035676310288e-05, + "loss": 3.4976, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.714197081559236e-05, + "loss": 3.4936, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.713360124688557e-05, + "loss": 3.5017, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.712521529937505e-05, + "loss": 3.4946, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.711682935186453e-05, + "loss": 3.5001, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.710844340435401e-05, + "loss": 3.4875, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7100073835647223e-05, + "loss": 3.4889, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7091687888136703e-05, + "loss": 3.4991, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7083301940626183e-05, + "loss": 3.4979, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074915993115663e-05, + "loss": 3.4968, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7066546424408872e-05, + "loss": 3.4804, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7058160476898352e-05, + "loss": 3.4993, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049774529387832e-05, + "loss": 3.4802, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7041404960681044e-05, + "loss": 3.5106, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7033019013170524e-05, + "loss": 3.4804, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024633065660004e-05, + "loss": 3.5002, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7016247118149484e-05, + "loss": 3.4914, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007861170638964e-05, + "loss": 3.488, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6999475223128444e-05, + "loss": 3.4896, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6991089275617924e-05, + "loss": 3.4926, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982703328107407e-05, + "loss": 3.4749, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6974333759400616e-05, + "loss": 3.4856, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965947811890096e-05, + "loss": 3.4934, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6957561864379576e-05, + "loss": 3.4971, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6949175916869056e-05, + "loss": 3.4833, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.694080634816227e-05, + "loss": 3.4862, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.693242040065175e-05, + "loss": 3.4847, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.692403445314123e-05, + "loss": 3.4871, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.691564850563071e-05, + "loss": 3.4928, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6907278936923918e-05, + "loss": 3.4914, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898892989413398e-05, + "loss": 3.5032, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6890507041902878e-05, + "loss": 3.4969, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.688212109439236e-05, + "loss": 3.4972, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.687375152568557e-05, + "loss": 3.4835, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686536557817505e-05, + "loss": 3.4938, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.685697963066453e-05, + "loss": 3.4976, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.684859368315401e-05, + "loss": 3.4845, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6840224114447223e-05, + "loss": 3.4936, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831838166936702e-05, + "loss": 3.4929, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6823452219426182e-05, + "loss": 3.5016, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6815066271915662e-05, + "loss": 3.4931, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.680669670320887e-05, + "loss": 3.4767, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.679831075569835e-05, + "loss": 3.4845, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.678992480818783e-05, + "loss": 3.5009, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781555239481044e-05, + "loss": 3.4965, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6773169291970524e-05, + "loss": 3.4938, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764783344460004e-05, + "loss": 3.5024, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6756397396949484e-05, + "loss": 3.4991, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6748027828242693e-05, + "loss": 3.48, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739641880732176e-05, + "loss": 3.4956, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6731255933221656e-05, + "loss": 3.4943, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722869985711136e-05, + "loss": 3.4887, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6714500417004345e-05, + "loss": 3.5052, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6706114469493825e-05, + "loss": 3.488, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697728521983305e-05, + "loss": 3.4801, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6689342574472785e-05, + "loss": 3.4893, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680973005765998e-05, + "loss": 3.4991, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6672587058255477e-05, + "loss": 3.4972, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6664201110744957e-05, + "loss": 3.4923, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6655815163234437e-05, + "loss": 3.484, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6647445594527647e-05, + "loss": 3.483, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.663905964701713e-05, + "loss": 3.5047, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.663067369950661e-05, + "loss": 3.4747, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6622287751996083e-05, + "loss": 3.4912, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.66139181832893e-05, + "loss": 3.497, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.660553223577878e-05, + "loss": 3.4896, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.659714628826826e-05, + "loss": 3.4871, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588760340757735e-05, + "loss": 3.4959, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.658039077205095e-05, + "loss": 3.4872, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.657200482454043e-05, + "loss": 3.4933, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.656361887702991e-05, + "loss": 3.4905, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6555232929519384e-05, + "loss": 3.4903, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.65468633608126e-05, + "loss": 3.498, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6538477413302084e-05, + "loss": 3.499, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6530091465791557e-05, + "loss": 3.4927, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521705518281037e-05, + "loss": 3.4848, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6513335949574253e-05, + "loss": 3.4908, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504950002063732e-05, + "loss": 3.4871, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.649656405455321e-05, + "loss": 3.4791, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.648817810704269e-05, + "loss": 3.4933, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479808538335905e-05, + "loss": 3.4805, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6471422590825385e-05, + "loss": 3.4957, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6463036643314858e-05, + "loss": 3.4827, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454650695804338e-05, + "loss": 3.4924, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6446281127097554e-05, + "loss": 3.4799, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.643789517958703e-05, + "loss": 3.4885, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642950923207651e-05, + "loss": 3.4817, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.642112328456599e-05, + "loss": 3.5012, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412753715859206e-05, + "loss": 3.4958, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6404367768348683e-05, + "loss": 3.4908, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395981820838163e-05, + "loss": 3.4803, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387595873327643e-05, + "loss": 3.49, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.637922630462086e-05, + "loss": 3.4986, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370840357110332e-05, + "loss": 3.5004, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636245440959981e-05, + "loss": 3.4912, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.635406846208929e-05, + "loss": 3.5022, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6345698893382504e-05, + "loss": 3.4901, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6337312945871984e-05, + "loss": 3.4947, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328926998361464e-05, + "loss": 3.4857, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.632055742965468e-05, + "loss": 3.4898, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6312171482144153e-05, + "loss": 3.4935, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303785534633636e-05, + "loss": 3.477, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6295399587123116e-05, + "loss": 3.4906, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6287030018416332e-05, + "loss": 3.4883, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6278644070905805e-05, + "loss": 3.4911, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6270258123395285e-05, + "loss": 3.4848, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6261872175884765e-05, + "loss": 3.4871, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.849630117416382, + "eval_runtime": 318.6061, + "eval_samples_per_second": 1197.689, + "eval_steps_per_second": 37.429, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253486228374245e-05, + "loss": 3.4787, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624510028086373e-05, + "loss": 3.4817, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.623671433335321e-05, + "loss": 3.4933, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622832838584269e-05, + "loss": 3.4894, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219958817135898e-05, + "loss": 3.4983, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211572869625378e-05, + "loss": 3.4776, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6203186922114858e-05, + "loss": 3.4863, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194800974604338e-05, + "loss": 3.4794, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618643140589755e-05, + "loss": 3.4936, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.617804545838703e-05, + "loss": 3.4901, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.616965951087651e-05, + "loss": 3.4892, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.616127356336599e-05, + "loss": 3.4884, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.61529039946592e-05, + "loss": 3.4764, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.614451804714868e-05, + "loss": 3.4803, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6136132099638162e-05, + "loss": 3.4846, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127746152127642e-05, + "loss": 3.4811, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611937658342085e-05, + "loss": 3.4809, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611099063591033e-05, + "loss": 3.4864, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.610260468839981e-05, + "loss": 3.4779, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6094235119693024e-05, + "loss": 3.5108, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085849172182504e-05, + "loss": 3.4851, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6077463224671984e-05, + "loss": 3.4856, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6069077277161464e-05, + "loss": 3.4897, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060707708454673e-05, + "loss": 3.4928, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6052321760944153e-05, + "loss": 3.4782, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043935813433633e-05, + "loss": 3.489, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035549865923116e-05, + "loss": 3.4831, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6027180297216325e-05, + "loss": 3.4851, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018794349705805e-05, + "loss": 3.477, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6010408402195285e-05, + "loss": 3.4865, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6002022454684765e-05, + "loss": 3.499, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993652885977977e-05, + "loss": 3.4901, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5985266938467457e-05, + "loss": 3.4905, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976880990956937e-05, + "loss": 3.4904, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5968495043446417e-05, + "loss": 3.4843, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5960125474739626e-05, + "loss": 3.4908, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951739527229106e-05, + "loss": 3.4729, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5943353579718586e-05, + "loss": 3.486, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.593496763220807e-05, + "loss": 3.4715, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.592659806350128e-05, + "loss": 3.4852, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.591821211599076e-05, + "loss": 3.4788, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.590982616848024e-05, + "loss": 3.4928, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.590144022096972e-05, + "loss": 3.4849, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589307065226293e-05, + "loss": 3.4804, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.588468470475241e-05, + "loss": 3.4898, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.587629875724189e-05, + "loss": 3.4846, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.586791280973137e-05, + "loss": 3.4848, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.585954324102458e-05, + "loss": 3.4793, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.585115729351406e-05, + "loss": 3.4698, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.584277134600354e-05, + "loss": 3.4863, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5834385398493023e-05, + "loss": 3.4848, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5826015829786232e-05, + "loss": 3.485, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817629882275712e-05, + "loss": 3.4705, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5809243934765192e-05, + "loss": 3.4908, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800857987254672e-05, + "loss": 3.4652, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5792504797351614e-05, + "loss": 3.4975, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5784118849841094e-05, + "loss": 3.4698, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775732902330574e-05, + "loss": 3.4854, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5767346954820054e-05, + "loss": 3.4803, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758961007309534e-05, + "loss": 3.4775, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750575059799014e-05, + "loss": 3.4755, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5742189112288494e-05, + "loss": 3.484, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733803164777977e-05, + "loss": 3.4628, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5725433596071186e-05, + "loss": 3.4715, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5717047648560666e-05, + "loss": 3.4847, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708661701050146e-05, + "loss": 3.4822, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5700275753539626e-05, + "loss": 3.4737, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.569190618483284e-05, + "loss": 3.4741, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568352023732232e-05, + "loss": 3.4678, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5675134289811798e-05, + "loss": 3.4744, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666748342301278e-05, + "loss": 3.4837, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5658378773594487e-05, + "loss": 3.4786, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649992826083967e-05, + "loss": 3.4928, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641606878573447e-05, + "loss": 3.4832, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.563322093106293e-05, + "loss": 3.4887, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.562485136235614e-05, + "loss": 3.47, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.561646541484562e-05, + "loss": 3.481, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.56080794673351e-05, + "loss": 3.4853, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559969351982458e-05, + "loss": 3.4687, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5591323951117792e-05, + "loss": 3.4838, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582938003607272e-05, + "loss": 3.4784, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574552056096752e-05, + "loss": 3.4866, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5566166108586232e-05, + "loss": 3.4792, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.555779653987944e-05, + "loss": 3.4679, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.554941059236892e-05, + "loss": 3.4752, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.55410246448584e-05, + "loss": 3.4824, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532638697347877e-05, + "loss": 3.487, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5524269128641093e-05, + "loss": 3.4841, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515883181130573e-05, + "loss": 3.4843, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507497233620053e-05, + "loss": 3.4911, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5499127664913262e-05, + "loss": 3.469, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490741717402746e-05, + "loss": 3.4833, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5482355769892226e-05, + "loss": 3.4787, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473969822381706e-05, + "loss": 3.4784, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465600253674915e-05, + "loss": 3.4913, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5457214306164395e-05, + "loss": 3.4799, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448828358653875e-05, + "loss": 3.4678, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.544044241114335e-05, + "loss": 3.4791, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5432072842436567e-05, + "loss": 3.4853, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423686894926047e-05, + "loss": 3.4883, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5415300947415527e-05, + "loss": 3.4802, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406914999905e-05, + "loss": 3.4718, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5398545431198216e-05, + "loss": 3.4723, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.53901594836877e-05, + "loss": 3.49, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538177353617718e-05, + "loss": 3.464, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5373387588666653e-05, + "loss": 3.4751, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536501801995987e-05, + "loss": 3.4849, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535663207244935e-05, + "loss": 3.4802, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5348246124938825e-05, + "loss": 3.4711, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339860177428305e-05, + "loss": 3.4846, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.533149060872152e-05, + "loss": 3.4767, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5323104661211e-05, + "loss": 3.4792, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314718713700474e-05, + "loss": 3.4803, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5306332766189954e-05, + "loss": 3.476, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.529796319748317e-05, + "loss": 3.4917, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.528957724997265e-05, + "loss": 3.4826, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5281191302462126e-05, + "loss": 3.4833, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272805354951606e-05, + "loss": 3.4728, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5264435786244822e-05, + "loss": 3.4795, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.52560498387343e-05, + "loss": 3.4783, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524766389122378e-05, + "loss": 3.4666, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.523927794371326e-05, + "loss": 3.4811, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230908375006474e-05, + "loss": 3.4738, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5222522427495948e-05, + "loss": 3.4809, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5214136479985428e-05, + "loss": 3.4721, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205750532474908e-05, + "loss": 3.4822, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5197380963768123e-05, + "loss": 3.4622, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.51889950162576e-05, + "loss": 3.4777, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.518060906874708e-05, + "loss": 3.4729, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517222312123656e-05, + "loss": 3.4862, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516385355252977e-05, + "loss": 3.4834, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.515546760501925e-05, + "loss": 3.4831, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5147081657508732e-05, + "loss": 3.4675, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138695709998212e-05, + "loss": 3.4814, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.513032614129142e-05, + "loss": 3.4832, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.51219401937809e-05, + "loss": 3.4857, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511355424627038e-05, + "loss": 3.4841, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510516829875986e-05, + "loss": 3.4853, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096798730053074e-05, + "loss": 3.4816, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5088412782542554e-05, + "loss": 3.4857, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5080026835032034e-05, + "loss": 3.4717, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071640887521514e-05, + "loss": 3.4782, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5063271318814723e-05, + "loss": 3.4797, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054885371304203e-05, + "loss": 3.4672, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5046499423793686e-05, + "loss": 3.4752, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5038113476283166e-05, + "loss": 3.4777, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029743907576375e-05, + "loss": 3.4782, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5021357960065855e-05, + "loss": 3.4697, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012972012555335e-05, + "loss": 3.4814, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8519198894500732, + "eval_runtime": 305.205, + "eval_samples_per_second": 1250.278, + "eval_steps_per_second": 39.072, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.5004586065044815e-05, + "loss": 3.4676, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.499621649633803e-05, + "loss": 3.4706, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.498783054882751e-05, + "loss": 3.4811, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4979444601316987e-05, + "loss": 3.4778, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4971058653806467e-05, + "loss": 3.488, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.496268908509968e-05, + "loss": 3.4667, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4954303137589156e-05, + "loss": 3.4755, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.494591719007864e-05, + "loss": 3.466, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4937547621371852e-05, + "loss": 3.4809, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4929161673861332e-05, + "loss": 3.4826, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.492077572635081e-05, + "loss": 3.471, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.491238977884029e-05, + "loss": 3.485, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.49040202101335e-05, + "loss": 3.4608, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4895634262622984e-05, + "loss": 3.4667, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.488724831511246e-05, + "loss": 3.4752, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.487886236760194e-05, + "loss": 3.467, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4870492798895153e-05, + "loss": 3.4684, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.486210685138463e-05, + "loss": 3.4716, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.485372090387411e-05, + "loss": 3.4697, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4845334956363593e-05, + "loss": 3.4955, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836965387656806e-05, + "loss": 3.4749, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4828579440146282e-05, + "loss": 3.4703, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4820193492635762e-05, + "loss": 3.4815, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4811807545125242e-05, + "loss": 3.4824, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4803437976418455e-05, + "loss": 3.4674, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4795052028907935e-05, + "loss": 3.4788, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786666081397415e-05, + "loss": 3.4706, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4778280133886895e-05, + "loss": 3.4741, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4769910565180104e-05, + "loss": 3.4639, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4761524617669584e-05, + "loss": 3.4748, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4753138670159064e-05, + "loss": 3.4907, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4744752722648547e-05, + "loss": 3.477, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4736383153941756e-05, + "loss": 3.4754, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727997206431236e-05, + "loss": 3.4789, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719611258920716e-05, + "loss": 3.4716, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4711225311410196e-05, + "loss": 3.4793, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470285574270341e-05, + "loss": 3.4629, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.469446979519289e-05, + "loss": 3.4724, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4686083847682368e-05, + "loss": 3.4626, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4677697900171848e-05, + "loss": 3.4684, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.466934471026879e-05, + "loss": 3.4702, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.466095876275827e-05, + "loss": 3.4797, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.465257281524775e-05, + "loss": 3.4735, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464418686773723e-05, + "loss": 3.4712, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463580092022671e-05, + "loss": 3.4759, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.462741497271619e-05, + "loss": 3.4708, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461902902520567e-05, + "loss": 3.4745, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.461064307769515e-05, + "loss": 3.4682, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4602273508988362e-05, + "loss": 3.4588, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4593887561477842e-05, + "loss": 3.4748, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4585501613967322e-05, + "loss": 3.4684, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4577115666456802e-05, + "loss": 3.476, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456874609775001e-05, + "loss": 3.4622, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.456036015023949e-05, + "loss": 3.4745, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.455197420272897e-05, + "loss": 3.4542, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4543604634022183e-05, + "loss": 3.4835, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4535218686511663e-05, + "loss": 3.4595, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4526832739001143e-05, + "loss": 3.4685, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4518446791490623e-05, + "loss": 3.4726, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4510060843980103e-05, + "loss": 3.4656, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4501674896469583e-05, + "loss": 3.4669, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4493288948959063e-05, + "loss": 3.4689, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4484903001448543e-05, + "loss": 3.4564, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4476533432741756e-05, + "loss": 3.4568, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4468147485231232e-05, + "loss": 3.4721, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4459761537720712e-05, + "loss": 3.4693, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4451375590210192e-05, + "loss": 3.4589, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4443006021503408e-05, + "loss": 3.4669, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4434620073992884e-05, + "loss": 3.4554, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4426234126482364e-05, + "loss": 3.4638, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4417848178971844e-05, + "loss": 3.4711, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4409478610265057e-05, + "loss": 3.4654, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4401092662754533e-05, + "loss": 3.4791, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4392706715244017e-05, + "loss": 3.472, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4384320767733497e-05, + "loss": 3.4814, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375951199026706e-05, + "loss": 3.4585, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367565251516186e-05, + "loss": 3.4689, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4359179304005666e-05, + "loss": 3.4718, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4350793356495146e-05, + "loss": 3.4554, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4342423787788358e-05, + "loss": 3.4752, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4334037840277838e-05, + "loss": 3.469, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4325651892767318e-05, + "loss": 3.4736, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4317265945256798e-05, + "loss": 3.4687, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4308896376550007e-05, + "loss": 3.4546, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4300510429039487e-05, + "loss": 3.4652, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.429212448152897e-05, + "loss": 3.4691, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.428373853401845e-05, + "loss": 3.4744, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.427536896531166e-05, + "loss": 3.4722, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.426698301780114e-05, + "loss": 3.4743, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.425859707029062e-05, + "loss": 3.4765, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.42502111227801e-05, + "loss": 3.4608, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4241841554073312e-05, + "loss": 3.4714, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4233455606562792e-05, + "loss": 3.4647, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4225069659052272e-05, + "loss": 3.4722, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4216683711541752e-05, + "loss": 3.48, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.420831414283496e-05, + "loss": 3.4654, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.419992819532444e-05, + "loss": 3.4607, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4191542247813924e-05, + "loss": 3.4635, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4183156300303404e-05, + "loss": 3.4705, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.4174786731596613e-05, + "loss": 3.4803, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4166400784086093e-05, + "loss": 3.464, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4158014836575573e-05, + "loss": 3.4632, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4149645267868786e-05, + "loss": 3.4598, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4141259320358266e-05, + "loss": 3.4781, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132873372847745e-05, + "loss": 3.455, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4124487425337225e-05, + "loss": 3.4659, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.4116117856630435e-05, + "loss": 3.4713, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4107731909119914e-05, + "loss": 3.4683, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4099345961609394e-05, + "loss": 3.4623, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4090960014098878e-05, + "loss": 3.4743, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4082590445392087e-05, + "loss": 3.4664, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4074204497881567e-05, + "loss": 3.4635, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4065818550371047e-05, + "loss": 3.47, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4057432602860527e-05, + "loss": 3.4677, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.404906303415374e-05, + "loss": 3.4782, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.404067708664322e-05, + "loss": 3.4738, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.40322911391327e-05, + "loss": 3.4678, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.402390519162218e-05, + "loss": 3.4599, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4015535622915388e-05, + "loss": 3.4705, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4007149675404868e-05, + "loss": 3.4662, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3998763727894348e-05, + "loss": 3.4548, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.399037778038383e-05, + "loss": 3.47, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.398200821167704e-05, + "loss": 3.4593, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.397362226416652e-05, + "loss": 3.4681, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3965236316656e-05, + "loss": 3.4646, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.395685036914548e-05, + "loss": 3.4677, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3948480800438693e-05, + "loss": 3.4521, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3940094852928173e-05, + "loss": 3.4654, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3931708905417653e-05, + "loss": 3.4645, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.392332295790713e-05, + "loss": 3.4676, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3914953389200342e-05, + "loss": 3.4709, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3906567441689822e-05, + "loss": 3.4742, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3898181494179302e-05, + "loss": 3.4534, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3889795546668782e-05, + "loss": 3.4697, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3881425977961994e-05, + "loss": 3.477, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3873040030451474e-05, + "loss": 3.4714, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.3864654082940954e-05, + "loss": 3.4721, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385626813543043e-05, + "loss": 3.4753, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.3847898566723643e-05, + "loss": 3.4673, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3839512619213127e-05, + "loss": 3.4759, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3831126671702603e-05, + "loss": 3.4566, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822740724192083e-05, + "loss": 3.4708, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3814371155485296e-05, + "loss": 3.4627, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3805985207974775e-05, + "loss": 3.462, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3797599260464255e-05, + "loss": 3.4668, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3789213312953735e-05, + "loss": 3.462, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780843744246948e-05, + "loss": 3.4693, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3772457796736428e-05, + "loss": 3.4553, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3764071849225904e-05, + "loss": 3.4706, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.8534233570098877, + "eval_runtime": 303.133, + "eval_samples_per_second": 1258.824, + "eval_steps_per_second": 39.339, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755685901715384e-05, + "loss": 3.4564, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3747299954204864e-05, + "loss": 3.4571, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738914006694348e-05, + "loss": 3.4667, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730528059183828e-05, + "loss": 3.4712, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3722158490477037e-05, + "loss": 3.4686, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713772542966517e-05, + "loss": 3.4596, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3705386595455997e-05, + "loss": 3.4586, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3697000647945477e-05, + "loss": 3.4575, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368863107923869e-05, + "loss": 3.4656, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.368024513172817e-05, + "loss": 3.4737, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.367185918421765e-05, + "loss": 3.4584, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.366347323670713e-05, + "loss": 3.4704, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3655103668000338e-05, + "loss": 3.4541, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646717720489818e-05, + "loss": 3.4561, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.36383317729793e-05, + "loss": 3.4624, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362996220427251e-05, + "loss": 3.4529, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.362157625676199e-05, + "loss": 3.4583, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.361319030925147e-05, + "loss": 3.4603, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.360480436174095e-05, + "loss": 3.4538, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596434793034163e-05, + "loss": 3.4825, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3588048845523643e-05, + "loss": 3.4678, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579662898013123e-05, + "loss": 3.4616, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3571276950502603e-05, + "loss": 3.4656, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562907381795812e-05, + "loss": 3.471, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554521434285292e-05, + "loss": 3.4551, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.354613548677477e-05, + "loss": 3.4658, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.353774953926425e-05, + "loss": 3.4635, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3529379970557464e-05, + "loss": 3.4576, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520994023046944e-05, + "loss": 3.4509, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3512608075536424e-05, + "loss": 3.4664, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504222128025904e-05, + "loss": 3.4787, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495852559319116e-05, + "loss": 3.4657, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3487466611808596e-05, + "loss": 3.4708, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3479080664298076e-05, + "loss": 3.4652, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470694716787553e-05, + "loss": 3.4596, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3462325148080765e-05, + "loss": 3.4662, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3453939200570245e-05, + "loss": 3.4571, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3445553253059725e-05, + "loss": 3.4588, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3437167305549205e-05, + "loss": 3.4525, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428797736842418e-05, + "loss": 3.4557, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420411789331898e-05, + "loss": 3.4582, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3412025841821378e-05, + "loss": 3.468, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403639894310854e-05, + "loss": 3.4622, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3395270325604067e-05, + "loss": 3.4599, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338688437809355e-05, + "loss": 3.466, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378498430583027e-05, + "loss": 3.4618, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3370112483072507e-05, + "loss": 3.4618, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.336174291436572e-05, + "loss": 3.4571, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.33533569668552e-05, + "loss": 3.4462, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334497101934468e-05, + "loss": 3.4649, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333658507183416e-05, + "loss": 3.4581, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.332821550312737e-05, + "loss": 3.4644, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331982955561685e-05, + "loss": 3.4509, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3311443608106328e-05, + "loss": 3.461, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3303057660595808e-05, + "loss": 3.4431, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329468809188902e-05, + "loss": 3.4688, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.32863021443785e-05, + "loss": 3.45, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327791619686798e-05, + "loss": 3.4585, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326953024935746e-05, + "loss": 3.4623, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3261160680650673e-05, + "loss": 3.4507, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.325277473314015e-05, + "loss": 3.4538, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3244388785629633e-05, + "loss": 3.4651, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3236002838119113e-05, + "loss": 3.4438, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3227633269412325e-05, + "loss": 3.4429, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.32192473219018e-05, + "loss": 3.4618, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321086137439128e-05, + "loss": 3.4591, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.320247542688076e-05, + "loss": 3.4464, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3194105858173974e-05, + "loss": 3.4588, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185719910663454e-05, + "loss": 3.4413, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3177333963152934e-05, + "loss": 3.4497, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168948015642414e-05, + "loss": 3.4621, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3160578446935623e-05, + "loss": 3.4557, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3152192499425103e-05, + "loss": 3.4647, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3143806551914586e-05, + "loss": 3.4616, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3135420604404066e-05, + "loss": 3.47, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3127051035697275e-05, + "loss": 3.4448, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118665088186755e-05, + "loss": 3.4605, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3110279140676235e-05, + "loss": 3.4605, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101909571969448e-05, + "loss": 3.4413, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3093523624458928e-05, + "loss": 3.4627, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3085137676948408e-05, + "loss": 3.4591, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076751729437888e-05, + "loss": 3.4602, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3068382160731097e-05, + "loss": 3.4601, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059996213220577e-05, + "loss": 3.4471, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051610265710057e-05, + "loss": 3.4475, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304322431819954e-05, + "loss": 3.4569, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303485474949275e-05, + "loss": 3.4646, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.302646880198223e-05, + "loss": 3.4564, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.301808285447171e-05, + "loss": 3.4658, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.300969690696119e-05, + "loss": 3.4667, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.30013273382544e-05, + "loss": 3.4508, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299294139074388e-05, + "loss": 3.4596, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298455544323336e-05, + "loss": 3.4505, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.297616949572284e-05, + "loss": 3.4612, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.296779992701605e-05, + "loss": 3.4727, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.295941397950553e-05, + "loss": 3.4499, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.295102803199501e-05, + "loss": 3.4506, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.294264208448449e-05, + "loss": 3.451, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2934272515777703e-05, + "loss": 3.4607, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925886568267183e-05, + "loss": 3.4711, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2917500620756663e-05, + "loss": 3.4526, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2909114673246143e-05, + "loss": 3.4522, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900745104539352e-05, + "loss": 3.4466, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2892359157028835e-05, + "loss": 3.467, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883973209518315e-05, + "loss": 3.4404, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875587262007795e-05, + "loss": 3.4548, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2867217693301004e-05, + "loss": 3.4561, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2858831745790484e-05, + "loss": 3.4589, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2850445798279964e-05, + "loss": 3.451, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2842059850769444e-05, + "loss": 3.46, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833690282062656e-05, + "loss": 3.4581, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2825304334552136e-05, + "loss": 3.4536, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816918387041616e-05, + "loss": 3.4579, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2808532439531096e-05, + "loss": 3.4554, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2800162870824305e-05, + "loss": 3.4651, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279177692331379e-05, + "loss": 3.4659, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278339097580327e-05, + "loss": 3.4539, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277500502829275e-05, + "loss": 3.4509, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766635459585958e-05, + "loss": 3.4577, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2758249512075438e-05, + "loss": 3.4571, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749863564564918e-05, + "loss": 3.4444, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2741477617054398e-05, + "loss": 3.4557, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273310804834761e-05, + "loss": 3.4466, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.272472210083709e-05, + "loss": 3.4582, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.271633615332657e-05, + "loss": 3.4524, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707950205816047e-05, + "loss": 3.4558, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.269958063710926e-05, + "loss": 3.4471, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2691194689598742e-05, + "loss": 3.4491, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682808742088222e-05, + "loss": 3.4557, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.26744227945777e-05, + "loss": 3.4604, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.266605322587091e-05, + "loss": 3.4521, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.265766727836039e-05, + "loss": 3.4611, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.264928133084987e-05, + "loss": 3.4492, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.264089538333935e-05, + "loss": 3.4585, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632525814632564e-05, + "loss": 3.4647, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2624139867122044e-05, + "loss": 3.4602, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261575391961152e-05, + "loss": 3.4603, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2607384350904733e-05, + "loss": 3.466, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598998403394213e-05, + "loss": 3.4523, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590612455883696e-05, + "loss": 3.4659, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2582226508373173e-05, + "loss": 3.444, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573856939666385e-05, + "loss": 3.4587, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2565470992155865e-05, + "loss": 3.4537, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255708504464534e-05, + "loss": 3.4502, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548699097134825e-05, + "loss": 3.4552, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2540329528428037e-05, + "loss": 3.4482, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531943580917517e-05, + "loss": 3.4634, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523557633406994e-05, + "loss": 3.4378, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2515171685896474e-05, + "loss": 3.4648, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8558437824249268, + "eval_runtime": 305.3408, + "eval_samples_per_second": 1249.722, + "eval_steps_per_second": 39.055, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2506802117189686e-05, + "loss": 3.4471, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2498416169679166e-05, + "loss": 3.4468, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2490030222168646e-05, + "loss": 3.4561, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481644274658126e-05, + "loss": 3.4589, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.247327470595134e-05, + "loss": 3.4588, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464888758440815e-05, + "loss": 3.4482, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2456502810930295e-05, + "loss": 3.4426, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2448116863419775e-05, + "loss": 3.4507, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243974729471299e-05, + "loss": 3.4538, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2431361347202468e-05, + "loss": 3.4595, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422975399691948e-05, + "loss": 3.4513, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2414589452181428e-05, + "loss": 3.454, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.240621988347464e-05, + "loss": 3.445, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239783393596412e-05, + "loss": 3.4419, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.23894479884536e-05, + "loss": 3.4522, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.238106204094308e-05, + "loss": 3.4418, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237269247223629e-05, + "loss": 3.4455, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.236430652472577e-05, + "loss": 3.4529, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.235592057721525e-05, + "loss": 3.4426, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.234753462970473e-05, + "loss": 3.4696, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233916506099794e-05, + "loss": 3.4584, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.233077911348742e-05, + "loss": 3.4484, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.23223931659769e-05, + "loss": 3.4561, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231400721846638e-05, + "loss": 3.4625, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.230563764975959e-05, + "loss": 3.442, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2297251702249074e-05, + "loss": 3.4565, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288865754738554e-05, + "loss": 3.4497, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2280479807228034e-05, + "loss": 3.4479, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2272110238521243e-05, + "loss": 3.4419, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263724291010723e-05, + "loss": 3.4533, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2255338343500203e-05, + "loss": 3.4647, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246952395989683e-05, + "loss": 3.4539, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238582827282895e-05, + "loss": 3.4621, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2230196879772375e-05, + "loss": 3.455, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221810932261855e-05, + "loss": 3.4469, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2213424984751335e-05, + "loss": 3.4546, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2205055416044544e-05, + "loss": 3.4497, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2196669468534027e-05, + "loss": 3.4461, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2188283521023507e-05, + "loss": 3.4422, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179897573512987e-05, + "loss": 3.4446, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171528004806196e-05, + "loss": 3.4496, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2163142057295676e-05, + "loss": 3.4566, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2154756109785156e-05, + "loss": 3.4519, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214638654107837e-05, + "loss": 3.4484, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213800059356785e-05, + "loss": 3.4539, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.212961464605733e-05, + "loss": 3.4483, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.212122869854681e-05, + "loss": 3.4531, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112859129840018e-05, + "loss": 3.4458, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2104473182329498e-05, + "loss": 3.4314, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209608723481898e-05, + "loss": 3.4566, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208770128730846e-05, + "loss": 3.4458, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.207933171860167e-05, + "loss": 3.4558, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.207094577109115e-05, + "loss": 3.4421, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.206255982358063e-05, + "loss": 3.4446, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.205417387607011e-05, + "loss": 3.4358, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045820686167055e-05, + "loss": 3.4536, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203743473865653e-05, + "loss": 3.4411, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.202904879114601e-05, + "loss": 3.4475, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.202066284363549e-05, + "loss": 3.4563, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.201227689612497e-05, + "loss": 3.4356, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.200389094861445e-05, + "loss": 3.441, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1995505001103935e-05, + "loss": 3.4592, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1987119053593415e-05, + "loss": 3.4283, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1978749484886624e-05, + "loss": 3.4339, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1970363537376104e-05, + "loss": 3.4472, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961977589865584e-05, + "loss": 3.4504, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1953591642355064e-05, + "loss": 3.4375, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1945222073648276e-05, + "loss": 3.4494, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936836126137756e-05, + "loss": 3.4331, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928450178627236e-05, + "loss": 3.4365, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1920064231116713e-05, + "loss": 3.4519, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911694662409925e-05, + "loss": 3.4438, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1903308714899405e-05, + "loss": 3.4523, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.189492276738889e-05, + "loss": 3.4515, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1886536819878365e-05, + "loss": 3.4566, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1878167251171577e-05, + "loss": 3.4369, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869781303661057e-05, + "loss": 3.447, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1861395356150537e-05, + "loss": 3.449, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1853009408640014e-05, + "loss": 3.4327, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.184463983993323e-05, + "loss": 3.452, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.183625389242271e-05, + "loss": 3.4489, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827867944912186e-05, + "loss": 3.4498, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1819481997401666e-05, + "loss": 3.4476, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.181111242869488e-05, + "loss": 3.4382, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180272648118436e-05, + "loss": 3.4363, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179434053367384e-05, + "loss": 3.4489, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.178595458616332e-05, + "loss": 3.4479, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.177758501745653e-05, + "loss": 3.4478, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.176919906994601e-05, + "loss": 3.4537, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760813122435488e-05, + "loss": 3.4555, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1752427174924968e-05, + "loss": 3.4412, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1744057606218183e-05, + "loss": 3.4478, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173567165870766e-05, + "loss": 3.4381, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172728571119714e-05, + "loss": 3.4535, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.171889976368662e-05, + "loss": 3.4565, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1710530194979832e-05, + "loss": 3.4407, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1702144247469312e-05, + "loss": 3.4412, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1693758299958792e-05, + "loss": 3.4387, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1685372352448272e-05, + "loss": 3.4486, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167700278374148e-05, + "loss": 3.458, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166861683623096e-05, + "loss": 3.443, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.166023088872044e-05, + "loss": 3.4442, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.165184494120992e-05, + "loss": 3.439, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1643475372503134e-05, + "loss": 3.4516, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1635089424992614e-05, + "loss": 3.4341, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1626703477482094e-05, + "loss": 3.4464, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1618317529971574e-05, + "loss": 3.4368, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1609947961264783e-05, + "loss": 3.4525, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1601562013754266e-05, + "loss": 3.4394, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1593176066243746e-05, + "loss": 3.446, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584790118733226e-05, + "loss": 3.447, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1576420550026435e-05, + "loss": 3.4386, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1568034602515915e-05, + "loss": 3.4505, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559648655005395e-05, + "loss": 3.4454, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1551262707494875e-05, + "loss": 3.4534, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542893138788087e-05, + "loss": 3.4538, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1534507191277567e-05, + "loss": 3.4386, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1526121243767047e-05, + "loss": 3.4474, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517735296256527e-05, + "loss": 3.4413, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1509365727549736e-05, + "loss": 3.4482, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.150097978003922e-05, + "loss": 3.441, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.14925938325287e-05, + "loss": 3.4419, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.148422426382191e-05, + "loss": 3.4336, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.147583831631139e-05, + "loss": 3.4465, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.146745236880087e-05, + "loss": 3.4401, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.145906642129035e-05, + "loss": 3.4472, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.145069685258356e-05, + "loss": 3.4333, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.144231090507304e-05, + "loss": 3.4426, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143392495756252e-05, + "loss": 3.4426, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1425539010052e-05, + "loss": 3.4508, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.141716944134521e-05, + "loss": 3.4418, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140878349383469e-05, + "loss": 3.4515, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1400397546324173e-05, + "loss": 3.4339, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1392011598813653e-05, + "loss": 3.4487, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1383642030106862e-05, + "loss": 3.4506, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1375256082596342e-05, + "loss": 3.4489, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1366870135085822e-05, + "loss": 3.4478, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1358484187575302e-05, + "loss": 3.4559, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1350114618868515e-05, + "loss": 3.4435, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1341728671357995e-05, + "loss": 3.4567, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1333342723847475e-05, + "loss": 3.4338, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324956776336955e-05, + "loss": 3.449, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1316587207630164e-05, + "loss": 3.4419, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1308201260119644e-05, + "loss": 3.4409, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1299815312609127e-05, + "loss": 3.4408, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1291429365098607e-05, + "loss": 3.4354, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1283059796391816e-05, + "loss": 3.4497, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1274673848881296e-05, + "loss": 3.4298, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1266287901370776e-05, + "loss": 3.4547, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.8560590744018555, + "eval_runtime": 336.0974, + "eval_samples_per_second": 1135.358, + "eval_steps_per_second": 35.481, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257901953860256e-05, + "loss": 3.4395, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1249516006349736e-05, + "loss": 3.4348, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1241130058839216e-05, + "loss": 3.4423, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232744111328696e-05, + "loss": 3.448, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.122437454262191e-05, + "loss": 3.4449, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215988595111385e-05, + "loss": 3.4409, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207602647600865e-05, + "loss": 3.4363, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1199216700090345e-05, + "loss": 3.4363, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190847131383557e-05, + "loss": 3.4446, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1182461183873037e-05, + "loss": 3.4484, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1174075236362517e-05, + "loss": 3.4415, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165689288851997e-05, + "loss": 3.4403, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1157319720145206e-05, + "loss": 3.4392, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114893377263469e-05, + "loss": 3.4303, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.114054782512417e-05, + "loss": 3.4387, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.113216187761365e-05, + "loss": 3.4306, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.112379230890686e-05, + "loss": 3.4385, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111540636139634e-05, + "loss": 3.4391, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110702041388582e-05, + "loss": 3.4323, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.10986344663753e-05, + "loss": 3.4569, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.109026489766851e-05, + "loss": 3.4508, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108187895015799e-05, + "loss": 3.4359, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107349300264747e-05, + "loss": 3.4438, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106510705513695e-05, + "loss": 3.4498, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.105673748643016e-05, + "loss": 3.4329, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1048351538919643e-05, + "loss": 3.4455, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039965591409123e-05, + "loss": 3.4405, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031579643898603e-05, + "loss": 3.4355, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1023210075191812e-05, + "loss": 3.4318, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1014824127681292e-05, + "loss": 3.4459, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1006438180170772e-05, + "loss": 3.4508, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0998068611463985e-05, + "loss": 3.4453, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989682663953465e-05, + "loss": 3.4515, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0981296716442945e-05, + "loss": 3.4404, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972910768932425e-05, + "loss": 3.4365, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0964541200225634e-05, + "loss": 3.4455, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0956155252715114e-05, + "loss": 3.4394, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947769305204597e-05, + "loss": 3.4314, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0939383357694077e-05, + "loss": 3.4329, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0931013788987286e-05, + "loss": 3.4359, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922627841476766e-05, + "loss": 3.437, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0914241893966246e-05, + "loss": 3.4441, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905855946455726e-05, + "loss": 3.4418, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089748637774894e-05, + "loss": 3.4369, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0889100430238418e-05, + "loss": 3.4434, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880714482727898e-05, + "loss": 3.4405, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0872328535217378e-05, + "loss": 3.4432, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863958966510587e-05, + "loss": 3.4375, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0855573019000067e-05, + "loss": 3.4163, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084718707148955e-05, + "loss": 3.4502, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.083880112397903e-05, + "loss": 3.433, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.083043155527224e-05, + "loss": 3.4457, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.082204560776172e-05, + "loss": 3.4306, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.08136596602512e-05, + "loss": 3.4363, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.080527371274068e-05, + "loss": 3.4263, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796904144033892e-05, + "loss": 3.441, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0788518196523372e-05, + "loss": 3.4314, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0780132249012852e-05, + "loss": 3.4342, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771746301502332e-05, + "loss": 3.444, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.076337673279554e-05, + "loss": 3.4273, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.075499078528502e-05, + "loss": 3.4285, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746604837774504e-05, + "loss": 3.4458, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073821889026398e-05, + "loss": 3.4206, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729849321557193e-05, + "loss": 3.422, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0721463374046673e-05, + "loss": 3.4388, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0713077426536153e-05, + "loss": 3.4366, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.070469147902563e-05, + "loss": 3.43, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0696321910318846e-05, + "loss": 3.4362, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687935962808326e-05, + "loss": 3.42, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679550015297806e-05, + "loss": 3.4306, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0671164067787282e-05, + "loss": 3.4409, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662794499080495e-05, + "loss": 3.4326, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0654408551569975e-05, + "loss": 3.4436, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0646022604059455e-05, + "loss": 3.4392, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637636656548934e-05, + "loss": 3.445, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0629267087842147e-05, + "loss": 3.4252, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620881140331627e-05, + "loss": 3.4407, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0612495192821104e-05, + "loss": 3.4355, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0604109245310583e-05, + "loss": 3.4228, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.05957396766038e-05, + "loss": 3.44, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.058735372909328e-05, + "loss": 3.4404, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578967781582756e-05, + "loss": 3.439, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570581834072236e-05, + "loss": 3.4419, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0562212265365448e-05, + "loss": 3.4242, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553826317854928e-05, + "loss": 3.4248, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0545440370344408e-05, + "loss": 3.4372, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0537054422833888e-05, + "loss": 3.4377, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.05286848541271e-05, + "loss": 3.4386, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0520298906616577e-05, + "loss": 3.4384, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511912959106057e-05, + "loss": 3.4442, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0503527011595537e-05, + "loss": 3.4373, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0495157442888753e-05, + "loss": 3.4346, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.048677149537823e-05, + "loss": 3.4291, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.047838554786771e-05, + "loss": 3.4417, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046999960035719e-05, + "loss": 3.444, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.04616300316504e-05, + "loss": 3.4335, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0453244084139882e-05, + "loss": 3.427, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444858136629362e-05, + "loss": 3.4307, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0436472189118842e-05, + "loss": 3.4351, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042810262041205e-05, + "loss": 3.4523, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041971667290153e-05, + "loss": 3.4294, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.041133072539101e-05, + "loss": 3.4348, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402961156684223e-05, + "loss": 3.4283, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0394575209173703e-05, + "loss": 3.437, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0386189261663183e-05, + "loss": 3.4257, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0377803314152663e-05, + "loss": 3.4363, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0369433745445872e-05, + "loss": 3.4249, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0361047797935352e-05, + "loss": 3.4419, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352661850424836e-05, + "loss": 3.4327, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0344275902914316e-05, + "loss": 3.4343, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335906334207525e-05, + "loss": 3.435, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0327520386697005e-05, + "loss": 3.4359, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0319134439186485e-05, + "loss": 3.4356, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310748491675965e-05, + "loss": 3.4343, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0302378922969177e-05, + "loss": 3.4396, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293992975458657e-05, + "loss": 3.4475, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285607027948137e-05, + "loss": 3.4306, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0277221080437617e-05, + "loss": 3.4383, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268851511730826e-05, + "loss": 3.4316, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0260465564220306e-05, + "loss": 3.4322, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025207961670979e-05, + "loss": 3.4297, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024369366919927e-05, + "loss": 3.4323, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023532410049248e-05, + "loss": 3.4258, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226938152981958e-05, + "loss": 3.432, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0218552205471438e-05, + "loss": 3.4345, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0210166257960918e-05, + "loss": 3.434, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.020179668925413e-05, + "loss": 3.4205, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.019341074174361e-05, + "loss": 3.4354, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.018502479423309e-05, + "loss": 3.43, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.017663884672257e-05, + "loss": 3.4404, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016826927801578e-05, + "loss": 3.4335, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015988333050526e-05, + "loss": 3.4391, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.015149738299474e-05, + "loss": 3.4237, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0143111435484223e-05, + "loss": 3.4421, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134741866777432e-05, + "loss": 3.4385, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0126355919266912e-05, + "loss": 3.4393, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117969971756392e-05, + "loss": 3.4395, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0109584024245872e-05, + "loss": 3.4417, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0101214455539084e-05, + "loss": 3.4336, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092828508028564e-05, + "loss": 3.4441, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0084442560518044e-05, + "loss": 3.4239, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0076056613007524e-05, + "loss": 3.4386, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067687044300733e-05, + "loss": 3.4292, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0059301096790213e-05, + "loss": 3.4356, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050915149279693e-05, + "loss": 3.4264, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0042529201769177e-05, + "loss": 3.4273, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0034159633062386e-05, + "loss": 3.4357, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025773685551866e-05, + "loss": 3.4218, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0017387738041346e-05, + "loss": 3.4429, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8579628467559814, + "eval_runtime": 318.9932, + "eval_samples_per_second": 1196.236, + "eval_steps_per_second": 37.383, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0009001790530822e-05, + "loss": 3.4236, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.0000632221824038e-05, + "loss": 3.4255, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9992246274313518e-05, + "loss": 3.4283, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983860326802998e-05, + "loss": 3.4376, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9975474379292474e-05, + "loss": 3.4365, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9967104810585687e-05, + "loss": 3.4285, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9958718863075167e-05, + "loss": 3.433, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9950332915564647e-05, + "loss": 3.4252, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941946968054127e-05, + "loss": 3.4288, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993357739934734e-05, + "loss": 3.4421, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992519145183682e-05, + "loss": 3.429, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916805504326296e-05, + "loss": 3.4303, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990843593561951e-05, + "loss": 3.4272, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.990004998810899e-05, + "loss": 3.4199, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989166404059847e-05, + "loss": 3.4319, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9883278093087948e-05, + "loss": 3.4197, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874892145577428e-05, + "loss": 3.4273, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9866506198066908e-05, + "loss": 3.4328, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9858120250556388e-05, + "loss": 3.4184, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9849734303045868e-05, + "loss": 3.4442, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.984136473433908e-05, + "loss": 3.4435, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.983297878682856e-05, + "loss": 3.4283, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.982459283931804e-05, + "loss": 3.4297, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981620689180752e-05, + "loss": 3.4391, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.980783732310073e-05, + "loss": 3.427, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9799451375590213e-05, + "loss": 3.431, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9791065428079693e-05, + "loss": 3.4301, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9782679480569173e-05, + "loss": 3.4269, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9774309911862382e-05, + "loss": 3.4234, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765923964351862e-05, + "loss": 3.432, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9757538016841342e-05, + "loss": 3.4357, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.974915206933082e-05, + "loss": 3.4405, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740782500624034e-05, + "loss": 3.4395, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9732396553113514e-05, + "loss": 3.43, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9724010605602994e-05, + "loss": 3.4247, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9715624658092474e-05, + "loss": 3.4351, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9707255089385683e-05, + "loss": 3.4299, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698869141875163e-05, + "loss": 3.4218, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9690483194364646e-05, + "loss": 3.4229, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9682097246854126e-05, + "loss": 3.4213, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673727678147335e-05, + "loss": 3.4246, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9665341730636815e-05, + "loss": 3.4332, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656955783126295e-05, + "loss": 3.4341, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9648586214419508e-05, + "loss": 3.4311, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9640200266908988e-05, + "loss": 3.429, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631814319398468e-05, + "loss": 3.4305, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9623428371887948e-05, + "loss": 3.4266, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9615058803181157e-05, + "loss": 3.4287, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9606672855670637e-05, + "loss": 3.4053, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9598286908160117e-05, + "loss": 3.4394, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.95899009606496e-05, + "loss": 3.4247, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.958153139194281e-05, + "loss": 3.4379, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.957314544443229e-05, + "loss": 3.4216, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.956475949692177e-05, + "loss": 3.4215, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9556373549411246e-05, + "loss": 3.4165, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954802035950819e-05, + "loss": 3.43, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953963441199767e-05, + "loss": 3.4242, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953124846448715e-05, + "loss": 3.4235, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.952286251697663e-05, + "loss": 3.4328, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.951447656946611e-05, + "loss": 3.4215, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.950609062195559e-05, + "loss": 3.4151, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949770467444507e-05, + "loss": 3.4355, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948931872693455e-05, + "loss": 3.4112, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480949158227763e-05, + "loss": 3.4099, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9472563210717243e-05, + "loss": 3.4293, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.946417726320672e-05, + "loss": 3.4267, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.94557913156962e-05, + "loss": 3.4199, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9447421746989415e-05, + "loss": 3.4254, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9439035799478895e-05, + "loss": 3.4104, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9430649851968372e-05, + "loss": 3.4189, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.942226390445785e-05, + "loss": 3.431, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413894335751064e-05, + "loss": 3.42, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9405508388240544e-05, + "loss": 3.4338, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9397122440730024e-05, + "loss": 3.4258, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388736493219504e-05, + "loss": 3.4345, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9380366924512717e-05, + "loss": 3.4158, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371980977002193e-05, + "loss": 3.4309, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9363595029491673e-05, + "loss": 3.4233, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9355209081981153e-05, + "loss": 3.4154, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934683951327437e-05, + "loss": 3.4285, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9338453565763845e-05, + "loss": 3.4309, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9330067618253325e-05, + "loss": 3.4245, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321681670742805e-05, + "loss": 3.4356, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9313312102036018e-05, + "loss": 3.4114, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304926154525498e-05, + "loss": 3.413, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9296540207014978e-05, + "loss": 3.4289, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9288154259504458e-05, + "loss": 3.4278, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279784690797667e-05, + "loss": 3.4299, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9271398743287147e-05, + "loss": 3.432, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9263012795776627e-05, + "loss": 3.4295, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9254626848266107e-05, + "loss": 3.4285, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924625727955932e-05, + "loss": 3.4238, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.92378713320488e-05, + "loss": 3.4173, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.922948538453828e-05, + "loss": 3.4345, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.922109943702776e-05, + "loss": 3.429, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212729868320968e-05, + "loss": 3.4272, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9204343920810448e-05, + "loss": 3.4184, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.919595797329993e-05, + "loss": 3.4193, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.918757202578941e-05, + "loss": 3.4214, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.917920245708262e-05, + "loss": 3.4396, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.91708165095721e-05, + "loss": 3.422, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.916243056206158e-05, + "loss": 3.424, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.915404461455106e-05, + "loss": 3.4163, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145675045844273e-05, + "loss": 3.4231, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9137289098333753e-05, + "loss": 3.422, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9128903150823233e-05, + "loss": 3.421, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9120517203312713e-05, + "loss": 3.4142, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9112147634605922e-05, + "loss": 3.4314, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103761687095402e-05, + "loss": 3.4228, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9095375739584885e-05, + "loss": 3.4222, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086989792074365e-05, + "loss": 3.4188, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9078620223367574e-05, + "loss": 3.4276, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9070234275857054e-05, + "loss": 3.4254, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061848328346534e-05, + "loss": 3.4248, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9053462380836014e-05, + "loss": 3.43, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9045092812129226e-05, + "loss": 3.4351, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036706864618706e-05, + "loss": 3.4192, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9028320917108186e-05, + "loss": 3.4276, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019934969597666e-05, + "loss": 3.4172, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9011565400890875e-05, + "loss": 3.4245, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9003179453380355e-05, + "loss": 3.4198, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.899479350586984e-05, + "loss": 3.4178, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898640755835932e-05, + "loss": 3.4181, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8978037989652528e-05, + "loss": 3.4239, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8969652042142008e-05, + "loss": 3.4248, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8961266094631488e-05, + "loss": 3.4225, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8952880147120968e-05, + "loss": 3.413, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894451057841418e-05, + "loss": 3.4221, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.893612463090366e-05, + "loss": 3.4171, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.892773868339314e-05, + "loss": 3.4298, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8919352735882617e-05, + "loss": 3.425, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.891098316717583e-05, + "loss": 3.4256, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.890259721966531e-05, + "loss": 3.4145, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8894211272154792e-05, + "loss": 3.4316, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.888582532464427e-05, + "loss": 3.4282, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.887745575593748e-05, + "loss": 3.4287, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886906980842696e-05, + "loss": 3.4287, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.886068386091644e-05, + "loss": 3.43, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8852314292209654e-05, + "loss": 3.4252, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843928344699134e-05, + "loss": 3.4353, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8835542397188614e-05, + "loss": 3.4146, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882715644967809e-05, + "loss": 3.4272, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818786880971303e-05, + "loss": 3.4212, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8810400933460783e-05, + "loss": 3.4214, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8802014985950263e-05, + "loss": 3.4158, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793629038439743e-05, + "loss": 3.4184, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8785259469732955e-05, + "loss": 3.4247, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776873522222435e-05, + "loss": 3.418, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8768487574711915e-05, + "loss": 3.4308, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.859438896179199, + "eval_runtime": 315.903, + "eval_samples_per_second": 1207.937, + "eval_steps_per_second": 37.749, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.876010162720139e-05, + "loss": 3.4121, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.875171567969087e-05, + "loss": 3.4145, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8743329732180355e-05, + "loss": 3.4148, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734943784669835e-05, + "loss": 3.4309, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726574215963044e-05, + "loss": 3.4259, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8718188268452524e-05, + "loss": 3.4149, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709802320942004e-05, + "loss": 3.4229, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8701416373431484e-05, + "loss": 3.4158, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8693046804724696e-05, + "loss": 3.4154, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684660857214176e-05, + "loss": 3.4354, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8676274909703656e-05, + "loss": 3.4177, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667888962193136e-05, + "loss": 3.4175, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8659519393486345e-05, + "loss": 3.4266, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8651133445975825e-05, + "loss": 3.4063, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.864274749846531e-05, + "loss": 3.4219, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863436155095479e-05, + "loss": 3.4097, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625991982247998e-05, + "loss": 3.4205, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617606034737478e-05, + "loss": 3.4193, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8609220087226958e-05, + "loss": 3.4079, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600834139716438e-05, + "loss": 3.4311, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.859246457100965e-05, + "loss": 3.4322, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858407862349913e-05, + "loss": 3.421, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857569267598861e-05, + "loss": 3.423, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.856730672847809e-05, + "loss": 3.4222, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.85589371597713e-05, + "loss": 3.4211, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.855055121226078e-05, + "loss": 3.4163, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8542165264750262e-05, + "loss": 3.4232, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533779317239742e-05, + "loss": 3.4201, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852540974853295e-05, + "loss": 3.4122, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.851702380102243e-05, + "loss": 3.4195, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850863785351191e-05, + "loss": 3.4229, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.850025190600139e-05, + "loss": 3.4326, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491882337294604e-05, + "loss": 3.4286, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483496389784084e-05, + "loss": 3.4214, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8475110442273564e-05, + "loss": 3.4157, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466724494763044e-05, + "loss": 3.4184, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8458354926056253e-05, + "loss": 3.4241, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449968978545733e-05, + "loss": 3.4142, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441583031035216e-05, + "loss": 3.4132, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8433213462328425e-05, + "loss": 3.41, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424827514817905e-05, + "loss": 3.4181, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8416457946111114e-05, + "loss": 3.4168, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8408071998600594e-05, + "loss": 3.4233, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399686051090077e-05, + "loss": 3.4208, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8391300103579557e-05, + "loss": 3.4199, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382914156069037e-05, + "loss": 3.4156, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8374528208558514e-05, + "loss": 3.415, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8366142261047994e-05, + "loss": 3.4246, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357756313537474e-05, + "loss": 3.3916, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8349386744830686e-05, + "loss": 3.4242, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8341000797320166e-05, + "loss": 3.4159, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332614849809646e-05, + "loss": 3.4276, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8324228902299126e-05, + "loss": 3.4132, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831585933359234e-05, + "loss": 3.4114, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8307473386081815e-05, + "loss": 3.4029, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8299087438571295e-05, + "loss": 3.4164, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.829070149106078e-05, + "loss": 3.4189, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8282331922353988e-05, + "loss": 3.409, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273945974843468e-05, + "loss": 3.4239, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265560027332948e-05, + "loss": 3.4148, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8257174079822427e-05, + "loss": 3.3993, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824880451111564e-05, + "loss": 3.4281, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.824041856360512e-05, + "loss": 3.4038, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.82320326160946e-05, + "loss": 3.3997, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.822364666858408e-05, + "loss": 3.4167, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821527709987729e-05, + "loss": 3.4161, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.820689115236677e-05, + "loss": 3.4018, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819850520485625e-05, + "loss": 3.4217, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.819013563614946e-05, + "loss": 3.4014, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.818174968863894e-05, + "loss": 3.405, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.817336374112842e-05, + "loss": 3.4216, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.81649777936179e-05, + "loss": 3.4086, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815660822491111e-05, + "loss": 3.4251, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8148222277400594e-05, + "loss": 3.4106, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139836329890074e-05, + "loss": 3.4241, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8131450382379554e-05, + "loss": 3.4101, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8123080813672763e-05, + "loss": 3.4244, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114694866162243e-05, + "loss": 3.4072, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8106308918651723e-05, + "loss": 3.4105, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097922971141202e-05, + "loss": 3.4148, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089553402434415e-05, + "loss": 3.4185, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8081167454923895e-05, + "loss": 3.4153, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072781507413375e-05, + "loss": 3.4262, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8064395559902855e-05, + "loss": 3.4013, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8056025991196064e-05, + "loss": 3.403, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8047640043685547e-05, + "loss": 3.4183, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8039254096175027e-05, + "loss": 3.419, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030868148664507e-05, + "loss": 3.4158, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8022498579957716e-05, + "loss": 3.4214, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8014112632447196e-05, + "loss": 3.4178, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005726684936676e-05, + "loss": 3.4195, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7997340737426156e-05, + "loss": 3.4173, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.798897116871937e-05, + "loss": 3.4075, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.798058522120885e-05, + "loss": 3.4216, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.797219927369833e-05, + "loss": 3.4206, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796381332618781e-05, + "loss": 3.4144, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7955443757481018e-05, + "loss": 3.411, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.79470578099705e-05, + "loss": 3.4026, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793867186245998e-05, + "loss": 3.4139, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.793028591494946e-05, + "loss": 3.427, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.792191634624267e-05, + "loss": 3.4115, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.791353039873215e-05, + "loss": 3.4162, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.790514445122163e-05, + "loss": 3.4069, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.789675850371111e-05, + "loss": 3.4097, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7888388935004322e-05, + "loss": 3.4161, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7880002987493802e-05, + "loss": 3.4068, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7871617039983282e-05, + "loss": 3.4047, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7863231092472762e-05, + "loss": 3.421, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785486152376597e-05, + "loss": 3.419, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7846475576255455e-05, + "loss": 3.4062, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7838089628744935e-05, + "loss": 3.4141, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829703681234415e-05, + "loss": 3.4117, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7821334112527624e-05, + "loss": 3.4213, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812948165017104e-05, + "loss": 3.4102, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804562217506584e-05, + "loss": 3.4212, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7796176269996063e-05, + "loss": 3.425, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787806701289276e-05, + "loss": 3.4063, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7779420753778756e-05, + "loss": 3.4183, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7771034806268236e-05, + "loss": 3.4105, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762648858757712e-05, + "loss": 3.4161, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7754279290050925e-05, + "loss": 3.4125, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745893342540408e-05, + "loss": 3.4084, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7737507395029885e-05, + "loss": 3.4067, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7729121447519365e-05, + "loss": 3.4154, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720751878812577e-05, + "loss": 3.4148, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7712365931302057e-05, + "loss": 3.4147, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703979983791534e-05, + "loss": 3.4029, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7695594036281017e-05, + "loss": 3.4079, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.768722446757423e-05, + "loss": 3.4086, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767883852006371e-05, + "loss": 3.4177, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7670452572553186e-05, + "loss": 3.4156, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7662066625042666e-05, + "loss": 3.4153, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.765369705633588e-05, + "loss": 3.402, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.764531110882536e-05, + "loss": 3.4256, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.763692516131484e-05, + "loss": 3.4139, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762853921380432e-05, + "loss": 3.4214, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.762016964509753e-05, + "loss": 3.4129, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611783697587008e-05, + "loss": 3.4193, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7603397750076487e-05, + "loss": 3.415, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759501180256597e-05, + "loss": 3.4297, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7586642233859183e-05, + "loss": 3.4017, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757825628634866e-05, + "loss": 3.4196, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.756987033883814e-05, + "loss": 3.4102, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.756148439132762e-05, + "loss": 3.4101, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7553114822620832e-05, + "loss": 3.4072, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544728875110312e-05, + "loss": 3.4071, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7536342927599792e-05, + "loss": 3.4107, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527956980089272e-05, + "loss": 3.4112, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.751958741138248e-05, + "loss": 3.4165, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8601906299591064, + "eval_runtime": 306.121, + "eval_samples_per_second": 1246.536, + "eval_steps_per_second": 38.955, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.751120146387196e-05, + "loss": 3.4057, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.750281551636144e-05, + "loss": 3.4062, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7494445947654657e-05, + "loss": 3.405, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7486060000144134e-05, + "loss": 3.4195, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477674052633614e-05, + "loss": 3.42, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7469288105123093e-05, + "loss": 3.4033, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460918536416303e-05, + "loss": 3.4109, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7452532588905786e-05, + "loss": 3.4066, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7444146641395266e-05, + "loss": 3.4081, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435760693884746e-05, + "loss": 3.4202, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7427391125177955e-05, + "loss": 3.4072, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7419005177667435e-05, + "loss": 3.4098, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7410619230156915e-05, + "loss": 3.4155, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7402233282646395e-05, + "loss": 3.3964, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393863713939607e-05, + "loss": 3.4069, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7385477766429087e-05, + "loss": 3.396, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7377091818918567e-05, + "loss": 3.4087, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368705871408047e-05, + "loss": 3.4109, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7360336302701256e-05, + "loss": 3.3986, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735195035519074e-05, + "loss": 3.4192, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734356440768022e-05, + "loss": 3.4226, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.73351784601697e-05, + "loss": 3.4123, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.732680889146291e-05, + "loss": 3.411, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.731842294395239e-05, + "loss": 3.4125, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.731003699644187e-05, + "loss": 3.413, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.730165104893135e-05, + "loss": 3.4069, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.729328148022456e-05, + "loss": 3.4095, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728489553271404e-05, + "loss": 3.4129, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727650958520352e-05, + "loss": 3.4001, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7268123637693e-05, + "loss": 3.4083, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.725975406898621e-05, + "loss": 3.4145, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7251368121475693e-05, + "loss": 3.4155, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242982173965173e-05, + "loss": 3.4239, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7234596226454653e-05, + "loss": 3.4094, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7226226657747862e-05, + "loss": 3.4064, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217840710237342e-05, + "loss": 3.4083, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7209454762726822e-05, + "loss": 3.4143, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7201068815216302e-05, + "loss": 3.4019, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192699246509515e-05, + "loss": 3.4029, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7184313298998995e-05, + "loss": 3.4038, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7175927351488475e-05, + "loss": 3.4035, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7167541403977954e-05, + "loss": 3.4105, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7159171835271164e-05, + "loss": 3.4125, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150785887760647e-05, + "loss": 3.4113, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7142399940250127e-05, + "loss": 3.4041, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7134013992739607e-05, + "loss": 3.4121, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125644424032816e-05, + "loss": 3.4044, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7117258476522296e-05, + "loss": 3.4151, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108872529011776e-05, + "loss": 3.3858, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7100486581501256e-05, + "loss": 3.4125, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7092117012794468e-05, + "loss": 3.406, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7083731065283948e-05, + "loss": 3.4187, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7075345117773428e-05, + "loss": 3.401, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066959170262905e-05, + "loss": 3.4022, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7058589601556117e-05, + "loss": 3.3967, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.70502036540456e-05, + "loss": 3.404, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.704183408533881e-05, + "loss": 3.4133, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703344813782829e-05, + "loss": 3.393, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702506219031777e-05, + "loss": 3.4169, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.701667624280725e-05, + "loss": 3.4037, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7008290295296726e-05, + "loss": 3.3867, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.699990434778621e-05, + "loss": 3.417, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.699151840027569e-05, + "loss": 3.397, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6983148831568902e-05, + "loss": 3.3882, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.697476288405838e-05, + "loss": 3.4063, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.696637693654786e-05, + "loss": 3.4052, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.695799098903734e-05, + "loss": 3.3935, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694962142033055e-05, + "loss": 3.4113, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.694123547282003e-05, + "loss": 3.3891, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.693284952530951e-05, + "loss": 3.3946, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692446357779899e-05, + "loss": 3.4095, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.69160940090922e-05, + "loss": 3.4027, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.690770806158168e-05, + "loss": 3.4125, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6899322114071163e-05, + "loss": 3.4029, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890936166560643e-05, + "loss": 3.4149, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6882566597853852e-05, + "loss": 3.3998, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6874180650343332e-05, + "loss": 3.4154, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865794702832812e-05, + "loss": 3.395, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6857408755322292e-05, + "loss": 3.3988, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6849039186615505e-05, + "loss": 3.4065, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840653239104985e-05, + "loss": 3.4055, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6832267291594464e-05, + "loss": 3.4066, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823881344083944e-05, + "loss": 3.4143, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6815511775377154e-05, + "loss": 3.3987, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6807125827866633e-05, + "loss": 3.391, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798739880356117e-05, + "loss": 3.4048, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6790353932845597e-05, + "loss": 3.4112, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781984364138806e-05, + "loss": 3.4024, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6773598416628286e-05, + "loss": 3.4121, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6765212469117766e-05, + "loss": 3.4107, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756826521607246e-05, + "loss": 3.4084, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6748456952900458e-05, + "loss": 3.404, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6740071005389938e-05, + "loss": 3.3983, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6731685057879418e-05, + "loss": 3.4094, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6723299110368898e-05, + "loss": 3.4091, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714929541662107e-05, + "loss": 3.4093, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6706543594151587e-05, + "loss": 3.3988, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669815764664107e-05, + "loss": 3.3939, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.668977169913055e-05, + "loss": 3.4025, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.668140213042376e-05, + "loss": 3.4161, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.667301618291324e-05, + "loss": 3.4022, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.666463023540272e-05, + "loss": 3.4061, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.66562442878922e-05, + "loss": 3.3988, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647874719185412e-05, + "loss": 3.3977, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6639488771674892e-05, + "loss": 3.4088, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6631102824164372e-05, + "loss": 3.3948, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6622716876653852e-05, + "loss": 3.3984, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.661434730794706e-05, + "loss": 3.4085, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.660596136043654e-05, + "loss": 3.409, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6597575412926024e-05, + "loss": 3.3997, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6589189465415504e-05, + "loss": 3.4011, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580819896708713e-05, + "loss": 3.3988, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6572433949198193e-05, + "loss": 3.4118, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6564048001687673e-05, + "loss": 3.3986, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6555662054177153e-05, + "loss": 3.4124, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6547292485470366e-05, + "loss": 3.4136, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538906537959846e-05, + "loss": 3.4015, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6530520590449325e-05, + "loss": 3.4036, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6522134642938802e-05, + "loss": 3.4036, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6513765074232015e-05, + "loss": 3.4024, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6505379126721494e-05, + "loss": 3.4056, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496993179210974e-05, + "loss": 3.3932, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488607231700454e-05, + "loss": 3.3957, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6480237662993667e-05, + "loss": 3.4016, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471851715483147e-05, + "loss": 3.4049, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6463482146776356e-05, + "loss": 3.4016, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6455096199265836e-05, + "loss": 3.3965, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.644671025175532e-05, + "loss": 3.3985, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.64383243042448e-05, + "loss": 3.395, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429938356734276e-05, + "loss": 3.4135, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6421552409223756e-05, + "loss": 3.4027, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6413166461713236e-05, + "loss": 3.4079, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6404780514202716e-05, + "loss": 3.3931, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6396410945495928e-05, + "loss": 3.414, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6388024997985408e-05, + "loss": 3.4021, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6379639050474888e-05, + "loss": 3.4133, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6371253102964368e-05, + "loss": 3.4102, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362883534257577e-05, + "loss": 3.4047, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6354497586747057e-05, + "loss": 3.4024, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.634611163923654e-05, + "loss": 3.4188, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.633772569172602e-05, + "loss": 3.392, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632935612301923e-05, + "loss": 3.4074, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.632097017550871e-05, + "loss": 3.4006, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.631258422799819e-05, + "loss": 3.4015, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.630419828048767e-05, + "loss": 3.398, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295828711780882e-05, + "loss": 3.3967, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6287442764270362e-05, + "loss": 3.3984, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627905681675984e-05, + "loss": 3.4065, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.627067086924932e-05, + "loss": 3.4017, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.862354040145874, + "eval_runtime": 305.8249, + "eval_samples_per_second": 1247.743, + "eval_steps_per_second": 38.993, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.626230130054253e-05, + "loss": 3.394, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625391535303201e-05, + "loss": 3.3916, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6245529405521494e-05, + "loss": 3.3953, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6237143458010974e-05, + "loss": 3.4113, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228773889304183e-05, + "loss": 3.409, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6220387941793663e-05, + "loss": 3.394, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6212001994283143e-05, + "loss": 3.4038, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6203616046772623e-05, + "loss": 3.3966, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6195246478065835e-05, + "loss": 3.3998, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186860530555315e-05, + "loss": 3.4057, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6178474583044795e-05, + "loss": 3.4022, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6170088635534275e-05, + "loss": 3.3982, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6161719066827484e-05, + "loss": 3.4058, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6153333119316964e-05, + "loss": 3.3882, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144947171806448e-05, + "loss": 3.3969, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6136561224295928e-05, + "loss": 3.3859, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6128191655589137e-05, + "loss": 3.4025, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119805708078617e-05, + "loss": 3.4026, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6111419760568097e-05, + "loss": 3.3833, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6103033813057577e-05, + "loss": 3.4104, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609466424435079e-05, + "loss": 3.4114, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608627829684027e-05, + "loss": 3.3995, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.607789234932975e-05, + "loss": 3.4018, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6069506401819226e-05, + "loss": 3.4027, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6061136833112438e-05, + "loss": 3.4024, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052750885601918e-05, + "loss": 3.3971, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6044364938091398e-05, + "loss": 3.3949, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035978990580878e-05, + "loss": 3.4021, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602760942187409e-05, + "loss": 3.3918, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601922347436357e-05, + "loss": 3.3994, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.601083752685305e-05, + "loss": 3.4058, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6002451579342527e-05, + "loss": 3.408, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5994082010635743e-05, + "loss": 3.4047, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5985696063125223e-05, + "loss": 3.4077, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.59773101156147e-05, + "loss": 3.3938, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596892416810418e-05, + "loss": 3.3995, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5960554599397392e-05, + "loss": 3.406, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.595216865188687e-05, + "loss": 3.3879, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594378270437635e-05, + "loss": 3.3978, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.593539675686583e-05, + "loss": 3.3966, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5927027188159044e-05, + "loss": 3.3936, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5918641240648524e-05, + "loss": 3.3968, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5910255293138e-05, + "loss": 3.4051, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.590186934562748e-05, + "loss": 3.3984, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5893499776920696e-05, + "loss": 3.3969, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5885113829410173e-05, + "loss": 3.4003, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876727881899653e-05, + "loss": 3.3919, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5868341934389133e-05, + "loss": 3.4038, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859972365682345e-05, + "loss": 3.3788, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5851586418171825e-05, + "loss": 3.4005, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5843200470661305e-05, + "loss": 3.3912, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834814523150785e-05, + "loss": 3.4041, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5826444954443998e-05, + "loss": 3.3913, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5818059006933474e-05, + "loss": 3.3913, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5809673059422954e-05, + "loss": 3.3882, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5801303490716167e-05, + "loss": 3.3952, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.579293392200938e-05, + "loss": 3.404, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.578454797449886e-05, + "loss": 3.3847, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577616202698834e-05, + "loss": 3.408, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.576777607947782e-05, + "loss": 3.3963, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5759390131967296e-05, + "loss": 3.3742, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575100418445678e-05, + "loss": 3.4051, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.574261823694626e-05, + "loss": 3.3857, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5734248668239468e-05, + "loss": 3.3817, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725862720728948e-05, + "loss": 3.393, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5717476773218428e-05, + "loss": 3.396, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5709090825707908e-05, + "loss": 3.3866, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.570072125700112e-05, + "loss": 3.4037, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.56923353094906e-05, + "loss": 3.3776, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568394936198008e-05, + "loss": 3.3841, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567556341446956e-05, + "loss": 3.3992, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.566719384576277e-05, + "loss": 3.3946, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565880789825225e-05, + "loss": 3.3981, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5650421950741733e-05, + "loss": 3.3968, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5642036003231213e-05, + "loss": 3.4003, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5633666434524422e-05, + "loss": 3.3927, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.56252804870139e-05, + "loss": 3.4063, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561689453950338e-05, + "loss": 3.3881, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560850859199286e-05, + "loss": 3.3874, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5600139023286074e-05, + "loss": 3.3922, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591753075775554e-05, + "loss": 3.3974, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5583367128265034e-05, + "loss": 3.3957, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574981180754514e-05, + "loss": 3.4038, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5566611612047723e-05, + "loss": 3.3891, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5558225664537203e-05, + "loss": 3.3791, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549839717026683e-05, + "loss": 3.3943, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5541453769516166e-05, + "loss": 3.4012, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5533084200809375e-05, + "loss": 3.391, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524698253298855e-05, + "loss": 3.4006, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5516312305788335e-05, + "loss": 3.4033, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507926358277815e-05, + "loss": 3.3976, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5499556789571028e-05, + "loss": 3.3958, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5491170842060508e-05, + "loss": 3.3872, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5482784894549988e-05, + "loss": 3.4017, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5474398947039468e-05, + "loss": 3.4006, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5466029378332677e-05, + "loss": 3.3979, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5457643430822157e-05, + "loss": 3.3928, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5449257483311637e-05, + "loss": 3.3846, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.544087153580112e-05, + "loss": 3.394, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.543250196709433e-05, + "loss": 3.4065, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.542411601958381e-05, + "loss": 3.3901, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541573007207329e-05, + "loss": 3.3958, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.540734412456277e-05, + "loss": 3.3889, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539897455585598e-05, + "loss": 3.3904, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.539058860834546e-05, + "loss": 3.3953, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.538220266083494e-05, + "loss": 3.3907, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.537381671332442e-05, + "loss": 3.3866, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.536544714461763e-05, + "loss": 3.3984, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.535706119710711e-05, + "loss": 3.3958, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534867524959659e-05, + "loss": 3.3873, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.534028930208607e-05, + "loss": 3.3939, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5331919733379283e-05, + "loss": 3.3865, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5323533785868763e-05, + "loss": 3.4039, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5315147838358243e-05, + "loss": 3.3906, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.530676189084772e-05, + "loss": 3.3999, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5298392322140935e-05, + "loss": 3.4019, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5290006374630415e-05, + "loss": 3.3909, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5281620427119895e-05, + "loss": 3.3957, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527323447960937e-05, + "loss": 3.3939, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5264864910902584e-05, + "loss": 3.3911, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5256478963392066e-05, + "loss": 3.3971, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5248093015881542e-05, + "loss": 3.386, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239707068371022e-05, + "loss": 3.3878, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5231337499664236e-05, + "loss": 3.394, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222951552153716e-05, + "loss": 3.3946, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5214565604643195e-05, + "loss": 3.3922, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5206179657132675e-05, + "loss": 3.3859, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197810088425887e-05, + "loss": 3.3854, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5189424140915367e-05, + "loss": 3.3874, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5181038193404845e-05, + "loss": 3.4008, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172652245894325e-05, + "loss": 3.3912, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5164282677187538e-05, + "loss": 3.4002, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155896729677016e-05, + "loss": 3.3811, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5147510782166496e-05, + "loss": 3.4017, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5139124834655976e-05, + "loss": 3.3939, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.513075526594919e-05, + "loss": 3.4009, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5122369318438667e-05, + "loss": 3.4009, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113983370928148e-05, + "loss": 3.3936, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105597423417628e-05, + "loss": 3.397, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5097227854710837e-05, + "loss": 3.4041, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088841907200319e-05, + "loss": 3.3849, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5080455959689799e-05, + "loss": 3.3954, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5072070012179279e-05, + "loss": 3.393, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.506370044347249e-05, + "loss": 3.3905, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.505531449596197e-05, + "loss": 3.3848, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.504692854845145e-05, + "loss": 3.3919, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.503854260094093e-05, + "loss": 3.3867, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.503017303223414e-05, + "loss": 3.3915, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.502178708472362e-05, + "loss": 3.3941, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8633487224578857, + "eval_runtime": 309.0062, + "eval_samples_per_second": 1234.898, + "eval_steps_per_second": 38.591, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5013401137213102e-05, + "loss": 3.3937, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5005015189702582e-05, + "loss": 3.3804, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4996645620995791e-05, + "loss": 3.3863, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4988259673485273e-05, + "loss": 3.3976, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979873725974753e-05, + "loss": 3.3941, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4971487778464233e-05, + "loss": 3.3867, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4963118209757443e-05, + "loss": 3.3967, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954732262246923e-05, + "loss": 3.3869, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4946346314736403e-05, + "loss": 3.3863, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937976746029614e-05, + "loss": 3.3935, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4929590798519094e-05, + "loss": 3.4001, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4921204851008574e-05, + "loss": 3.3873, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912818903498054e-05, + "loss": 3.3971, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4904449334791265e-05, + "loss": 3.3723, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4896063387280745e-05, + "loss": 3.387, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887677439770226e-05, + "loss": 3.3802, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4879291492259706e-05, + "loss": 3.3922, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870921923552917e-05, + "loss": 3.3916, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4862535976042397e-05, + "loss": 3.3763, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4854150028531877e-05, + "loss": 3.3967, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845764081021357e-05, + "loss": 3.4045, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4837394512314568e-05, + "loss": 3.3894, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4829008564804048e-05, + "loss": 3.3925, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820622617293528e-05, + "loss": 3.3928, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4812236669783008e-05, + "loss": 3.3955, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803867101076218e-05, + "loss": 3.3867, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4795481153565698e-05, + "loss": 3.3854, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.478709520605518e-05, + "loss": 3.3931, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.477870925854466e-05, + "loss": 3.3809, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4770339689837869e-05, + "loss": 3.3901, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.476195374232735e-05, + "loss": 3.398, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.475356779481683e-05, + "loss": 3.3956, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.474518184730631e-05, + "loss": 3.3935, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736812278599521e-05, + "loss": 3.4012, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4728426331089001e-05, + "loss": 3.3849, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4720040383578481e-05, + "loss": 3.3898, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711654436067961e-05, + "loss": 3.3934, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4703284867361172e-05, + "loss": 3.3786, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694898919850652e-05, + "loss": 3.3853, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4686512972340134e-05, + "loss": 3.3867, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4678127024829614e-05, + "loss": 3.3804, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669773834926557e-05, + "loss": 3.3853, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4661387887416034e-05, + "loss": 3.3968, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4653001939905513e-05, + "loss": 3.3908, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644615992394995e-05, + "loss": 3.3862, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4636230044884475e-05, + "loss": 3.3927, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627844097373955e-05, + "loss": 3.3795, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4619458149863435e-05, + "loss": 3.3907, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4611072202352913e-05, + "loss": 3.3747, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4602702633646126e-05, + "loss": 3.3868, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4594316686135606e-05, + "loss": 3.3833, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585930738625087e-05, + "loss": 3.3963, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4577544791114564e-05, + "loss": 3.3807, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4569175222407776e-05, + "loss": 3.3797, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560789274897258e-05, + "loss": 3.38, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4552403327386738e-05, + "loss": 3.3835, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4544033758679949e-05, + "loss": 3.3965, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535647811169429e-05, + "loss": 3.3702, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4527261863658909e-05, + "loss": 3.3983, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518875916148387e-05, + "loss": 3.3836, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4510489968637867e-05, + "loss": 3.3682, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4502104021127347e-05, + "loss": 3.3959, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493718073616827e-05, + "loss": 3.3737, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4485332126106307e-05, + "loss": 3.3715, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476962557399518e-05, + "loss": 3.3804, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4468576609888998e-05, + "loss": 3.3879, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4460190662378477e-05, + "loss": 3.3821, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4451821093671688e-05, + "loss": 3.3857, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4443435146161168e-05, + "loss": 3.3715, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.443504919865065e-05, + "loss": 3.3742, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.442666325114013e-05, + "loss": 3.3881, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.441829368243334e-05, + "loss": 3.3882, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.440990773492282e-05, + "loss": 3.3884, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.44015217874123e-05, + "loss": 3.3835, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.439313583990178e-05, + "loss": 3.3928, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384766271194991e-05, + "loss": 3.3834, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4376380323684471e-05, + "loss": 3.3911, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367994376173951e-05, + "loss": 3.3818, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359608428663431e-05, + "loss": 3.3801, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4351238859956642e-05, + "loss": 3.3852, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342852912446122e-05, + "loss": 3.3808, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4334466964935604e-05, + "loss": 3.3885, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4326081017425083e-05, + "loss": 3.3946, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317711448718293e-05, + "loss": 3.3841, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4309325501207774e-05, + "loss": 3.3643, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300939553697254e-05, + "loss": 3.3846, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4292553606186734e-05, + "loss": 3.3901, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4284184037479945e-05, + "loss": 3.3831, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275798089969425e-05, + "loss": 3.3926, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4267412142458905e-05, + "loss": 3.398, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4259026194948385e-05, + "loss": 3.3852, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250656626241596e-05, + "loss": 3.3861, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4242270678731076e-05, + "loss": 3.3791, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233884731220557e-05, + "loss": 3.3917, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4225498783710037e-05, + "loss": 3.3884, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4217129215003246e-05, + "loss": 3.3868, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208743267492728e-05, + "loss": 3.3804, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4200357319982208e-05, + "loss": 3.3758, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191971372471688e-05, + "loss": 3.3818, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4183601803764899e-05, + "loss": 3.3962, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4175215856254379e-05, + "loss": 3.3838, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166829908743859e-05, + "loss": 3.3813, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4158443961233337e-05, + "loss": 3.3822, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.415007439252655e-05, + "loss": 3.3794, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.414168844501603e-05, + "loss": 3.3855, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4133302497505511e-05, + "loss": 3.3835, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124916549994987e-05, + "loss": 3.3764, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.41165469812882e-05, + "loss": 3.3849, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4108161033777682e-05, + "loss": 3.3884, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099775086267162e-05, + "loss": 3.3801, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4091389138756638e-05, + "loss": 3.3832, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4083019570049852e-05, + "loss": 3.3772, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074633622539332e-05, + "loss": 3.3907, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.406624767502881e-05, + "loss": 3.3838, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.405786172751829e-05, + "loss": 3.3849, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4049492158811503e-05, + "loss": 3.3891, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4041106211300983e-05, + "loss": 3.3889, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4032720263790461e-05, + "loss": 3.3863, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4024334316279941e-05, + "loss": 3.382, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015964747573154e-05, + "loss": 3.3825, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4007578800062635e-05, + "loss": 3.3846, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3999192852552112e-05, + "loss": 3.3735, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3990806905041592e-05, + "loss": 3.3808, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3982437336334806e-05, + "loss": 3.379, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3974051388824283e-05, + "loss": 3.384, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3965665441313764e-05, + "loss": 3.3854, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3957279493803244e-05, + "loss": 3.378, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948909925096457e-05, + "loss": 3.3724, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3940523977585935e-05, + "loss": 3.3786, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3932138030075415e-05, + "loss": 3.3929, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923752082564895e-05, + "loss": 3.3825, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3915382513858107e-05, + "loss": 3.3896, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906996566347586e-05, + "loss": 3.373, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898610618837065e-05, + "loss": 3.3913, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3890224671326545e-05, + "loss": 3.3864, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881855102619756e-05, + "loss": 3.388, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3873469155109236e-05, + "loss": 3.3905, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3865083207598716e-05, + "loss": 3.3831, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856697260088198e-05, + "loss": 3.3919, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3848327691381407e-05, + "loss": 3.3954, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839941743870889e-05, + "loss": 3.3732, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3831555796360368e-05, + "loss": 3.3883, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3823186227653581e-05, + "loss": 3.383, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.381480028014306e-05, + "loss": 3.3828, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.380641433263254e-05, + "loss": 3.3768, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3798028385122019e-05, + "loss": 3.3831, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.378965881641523e-05, + "loss": 3.3765, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.378127286890471e-05, + "loss": 3.3812, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.377288692139419e-05, + "loss": 3.3812, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8634586334228516, + "eval_runtime": 309.1928, + "eval_samples_per_second": 1234.152, + "eval_steps_per_second": 38.568, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.376450097388367e-05, + "loss": 3.3937, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3756115026373151e-05, + "loss": 3.3695, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747729078862631e-05, + "loss": 3.3784, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3739343131352111e-05, + "loss": 3.3865, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730973562645322e-05, + "loss": 3.3822, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3722587615134802e-05, + "loss": 3.3806, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3714201667624282e-05, + "loss": 3.3861, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.370581572011376e-05, + "loss": 3.375, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3697446151406973e-05, + "loss": 3.3759, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3689060203896453e-05, + "loss": 3.3855, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3680674256385934e-05, + "loss": 3.3832, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3672288308875411e-05, + "loss": 3.379, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663918740168623e-05, + "loss": 3.3913, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3655532792658105e-05, + "loss": 3.3611, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3647146845147585e-05, + "loss": 3.377, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638760897637062e-05, + "loss": 3.366, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3630391328930276e-05, + "loss": 3.3851, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3622005381419756e-05, + "loss": 3.3778, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3613619433909234e-05, + "loss": 3.3702, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3605233486398714e-05, + "loss": 3.38, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596863917691926e-05, + "loss": 3.3967, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3588477970181406e-05, + "loss": 3.3809, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3580092022670885e-05, + "loss": 3.3821, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571706075160365e-05, + "loss": 3.3846, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3563336506453577e-05, + "loss": 3.3847, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554950558943059e-05, + "loss": 3.3752, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3546564611432535e-05, + "loss": 3.3759, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3538178663922015e-05, + "loss": 3.3824, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.352980909521523e-05, + "loss": 3.3698, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3521423147704706e-05, + "loss": 3.3796, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3513037200194186e-05, + "loss": 3.3874, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3504651252683668e-05, + "loss": 3.3865, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.349628168397688e-05, + "loss": 3.3838, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487895736466358e-05, + "loss": 3.3895, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3479509788955838e-05, + "loss": 3.3733, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3471123841445318e-05, + "loss": 3.3813, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.346275427273853e-05, + "loss": 3.3857, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3454368325228009e-05, + "loss": 3.3658, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445982377717489e-05, + "loss": 3.3802, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437596430206969e-05, + "loss": 3.3732, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.342922686150018e-05, + "loss": 3.3697, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420857292793392e-05, + "loss": 3.3777, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3412471345282874e-05, + "loss": 3.3934, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3404085397772354e-05, + "loss": 3.3744, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.339569945026183e-05, + "loss": 3.3784, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3387313502751312e-05, + "loss": 3.3819, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378927555240792e-05, + "loss": 3.3712, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3370541607730272e-05, + "loss": 3.3813, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3362155660219752e-05, + "loss": 3.3633, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353786091512963e-05, + "loss": 3.3758, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3345400144002443e-05, + "loss": 3.3766, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3337014196491923e-05, + "loss": 3.3859, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328628248981404e-05, + "loss": 3.3759, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3320258680274613e-05, + "loss": 3.3691, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311872732764093e-05, + "loss": 3.369, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3303486785253575e-05, + "loss": 3.3738, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3295100837743055e-05, + "loss": 3.3859, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286731269036266e-05, + "loss": 3.3626, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3278345321525746e-05, + "loss": 3.3869, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269959374015226e-05, + "loss": 3.3731, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3261573426504706e-05, + "loss": 3.3622, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3253203857797916e-05, + "loss": 3.3836, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244817910287396e-05, + "loss": 3.3666, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3236431962776876e-05, + "loss": 3.3613, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3228046015266358e-05, + "loss": 3.3661, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219676446559567e-05, + "loss": 3.3783, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3211290499049047e-05, + "loss": 3.3754, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202904551538529e-05, + "loss": 3.3697, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3194534982831738e-05, + "loss": 3.3676, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.318614903532122e-05, + "loss": 3.3662, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.31777630878107e-05, + "loss": 3.3733, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.316937714030018e-05, + "loss": 3.3775, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.316100757159339e-05, + "loss": 3.3779, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.315262162408287e-05, + "loss": 3.38, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.314423567657235e-05, + "loss": 3.3786, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.313584972906183e-05, + "loss": 3.3734, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.312748016035504e-05, + "loss": 3.3808, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.311909421284452e-05, + "loss": 3.3736, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110708265334e-05, + "loss": 3.3722, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3102322317823482e-05, + "loss": 3.3697, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093952749116691e-05, + "loss": 3.3736, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3085566801606171e-05, + "loss": 3.382, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3077180854095653e-05, + "loss": 3.3827, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.306879490658513e-05, + "loss": 3.3761, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3060425337878344e-05, + "loss": 3.3562, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3052039390367824e-05, + "loss": 3.3729, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043653442857304e-05, + "loss": 3.3788, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3035267495346782e-05, + "loss": 3.3778, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026897926639994e-05, + "loss": 3.3752, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3018511979129474e-05, + "loss": 3.3877, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3010126031618954e-05, + "loss": 3.3752, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001740084108433e-05, + "loss": 3.3769, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2993370515401645e-05, + "loss": 3.3716, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984984567891125e-05, + "loss": 3.3802, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2976598620380603e-05, + "loss": 3.38, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2968212672870083e-05, + "loss": 3.3835, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959843104163297e-05, + "loss": 3.3669, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2951457156652777e-05, + "loss": 3.3701, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2943071209142254e-05, + "loss": 3.3711, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934685261631736e-05, + "loss": 3.3857, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2926315692924948e-05, + "loss": 3.3756, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917929745414428e-05, + "loss": 3.373, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2909543797903906e-05, + "loss": 3.3694, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2901157850393386e-05, + "loss": 3.369, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892788281686599e-05, + "loss": 3.3786, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2884402334176077e-05, + "loss": 3.3715, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2876016386665557e-05, + "loss": 3.3705, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867630439155037e-05, + "loss": 3.3761, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2859260870448251e-05, + "loss": 3.3777, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850874922937728e-05, + "loss": 3.3688, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2842488975427208e-05, + "loss": 3.3741, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.283410302791669e-05, + "loss": 3.3697, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825749838013631e-05, + "loss": 3.3803, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2817363890503113e-05, + "loss": 3.3759, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808977942992593e-05, + "loss": 3.3768, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800591995482072e-05, + "loss": 3.3773, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.279220604797155e-05, + "loss": 3.3796, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.278382010046103e-05, + "loss": 3.3742, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.277543415295051e-05, + "loss": 3.3718, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.276704820543999e-05, + "loss": 3.376, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2758678636733201e-05, + "loss": 3.3717, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2750292689222681e-05, + "loss": 3.3644, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741906741712161e-05, + "loss": 3.3717, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2733520794201643e-05, + "loss": 3.3709, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2725151225494852e-05, + "loss": 3.3754, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716765277984332e-05, + "loss": 3.369, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2708379330473814e-05, + "loss": 3.371, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699993382963294e-05, + "loss": 3.3634, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691623814256504e-05, + "loss": 3.3695, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2683237866745984e-05, + "loss": 3.3809, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674851919235464e-05, + "loss": 3.3736, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2666465971724944e-05, + "loss": 3.3807, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2658096403018155e-05, + "loss": 3.3618, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649710455507635e-05, + "loss": 3.3802, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2641324507997115e-05, + "loss": 3.3761, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632938560486595e-05, + "loss": 3.3797, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2624568991779806e-05, + "loss": 3.3754, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2616183044269286e-05, + "loss": 3.374, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607797096758767e-05, + "loss": 3.3862, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2599411149248247e-05, + "loss": 3.3811, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2591041580541458e-05, + "loss": 3.366, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582655633030938e-05, + "loss": 3.3767, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2574269685520418e-05, + "loss": 3.3748, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565883738009898e-05, + "loss": 3.3721, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2557514169303109e-05, + "loss": 3.364, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2549128221792589e-05, + "loss": 3.3777, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540742274282069e-05, + "loss": 3.3645, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2532356326771549e-05, + "loss": 3.3778, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.252398675806476e-05, + "loss": 3.3666, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8647894859313965, + "eval_runtime": 303.3316, + "eval_samples_per_second": 1257.999, + "eval_steps_per_second": 39.313, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.251560081055424e-05, + "loss": 3.3773, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2507214863043721e-05, + "loss": 3.3626, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.24988289155332e-05, + "loss": 3.367, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.249045934682641e-05, + "loss": 3.379, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2482073399315892e-05, + "loss": 3.3769, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.247368745180537e-05, + "loss": 3.3704, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.246530150429485e-05, + "loss": 3.3701, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2456931935588062e-05, + "loss": 3.3639, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2448545988077542e-05, + "loss": 3.3671, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.244016004056702e-05, + "loss": 3.3766, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431774093056502e-05, + "loss": 3.376, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2423404524349713e-05, + "loss": 3.3744, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2415018576839193e-05, + "loss": 3.3775, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2406632629328673e-05, + "loss": 3.3548, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2398263060621884e-05, + "loss": 3.3644, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2389877113111364e-05, + "loss": 3.3615, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2381491165600844e-05, + "loss": 3.3741, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2373105218090324e-05, + "loss": 3.3641, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364735649383536e-05, + "loss": 3.3654, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2356349701873016e-05, + "loss": 3.3702, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347963754362494e-05, + "loss": 3.388, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2339577806851974e-05, + "loss": 3.3739, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2331208238145187e-05, + "loss": 3.3713, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2322822290634665e-05, + "loss": 3.3721, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2314436343124145e-05, + "loss": 3.3832, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2306050395613627e-05, + "loss": 3.3601, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297680826906837e-05, + "loss": 3.3688, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2289294879396317e-05, + "loss": 3.3758, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2280908931885797e-05, + "loss": 3.3608, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2272522984375277e-05, + "loss": 3.3686, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.226415341566849e-05, + "loss": 3.3753, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2255767468157968e-05, + "loss": 3.3789, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2247381520647448e-05, + "loss": 3.3749, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238995573136928e-05, + "loss": 3.3795, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2230626004430139e-05, + "loss": 3.3638, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2222240056919619e-05, + "loss": 3.3752, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213854109409099e-05, + "loss": 3.3725, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.220546816189858e-05, + "loss": 3.3589, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.219709859319179e-05, + "loss": 3.3731, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2188712645681271e-05, + "loss": 3.3628, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2180326698170751e-05, + "loss": 3.3612, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171957129463962e-05, + "loss": 3.3686, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2163571181953442e-05, + "loss": 3.3816, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2155185234442922e-05, + "loss": 3.3626, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146799286932402e-05, + "loss": 3.3738, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.213841333942188e-05, + "loss": 3.3703, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2130027391911362e-05, + "loss": 3.3661, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121641444400842e-05, + "loss": 3.3688, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.211325549689032e-05, + "loss": 3.3541, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104885928183532e-05, + "loss": 3.3688, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2096499980673012e-05, + "loss": 3.3661, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2088114033162492e-05, + "loss": 3.375, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079728085651972e-05, + "loss": 3.3684, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2071358516945183e-05, + "loss": 3.3573, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062972569434663e-05, + "loss": 3.357, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2054586621924145e-05, + "loss": 3.3631, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2046200674413623e-05, + "loss": 3.3805, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037831105706834e-05, + "loss": 3.3542, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2029445158196315e-05, + "loss": 3.3755, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2021059210685793e-05, + "loss": 3.3665, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2012673263175273e-05, + "loss": 3.3509, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2004303694468486e-05, + "loss": 3.3721, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995917746957966e-05, + "loss": 3.3623, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1987531799447444e-05, + "loss": 3.3527, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1979145851936926e-05, + "loss": 3.3531, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970776283230137e-05, + "loss": 3.375, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1962390335719617e-05, + "loss": 3.3636, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1954004388209096e-05, + "loss": 3.3575, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1945618440698576e-05, + "loss": 3.3558, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1937248871991787e-05, + "loss": 3.3583, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1928862924481267e-05, + "loss": 3.3651, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1920476976970747e-05, + "loss": 3.3683, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1912091029460227e-05, + "loss": 3.3664, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.190372146075344e-05, + "loss": 3.3715, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1895335513242918e-05, + "loss": 3.368, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1886949565732398e-05, + "loss": 3.3696, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.187856361822188e-05, + "loss": 3.3655, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.187019404951509e-05, + "loss": 3.3617, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861808102004569e-05, + "loss": 3.3625, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.185342215449405e-05, + "loss": 3.3646, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.184503620698353e-05, + "loss": 3.3641, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1836666638276741e-05, + "loss": 3.3673, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1828280690766221e-05, + "loss": 3.3769, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.18198947432557e-05, + "loss": 3.367, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1811508795745179e-05, + "loss": 3.3455, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1803139227038392e-05, + "loss": 3.3632, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794753279527872e-05, + "loss": 3.3701, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1786367332017351e-05, + "loss": 3.3724, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777981384506831e-05, + "loss": 3.3622, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1769611815800042e-05, + "loss": 3.3773, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1761242247093255e-05, + "loss": 3.3701, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752856299582735e-05, + "loss": 3.3628, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1744470352072213e-05, + "loss": 3.3634, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1736084404561695e-05, + "loss": 3.3712, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1727698457051175e-05, + "loss": 3.3662, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1719312509540653e-05, + "loss": 3.3727, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710926562030133e-05, + "loss": 3.3592, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1702540614519614e-05, + "loss": 3.3593, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1694171045812825e-05, + "loss": 3.3611, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1685785098302303e-05, + "loss": 3.3742, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1677399150791785e-05, + "loss": 3.3671, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1669013203281265e-05, + "loss": 3.3647, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1660643634574476e-05, + "loss": 3.3585, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1652257687063956e-05, + "loss": 3.358, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643871739553436e-05, + "loss": 3.373, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1635485792042916e-05, + "loss": 3.356, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1627116223336127e-05, + "loss": 3.3612, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1618730275825606e-05, + "loss": 3.3674, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1610344328315086e-05, + "loss": 3.3676, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1601958380804568e-05, + "loss": 3.3612, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1593588812097777e-05, + "loss": 3.3659, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1585202864587257e-05, + "loss": 3.3574, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1576816917076739e-05, + "loss": 3.3708, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1568430969566217e-05, + "loss": 3.3661, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.156006140085943e-05, + "loss": 3.3627, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.155167545334891e-05, + "loss": 3.3719, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.154328950583839e-05, + "loss": 3.3716, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1534903558327868e-05, + "loss": 3.3634, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.152653398962108e-05, + "loss": 3.363, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.151814804211056e-05, + "loss": 3.3665, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.150976209460004e-05, + "loss": 3.3607, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.150137614708952e-05, + "loss": 3.3546, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.149300657838273e-05, + "loss": 3.3638, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.148462063087221e-05, + "loss": 3.3608, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.147623468336169e-05, + "loss": 3.3682, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.146784873585117e-05, + "loss": 3.3549, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1459479167144383e-05, + "loss": 3.3674, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1451093219633863e-05, + "loss": 3.357, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1442707272123341e-05, + "loss": 3.3604, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1434337703416554e-05, + "loss": 3.3651, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425951755906034e-05, + "loss": 3.3688, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1417565808395514e-05, + "loss": 3.3676, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1409179860884992e-05, + "loss": 3.3538, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400810292178205e-05, + "loss": 3.3727, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1392424344667684e-05, + "loss": 3.3664, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1384038397157164e-05, + "loss": 3.366, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1375652449646644e-05, + "loss": 3.3674, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1367282880939855e-05, + "loss": 3.3663, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1358896933429337e-05, + "loss": 3.3761, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1350510985918815e-05, + "loss": 3.371, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1342125038408295e-05, + "loss": 3.3591, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1333755469701508e-05, + "loss": 3.3645, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1325369522190988e-05, + "loss": 3.3644, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316983574680466e-05, + "loss": 3.3593, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1308597627169946e-05, + "loss": 3.3576, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1300228058463158e-05, + "loss": 3.366, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1291842110952636e-05, + "loss": 3.3547, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1283456163442118e-05, + "loss": 3.3688, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1275070215931598e-05, + "loss": 3.3561, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.865666389465332, + "eval_runtime": 304.2174, + "eval_samples_per_second": 1254.336, + "eval_steps_per_second": 39.199, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1266684268421078e-05, + "loss": 3.3329, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1258298320910556e-05, + "loss": 3.3593, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1249912373400038e-05, + "loss": 3.3546, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1241526425889518e-05, + "loss": 3.3691, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1233156857182727e-05, + "loss": 3.3682, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224770909672209e-05, + "loss": 3.3632, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1216384962161689e-05, + "loss": 3.3585, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207999014651167e-05, + "loss": 3.354, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.119962944594438e-05, + "loss": 3.3623, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.119124349843386e-05, + "loss": 3.3623, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.118285755092334e-05, + "loss": 3.366, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.117447160341282e-05, + "loss": 3.3617, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.116610203470603e-05, + "loss": 3.3686, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.115771608719551e-05, + "loss": 3.3464, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1149330139684992e-05, + "loss": 3.3549, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.114094419217447e-05, + "loss": 3.3532, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.113257462346768e-05, + "loss": 3.3624, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1124188675957162e-05, + "loss": 3.3551, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.111580272844664e-05, + "loss": 3.356, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.110741678093612e-05, + "loss": 3.359, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1099047212229333e-05, + "loss": 3.3798, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1090661264718813e-05, + "loss": 3.3616, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1082275317208291e-05, + "loss": 3.3582, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073889369697773e-05, + "loss": 3.3675, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1065519800990984e-05, + "loss": 3.371, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1057133853480464e-05, + "loss": 3.3532, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1048747905969944e-05, + "loss": 3.3563, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1040361958459424e-05, + "loss": 3.3676, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031992389752634e-05, + "loss": 3.3486, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1023606442242114e-05, + "loss": 3.3613, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1015220494731594e-05, + "loss": 3.3623, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1006834547221074e-05, + "loss": 3.3725, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0998464978514287e-05, + "loss": 3.3648, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0990079031003765e-05, + "loss": 3.3645, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0981693083493245e-05, + "loss": 3.3564, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0973307135982727e-05, + "loss": 3.3688, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0964937567275937e-05, + "loss": 3.3627, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0956551619765416e-05, + "loss": 3.349, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0948165672254897e-05, + "loss": 3.3595, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0939779724744377e-05, + "loss": 3.3519, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0931410156037588e-05, + "loss": 3.3555, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0923040587330799e-05, + "loss": 3.3558, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0914654639820279e-05, + "loss": 3.3727, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.090626869230976e-05, + "loss": 3.3575, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0897882744799239e-05, + "loss": 3.3587, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0889496797288719e-05, + "loss": 3.3635, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0881110849778199e-05, + "loss": 3.3519, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0872724902267679e-05, + "loss": 3.3641, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0864338954757158e-05, + "loss": 3.3448, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.085596938605037e-05, + "loss": 3.3516, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0847583438539851e-05, + "loss": 3.361, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.083919749102933e-05, + "loss": 3.3621, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830811543518809e-05, + "loss": 3.3614, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0822441974812022e-05, + "loss": 3.3467, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0814056027301502e-05, + "loss": 3.3526, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.080567007979098e-05, + "loss": 3.3509, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0797300511084192e-05, + "loss": 3.3731, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0788914563573672e-05, + "loss": 3.3446, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.078052861606315e-05, + "loss": 3.364, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0772142668552632e-05, + "loss": 3.3567, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0763756721042112e-05, + "loss": 3.343, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0755370773531592e-05, + "loss": 3.3611, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746984826021072e-05, + "loss": 3.3538, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0738598878510552e-05, + "loss": 3.3407, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0730229309803763e-05, + "loss": 3.345, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0721843362293243e-05, + "loss": 3.3647, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0713457414782723e-05, + "loss": 3.3538, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0705071467272203e-05, + "loss": 3.3518, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0696701898565415e-05, + "loss": 3.347, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0688315951054893e-05, + "loss": 3.3458, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0679930003544373e-05, + "loss": 3.3556, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0671544056033853e-05, + "loss": 3.3604, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0663174487327066e-05, + "loss": 3.3548, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0654788539816544e-05, + "loss": 3.3635, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0646402592306024e-05, + "loss": 3.3598, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0638016644795506e-05, + "loss": 3.3564, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0629647076088715e-05, + "loss": 3.3571, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0621261128578196e-05, + "loss": 3.3527, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0612875181067676e-05, + "loss": 3.3551, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0604489233557156e-05, + "loss": 3.359, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0596119664850367e-05, + "loss": 3.3523, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0587733717339847e-05, + "loss": 3.3613, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0579347769829327e-05, + "loss": 3.3608, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570961822318807e-05, + "loss": 3.3582, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0562592253612018e-05, + "loss": 3.3397, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0554206306101498e-05, + "loss": 3.3491, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545820358590978e-05, + "loss": 3.3636, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0537450789884188e-05, + "loss": 3.3591, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0529064842373668e-05, + "loss": 3.3554, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.052067889486315e-05, + "loss": 3.3689, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0512292947352628e-05, + "loss": 3.3576, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503923378645839e-05, + "loss": 3.3547, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.049553743113532e-05, + "loss": 3.3536, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.04871514836248e-05, + "loss": 3.3616, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478765536114279e-05, + "loss": 3.3568, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0470395967407491e-05, + "loss": 3.3672, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0462010019896971e-05, + "loss": 3.345, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0453624072386451e-05, + "loss": 3.3564, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0445238124875931e-05, + "loss": 3.3492, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436868556169142e-05, + "loss": 3.362, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0428482608658622e-05, + "loss": 3.3629, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0420096661148102e-05, + "loss": 3.3517, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411710713637582e-05, + "loss": 3.3529, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0403341144930793e-05, + "loss": 3.3495, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394955197420274e-05, + "loss": 3.3618, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0386569249909753e-05, + "loss": 3.3431, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0378183302399233e-05, + "loss": 3.3561, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369813733692445e-05, + "loss": 3.3563, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0361427786181925e-05, + "loss": 3.3542, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0353041838671403e-05, + "loss": 3.3549, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0344655891160885e-05, + "loss": 3.3597, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0336286322454096e-05, + "loss": 3.3442, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0327900374943574e-05, + "loss": 3.3645, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0319514427433056e-05, + "loss": 3.3575, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0311128479922536e-05, + "loss": 3.3533, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302758911215746e-05, + "loss": 3.3628, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0294372963705226e-05, + "loss": 3.3629, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285987016194706e-05, + "loss": 3.3542, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0277601068684186e-05, + "loss": 3.3511, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0269231499977399e-05, + "loss": 3.3557, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0260845552466877e-05, + "loss": 3.3506, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0252459604956357e-05, + "loss": 3.3484, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0244073657445839e-05, + "loss": 3.349, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0235704088739048e-05, + "loss": 3.3538, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0227318141228528e-05, + "loss": 3.357, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.021893219371801e-05, + "loss": 3.3474, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.021054624620749e-05, + "loss": 3.3577, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.02021766775007e-05, + "loss": 3.3455, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.019379072999018e-05, + "loss": 3.3542, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.018540478247966e-05, + "loss": 3.3545, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0177018834969138e-05, + "loss": 3.3594, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.016864926626235e-05, + "loss": 3.3587, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.016026331875183e-05, + "loss": 3.3453, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.015187737124131e-05, + "loss": 3.3585, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.014349142373079e-05, + "loss": 3.3593, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0135121855024001e-05, + "loss": 3.3611, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0126735907513481e-05, + "loss": 3.359, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0118349960002963e-05, + "loss": 3.3557, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0109964012492441e-05, + "loss": 3.37, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0101594443785654e-05, + "loss": 3.3569, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0093208496275134e-05, + "loss": 3.3542, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0084822548764612e-05, + "loss": 3.3556, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0076436601254092e-05, + "loss": 3.3547, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0068067032547304e-05, + "loss": 3.349, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0059681085036784e-05, + "loss": 3.3451, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0051311516329995e-05, + "loss": 3.3606, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042925568819475e-05, + "loss": 3.3442, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0034539621308955e-05, + "loss": 3.3589, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0026153673798435e-05, + "loss": 3.3499, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0017767726287915e-05, + "loss": 3.3549, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.8659253120422363, + "eval_runtime": 311.6188, + "eval_samples_per_second": 1224.544, + "eval_steps_per_second": 38.268, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0009381778777395e-05, + "loss": 3.3437, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000995831266875e-05, + "loss": 3.3466, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.992609883756355e-06, + "loss": 3.358, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.984240315049566e-06, + "loss": 3.3612, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.975854367539046e-06, + "loss": 3.3555, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.967468420028527e-06, + "loss": 3.3494, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.959098851321736e-06, + "loss": 3.346, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.950712903811216e-06, + "loss": 3.3443, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.942326956300698e-06, + "loss": 3.3593, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.933941008790176e-06, + "loss": 3.355, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.925571440083389e-06, + "loss": 3.3587, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.917185492572869e-06, + "loss": 3.3606, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.908799545062349e-06, + "loss": 3.3407, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.900413597551827e-06, + "loss": 3.3398, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.89204402884504e-06, + "loss": 3.3425, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.88365808133452e-06, + "loss": 3.355, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.875272133823998e-06, + "loss": 3.3474, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.86688618631348e-06, + "loss": 3.3512, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.85851661760669e-06, + "loss": 3.3465, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.85013067009617e-06, + "loss": 3.3702, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.84174472258565e-06, + "loss": 3.3524, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.83335877507513e-06, + "loss": 3.3504, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.824989206368342e-06, + "loss": 3.353, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.816603258857822e-06, + "loss": 3.3659, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.8082173113473e-06, + "loss": 3.3424, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.79983136383678e-06, + "loss": 3.3498, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.791461795129993e-06, + "loss": 3.3544, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.783075847619471e-06, + "loss": 3.3413, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.774689900108951e-06, + "loss": 3.3514, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.766303952598433e-06, + "loss": 3.3526, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.757934383891644e-06, + "loss": 3.3633, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.749548436381124e-06, + "loss": 3.3532, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.741162488870604e-06, + "loss": 3.3546, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.732776541360084e-06, + "loss": 3.3538, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.724406972653294e-06, + "loss": 3.3547, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.716021025142774e-06, + "loss": 3.3554, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.707635077632254e-06, + "loss": 3.3411, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.699249130121734e-06, + "loss": 3.3496, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.690879561414945e-06, + "loss": 3.3428, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.682493613904425e-06, + "loss": 3.3478, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.674107666393905e-06, + "loss": 3.3464, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.665721718883387e-06, + "loss": 3.3616, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.657352150176596e-06, + "loss": 3.3487, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648966202666077e-06, + "loss": 3.3482, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.640580255155557e-06, + "loss": 3.3553, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.632194307645036e-06, + "loss": 3.3429, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.623824738938248e-06, + "loss": 3.3558, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.615438791427728e-06, + "loss": 3.3327, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.607052843917208e-06, + "loss": 3.3449, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.598666896406686e-06, + "loss": 3.3526, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.590297327699899e-06, + "loss": 3.3552, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.581911380189379e-06, + "loss": 3.3512, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.573525432678859e-06, + "loss": 3.333, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.565139485168339e-06, + "loss": 3.3495, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.55676991646155e-06, + "loss": 3.3372, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.548400347754762e-06, + "loss": 3.364, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.540014400244242e-06, + "loss": 3.339, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.53162845273372e-06, + "loss": 3.3562, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.523242505223202e-06, + "loss": 3.3428, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.514856557712682e-06, + "loss": 3.3342, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.50647061020216e-06, + "loss": 3.3526, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.49808466269164e-06, + "loss": 3.3462, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.489698715181122e-06, + "loss": 3.33, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.481329146474332e-06, + "loss": 3.3357, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472943198963812e-06, + "loss": 3.3558, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.464557251453292e-06, + "loss": 3.345, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.456171303942772e-06, + "loss": 3.3402, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.447801735235983e-06, + "loss": 3.3391, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.439415787725463e-06, + "loss": 3.3363, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.431029840214943e-06, + "loss": 3.3436, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.422643892704423e-06, + "loss": 3.3522, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.414274323997634e-06, + "loss": 3.3466, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.405888376487114e-06, + "loss": 3.3546, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.397502428976594e-06, + "loss": 3.3463, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.389116481466074e-06, + "loss": 3.3532, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.380746912759284e-06, + "loss": 3.3449, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.372360965248766e-06, + "loss": 3.3456, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363975017738246e-06, + "loss": 3.3479, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.355605449031455e-06, + "loss": 3.3424, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.347219501520937e-06, + "loss": 3.3441, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.338833554010417e-06, + "loss": 3.3528, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.330447606499897e-06, + "loss": 3.3528, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.322078037793107e-06, + "loss": 3.3457, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.313692090282587e-06, + "loss": 3.3303, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.305306142772067e-06, + "loss": 3.341, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.296920195261547e-06, + "loss": 3.3553, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.288550626554758e-06, + "loss": 3.3532, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.280164679044238e-06, + "loss": 3.3441, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.271778731533718e-06, + "loss": 3.3595, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.263392784023198e-06, + "loss": 3.3509, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.255023215316409e-06, + "loss": 3.3421, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.24663726780589e-06, + "loss": 3.3461, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.238251320295369e-06, + "loss": 3.3523, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.229865372784849e-06, + "loss": 3.3455, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.221495804078061e-06, + "loss": 3.358, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.213109856567541e-06, + "loss": 3.3393, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.20472390905702e-06, + "loss": 3.3424, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.196337961546501e-06, + "loss": 3.3412, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.187968392839712e-06, + "loss": 3.3533, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.179582445329192e-06, + "loss": 3.3497, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.171196497818672e-06, + "loss": 3.346, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.162810550308152e-06, + "loss": 3.3396, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.154440981601362e-06, + "loss": 3.3418, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.146055034090842e-06, + "loss": 3.3561, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.137669086580322e-06, + "loss": 3.3307, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.129283139069802e-06, + "loss": 3.3473, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.120913570363015e-06, + "loss": 3.351, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.112527622852493e-06, + "loss": 3.3457, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.104141675341973e-06, + "loss": 3.3434, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.095755727831453e-06, + "loss": 3.3492, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.087386159124665e-06, + "loss": 3.3359, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.079000211614144e-06, + "loss": 3.3502, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.070614264103625e-06, + "loss": 3.3482, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.062228316593105e-06, + "loss": 3.3475, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053858747886314e-06, + "loss": 3.3523, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.045472800375796e-06, + "loss": 3.3547, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.037086852865276e-06, + "loss": 3.3463, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.028700905354756e-06, + "loss": 3.3444, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.020331336647967e-06, + "loss": 3.3461, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011945389137447e-06, + "loss": 3.3421, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.003559441626927e-06, + "loss": 3.3336, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.995173494116407e-06, + "loss": 3.342, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.986803925409617e-06, + "loss": 3.3424, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.978417977899097e-06, + "loss": 3.3512, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.970032030388579e-06, + "loss": 3.3377, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.961646082878057e-06, + "loss": 3.347, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.953276514171268e-06, + "loss": 3.3364, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.94489056666075e-06, + "loss": 3.3424, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.93650461915023e-06, + "loss": 3.3387, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.928118671639708e-06, + "loss": 3.3549, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.91974910293292e-06, + "loss": 3.3465, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.9113631554224e-06, + "loss": 3.3421, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.902977207911879e-06, + "loss": 3.3452, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.89459126040136e-06, + "loss": 3.346, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.886221691694571e-06, + "loss": 3.3511, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.877835744184051e-06, + "loss": 3.3484, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.869449796673531e-06, + "loss": 3.3483, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.861063849163011e-06, + "loss": 3.3577, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.852694280456222e-06, + "loss": 3.3477, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.844308332945703e-06, + "loss": 3.3464, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.835922385435182e-06, + "loss": 3.3417, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.827536437924662e-06, + "loss": 3.3494, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.819166869217874e-06, + "loss": 3.3431, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.810780921707352e-06, + "loss": 3.3331, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.802411353000565e-06, + "loss": 3.3483, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.794025405490045e-06, + "loss": 3.3389, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.785639457979525e-06, + "loss": 3.3497, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.777253510469003e-06, + "loss": 3.3405, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.768867562958485e-06, + "loss": 3.3444, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.866617441177368, + "eval_runtime": 309.0356, + "eval_samples_per_second": 1234.78, + "eval_steps_per_second": 38.588, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.760481615447965e-06, + "loss": 3.3355, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.752095667937443e-06, + "loss": 3.3396, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.743709720426924e-06, + "loss": 3.3498, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.735340151720135e-06, + "loss": 3.347, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.726954204209615e-06, + "loss": 3.3488, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.718568256699095e-06, + "loss": 3.3431, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.710182309188575e-06, + "loss": 3.3355, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.701812740481786e-06, + "loss": 3.3387, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.693426792971268e-06, + "loss": 3.3494, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.685040845460746e-06, + "loss": 3.3462, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.676654897950226e-06, + "loss": 3.3456, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.668285329243438e-06, + "loss": 3.3489, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.659899381732916e-06, + "loss": 3.332, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.651513434222396e-06, + "loss": 3.3335, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.643127486711876e-06, + "loss": 3.3415, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.634757918005089e-06, + "loss": 3.3337, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.626371970494567e-06, + "loss": 3.3395, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.617986022984049e-06, + "loss": 3.3393, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.609600075473529e-06, + "loss": 3.3363, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.601230506766738e-06, + "loss": 3.3645, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.59284455925622e-06, + "loss": 3.3438, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.5844586117457e-06, + "loss": 3.3399, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.57607266423518e-06, + "loss": 3.344, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.56770309552839e-06, + "loss": 3.3526, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.55931714801787e-06, + "loss": 3.3364, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.55093120050735e-06, + "loss": 3.3396, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.54254525299683e-06, + "loss": 3.3434, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.534175684290041e-06, + "loss": 3.341, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.52578973677952e-06, + "loss": 3.338, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.517403789269002e-06, + "loss": 3.339, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.50901784175848e-06, + "loss": 3.3595, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.500648273051692e-06, + "loss": 3.3454, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.492262325541173e-06, + "loss": 3.3438, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.483876378030653e-06, + "loss": 3.3452, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.475490430520131e-06, + "loss": 3.3447, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.467120861813344e-06, + "loss": 3.3455, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.458734914302824e-06, + "loss": 3.3319, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.450348966792302e-06, + "loss": 3.34, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.441963019281784e-06, + "loss": 3.3304, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.433593450574995e-06, + "loss": 3.343, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.425207503064474e-06, + "loss": 3.3353, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.416821555553954e-06, + "loss": 3.3515, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.408435608043434e-06, + "loss": 3.3414, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.400066039336645e-06, + "loss": 3.3399, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.391680091826127e-06, + "loss": 3.3473, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.383294144315605e-06, + "loss": 3.3365, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.374908196805085e-06, + "loss": 3.3444, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.366538628098298e-06, + "loss": 3.3299, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.358152680587776e-06, + "loss": 3.3365, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.349766733077256e-06, + "loss": 3.3412, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.341380785566737e-06, + "loss": 3.3434, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.333011216859948e-06, + "loss": 3.3475, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.324625269349426e-06, + "loss": 3.3217, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.316239321838908e-06, + "loss": 3.3418, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.307869753132119e-06, + "loss": 3.3239, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.299483805621599e-06, + "loss": 3.355, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.291097858111079e-06, + "loss": 3.3302, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.282711910600559e-06, + "loss": 3.3447, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.274325963090039e-06, + "loss": 3.336, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.26595639438325e-06, + "loss": 3.328, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.25757044687273e-06, + "loss": 3.3377, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.24918449936221e-06, + "loss": 3.338, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.240814930655422e-06, + "loss": 3.3221, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.2324289831449e-06, + "loss": 3.3277, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.22404303563438e-06, + "loss": 3.3435, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.215657088123862e-06, + "loss": 3.3376, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.207287519417073e-06, + "loss": 3.3323, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.198901571906553e-06, + "loss": 3.3317, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.190515624396032e-06, + "loss": 3.3251, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.182129676885512e-06, + "loss": 3.3368, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.173760108178723e-06, + "loss": 3.3381, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.165374160668203e-06, + "loss": 3.3385, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.156988213157683e-06, + "loss": 3.347, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.148602265647163e-06, + "loss": 3.3397, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.140232696940374e-06, + "loss": 3.3443, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.131846749429854e-06, + "loss": 3.3302, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.123460801919334e-06, + "loss": 3.3422, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.115074854408814e-06, + "loss": 3.3351, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.106705285702025e-06, + "loss": 3.3327, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.098319338191506e-06, + "loss": 3.3372, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.089933390680986e-06, + "loss": 3.3392, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.081547443170464e-06, + "loss": 3.3468, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.073177874463677e-06, + "loss": 3.3371, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.064791926953157e-06, + "loss": 3.3226, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.056405979442637e-06, + "loss": 3.3262, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.048020031932115e-06, + "loss": 3.3488, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.039650463225328e-06, + "loss": 3.3416, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.031264515714808e-06, + "loss": 3.34, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.022878568204287e-06, + "loss": 3.347, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.014492620693767e-06, + "loss": 3.3443, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.006123051986978e-06, + "loss": 3.3288, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.99773710447646e-06, + "loss": 3.3361, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.989351156965938e-06, + "loss": 3.3445, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.980965209455418e-06, + "loss": 3.3366, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.97259564074863e-06, + "loss": 3.3472, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.96420969323811e-06, + "loss": 3.3298, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.955823745727589e-06, + "loss": 3.3362, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.947437798217069e-06, + "loss": 3.3352, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.939068229510281e-06, + "loss": 3.3432, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.93068228199976e-06, + "loss": 3.3423, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.922296334489241e-06, + "loss": 3.3368, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.913910386978721e-06, + "loss": 3.3306, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.905540818271932e-06, + "loss": 3.331, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.897154870761412e-06, + "loss": 3.3505, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.888768923250892e-06, + "loss": 3.3235, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.880382975740372e-06, + "loss": 3.3328, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.872013407033583e-06, + "loss": 3.3468, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.863627459523062e-06, + "loss": 3.3373, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.855241512012542e-06, + "loss": 3.3317, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.846855564502022e-06, + "loss": 3.3382, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.838485995795233e-06, + "loss": 3.332, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.830100048284713e-06, + "loss": 3.3415, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.821714100774195e-06, + "loss": 3.3346, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.813328153263673e-06, + "loss": 3.3357, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.804958584556884e-06, + "loss": 3.345, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.796572637046366e-06, + "loss": 3.3481, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.788186689535845e-06, + "loss": 3.3341, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.779800742025324e-06, + "loss": 3.3342, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.771431173318536e-06, + "loss": 3.3379, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.763045225808016e-06, + "loss": 3.333, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.754659278297496e-06, + "loss": 3.3262, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.746273330786976e-06, + "loss": 3.3339, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.737903762080187e-06, + "loss": 3.3328, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.729517814569667e-06, + "loss": 3.3408, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.721131867059147e-06, + "loss": 3.3309, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.712745919548627e-06, + "loss": 3.3394, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.704376350841838e-06, + "loss": 3.3219, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.69599040333132e-06, + "loss": 3.3357, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.687604455820797e-06, + "loss": 3.3315, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.679218508310277e-06, + "loss": 3.3441, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.67084893960349e-06, + "loss": 3.3404, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.66246299209297e-06, + "loss": 3.3365, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.654077044582448e-06, + "loss": 3.3294, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.64570747587566e-06, + "loss": 3.335, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.63732152836514e-06, + "loss": 3.3461, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.62893558085462e-06, + "loss": 3.3417, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.6205496333441e-06, + "loss": 3.3422, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.612180064637311e-06, + "loss": 3.3477, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.603794117126792e-06, + "loss": 3.3351, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.595408169616271e-06, + "loss": 3.3385, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.587022222105751e-06, + "loss": 3.333, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.578652653398963e-06, + "loss": 3.3401, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.570266705888443e-06, + "loss": 3.3367, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.561880758377922e-06, + "loss": 3.321, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.5535111896711334e-06, + "loss": 3.3417, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.545125242160614e-06, + "loss": 3.3319, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.5367392946500925e-06, + "loss": 3.3404, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.528353347139573e-06, + "loss": 3.3305, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.519967399629053e-06, + "loss": 3.3371, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.8664703369140625, + "eval_runtime": 328.434, + "eval_samples_per_second": 1161.85, + "eval_steps_per_second": 36.309, + "step": 2594880 + }, + { + "epoch": 1.0, + "learning_rate": 7.511581452118534e-06, + "loss": 3.3273, + "step": 2595328 + }, + { + "epoch": 1.0, + "learning_rate": 7.503195504608012e-06, + "loss": 3.3312, + "step": 2595840 + }, + { + "epoch": 1.0, + "learning_rate": 7.494809557097493e-06, + "loss": 3.3395, + "step": 2596352 + }, + { + "epoch": 1.0, + "learning_rate": 7.486439988390705e-06, + "loss": 3.3384, + "step": 2596864 + }, + { + "epoch": 1.0, + "learning_rate": 7.478054040880184e-06, + "loss": 3.3444, + "step": 2597376 + }, + { + "epoch": 1.0, + "learning_rate": 7.469668093369664e-06, + "loss": 3.3275, + "step": 2597888 + }, + { + "epoch": 1.0, + "learning_rate": 7.461282145859144e-06, + "loss": 3.33, + "step": 2598400 + }, + { + "epoch": 1.0, + "learning_rate": 7.452912577152356e-06, + "loss": 3.3289, + "step": 2598912 + }, + { + "epoch": 1.0, + "learning_rate": 7.4445266296418345e-06, + "loss": 3.3379, + "step": 2599424 + }, + { + "epoch": 1.0, + "learning_rate": 7.436140682131315e-06, + "loss": 3.3398, + "step": 2599936 + }, + { + "epoch": 1.0, + "learning_rate": 7.427754734620795e-06, + "loss": 3.3363, + "step": 2600448 + }, + { + "epoch": 1.0, + "learning_rate": 7.419385165914007e-06, + "loss": 3.3358, + "step": 2600960 + }, + { + "epoch": 1.0, + "learning_rate": 7.410999218403486e-06, + "loss": 3.325, + "step": 2601472 + }, + { + "epoch": 1.0, + "learning_rate": 7.402613270892966e-06, + "loss": 3.3231, + "step": 2601984 + }, + { + "epoch": 1.0, + "learning_rate": 7.394227323382447e-06, + "loss": 3.333, + "step": 2602496 + }, + { + "epoch": 1.0, + "learning_rate": 7.385857754675657e-06, + "loss": 3.3273, + "step": 2603008 + }, + { + "epoch": 1.0, + "learning_rate": 7.3774718071651375e-06, + "loss": 3.3279, + "step": 2603520 + }, + { + "epoch": 1.0, + "learning_rate": 7.3690858596546175e-06, + "loss": 3.3293, + "step": 2604032 + }, + { + "epoch": 1.0, + "learning_rate": 7.360716290947829e-06, + "loss": 3.3298, + "step": 2604544 + }, + { + "epoch": 1.0, + "learning_rate": 7.352330343437308e-06, + "loss": 3.3571, + "step": 2605056 + }, + { + "epoch": 1.0, + "learning_rate": 7.343944395926788e-06, + "loss": 3.335, + "step": 2605568 + }, + { + "epoch": 1.0, + "learning_rate": 7.335558448416269e-06, + "loss": 3.3362, + "step": 2606080 + }, + { + "epoch": 1.0, + "learning_rate": 7.327188879709481e-06, + "loss": 3.3358, + "step": 2606592 + }, + { + "epoch": 1.0, + "learning_rate": 7.318802932198959e-06, + "loss": 3.343, + "step": 2607104 + }, + { + "epoch": 1.0, + "learning_rate": 7.31041698468844e-06, + "loss": 3.3249, + "step": 2607616 + }, + { + "epoch": 1.0, + "learning_rate": 7.30203103717792e-06, + "loss": 3.3305, + "step": 2608128 + }, + { + "epoch": 1.0, + "learning_rate": 7.2936614684711304e-06, + "loss": 3.3329, + "step": 2608640 + }, + { + "epoch": 1.0, + "learning_rate": 7.28527552096061e-06, + "loss": 3.3321, + "step": 2609152 + }, + { + "epoch": 1.0, + "learning_rate": 7.276889573450091e-06, + "loss": 3.327, + "step": 2609664 + }, + { + "epoch": 1.01, + "learning_rate": 7.2685036259395695e-06, + "loss": 3.3326, + "step": 2610176 + }, + { + "epoch": 1.01, + "learning_rate": 7.260134057232781e-06, + "loss": 3.3476, + "step": 2610688 + }, + { + "epoch": 1.01, + "learning_rate": 7.251748109722262e-06, + "loss": 3.338, + "step": 2611200 + }, + { + "epoch": 1.01, + "learning_rate": 7.243362162211742e-06, + "loss": 3.3344, + "step": 2611712 + }, + { + "epoch": 1.01, + "learning_rate": 7.234976214701221e-06, + "loss": 3.339, + "step": 2612224 + }, + { + "epoch": 1.01, + "learning_rate": 7.226606645994433e-06, + "loss": 3.3366, + "step": 2612736 + }, + { + "epoch": 1.01, + "learning_rate": 7.2182206984839126e-06, + "loss": 3.3333, + "step": 2613248 + }, + { + "epoch": 1.01, + "learning_rate": 7.209834750973393e-06, + "loss": 3.323, + "step": 2613760 + }, + { + "epoch": 1.01, + "learning_rate": 7.2014488034628725e-06, + "loss": 3.3351, + "step": 2614272 + }, + { + "epoch": 1.01, + "learning_rate": 7.193079234756084e-06, + "loss": 3.3216, + "step": 2614784 + }, + { + "epoch": 1.01, + "learning_rate": 7.184693287245564e-06, + "loss": 3.3316, + "step": 2615296 + }, + { + "epoch": 1.01, + "learning_rate": 7.176323718538776e-06, + "loss": 3.3254, + "step": 2615808 + }, + { + "epoch": 1.01, + "learning_rate": 7.167937771028255e-06, + "loss": 3.3414, + "step": 2616320 + }, + { + "epoch": 1.01, + "learning_rate": 7.159551823517735e-06, + "loss": 3.3333, + "step": 2616832 + }, + { + "epoch": 1.01, + "learning_rate": 7.1511658760072156e-06, + "loss": 3.3294, + "step": 2617344 + }, + { + "epoch": 1.01, + "learning_rate": 7.142779928496694e-06, + "loss": 3.3351, + "step": 2617856 + }, + { + "epoch": 1.01, + "learning_rate": 7.134393980986175e-06, + "loss": 3.329, + "step": 2618368 + }, + { + "epoch": 1.01, + "learning_rate": 7.126008033475655e-06, + "loss": 3.3354, + "step": 2618880 + }, + { + "epoch": 1.01, + "learning_rate": 7.117622085965134e-06, + "loss": 3.3196, + "step": 2619392 + }, + { + "epoch": 1.01, + "learning_rate": 7.109252517258345e-06, + "loss": 3.3234, + "step": 2619904 + }, + { + "epoch": 1.01, + "learning_rate": 7.100866569747826e-06, + "loss": 3.3334, + "step": 2620416 + }, + { + "epoch": 1.01, + "learning_rate": 7.092480622237306e-06, + "loss": 3.3338, + "step": 2620928 + }, + { + "epoch": 1.01, + "learning_rate": 7.084094674726785e-06, + "loss": 3.3349, + "step": 2621440 + }, + { + "epoch": 1.01, + "learning_rate": 7.075725106019997e-06, + "loss": 3.3158, + "step": 2621952 + }, + { + "epoch": 1.01, + "learning_rate": 7.067339158509477e-06, + "loss": 3.335, + "step": 2622464 + }, + { + "epoch": 1.01, + "learning_rate": 7.058953210998958e-06, + "loss": 3.3151, + "step": 2622976 + }, + { + "epoch": 1.01, + "learning_rate": 7.0505836422921675e-06, + "loss": 3.345, + "step": 2623488 + }, + { + "epoch": 1.01, + "learning_rate": 7.0421976947816475e-06, + "loss": 3.3169, + "step": 2624000 + }, + { + "epoch": 1.01, + "learning_rate": 7.033811747271128e-06, + "loss": 3.3374, + "step": 2624512 + }, + { + "epoch": 1.01, + "learning_rate": 7.025425799760607e-06, + "loss": 3.3267, + "step": 2625024 + }, + { + "epoch": 1.01, + "learning_rate": 7.017039852250087e-06, + "loss": 3.326, + "step": 2625536 + }, + { + "epoch": 1.01, + "learning_rate": 7.008653904739567e-06, + "loss": 3.3265, + "step": 2626048 + }, + { + "epoch": 1.01, + "learning_rate": 7.000267957229048e-06, + "loss": 3.329, + "step": 2626560 + }, + { + "epoch": 1.01, + "learning_rate": 6.991882009718527e-06, + "loss": 3.313, + "step": 2627072 + }, + { + "epoch": 1.01, + "learning_rate": 6.983512441011739e-06, + "loss": 3.3221, + "step": 2627584 + }, + { + "epoch": 1.01, + "learning_rate": 6.975126493501219e-06, + "loss": 3.3296, + "step": 2628096 + }, + { + "epoch": 1.01, + "learning_rate": 6.966740545990698e-06, + "loss": 3.3334, + "step": 2628608 + }, + { + "epoch": 1.01, + "learning_rate": 6.958354598480178e-06, + "loss": 3.3208, + "step": 2629120 + }, + { + "epoch": 1.01, + "learning_rate": 6.9499850297733895e-06, + "loss": 3.3224, + "step": 2629632 + }, + { + "epoch": 1.01, + "learning_rate": 6.94159908226287e-06, + "loss": 3.3209, + "step": 2630144 + }, + { + "epoch": 1.01, + "learning_rate": 6.9332131347523494e-06, + "loss": 3.3242, + "step": 2630656 + }, + { + "epoch": 1.01, + "learning_rate": 6.924827187241829e-06, + "loss": 3.3285, + "step": 2631168 + }, + { + "epoch": 1.01, + "learning_rate": 6.916457618535041e-06, + "loss": 3.3297, + "step": 2631680 + }, + { + "epoch": 1.01, + "learning_rate": 6.908071671024521e-06, + "loss": 3.3385, + "step": 2632192 + }, + { + "epoch": 1.01, + "learning_rate": 6.899685723514e-06, + "loss": 3.3324, + "step": 2632704 + }, + { + "epoch": 1.01, + "learning_rate": 6.891299776003481e-06, + "loss": 3.3342, + "step": 2633216 + }, + { + "epoch": 1.01, + "learning_rate": 6.8829302072966925e-06, + "loss": 3.3213, + "step": 2633728 + }, + { + "epoch": 1.01, + "learning_rate": 6.874544259786171e-06, + "loss": 3.3319, + "step": 2634240 + }, + { + "epoch": 1.01, + "learning_rate": 6.866158312275652e-06, + "loss": 3.3319, + "step": 2634752 + }, + { + "epoch": 1.01, + "learning_rate": 6.8577723647651316e-06, + "loss": 3.3191, + "step": 2635264 + }, + { + "epoch": 1.01, + "learning_rate": 6.849402796058343e-06, + "loss": 3.3312, + "step": 2635776 + }, + { + "epoch": 1.01, + "learning_rate": 6.841016848547822e-06, + "loss": 3.329, + "step": 2636288 + }, + { + "epoch": 1.01, + "learning_rate": 6.832630901037303e-06, + "loss": 3.3361, + "step": 2636800 + }, + { + "epoch": 1.01, + "learning_rate": 6.824244953526783e-06, + "loss": 3.3286, + "step": 2637312 + }, + { + "epoch": 1.01, + "learning_rate": 6.815875384819995e-06, + "loss": 3.3141, + "step": 2637824 + }, + { + "epoch": 1.01, + "learning_rate": 6.807489437309474e-06, + "loss": 3.3203, + "step": 2638336 + }, + { + "epoch": 1.01, + "learning_rate": 6.799103489798954e-06, + "loss": 3.3361, + "step": 2638848 + }, + { + "epoch": 1.01, + "learning_rate": 6.7907175422884346e-06, + "loss": 3.3325, + "step": 2639360 + }, + { + "epoch": 1.01, + "learning_rate": 6.7823479735816445e-06, + "loss": 3.3302, + "step": 2639872 + }, + { + "epoch": 1.01, + "learning_rate": 6.7739620260711245e-06, + "loss": 3.3402, + "step": 2640384 + }, + { + "epoch": 1.02, + "learning_rate": 6.765592457364336e-06, + "loss": 3.3375, + "step": 2640896 + }, + { + "epoch": 1.02, + "learning_rate": 6.757206509853817e-06, + "loss": 3.3179, + "step": 2641408 + }, + { + "epoch": 1.02, + "learning_rate": 6.748820562343296e-06, + "loss": 3.3317, + "step": 2641920 + }, + { + "epoch": 1.02, + "learning_rate": 6.740434614832776e-06, + "loss": 3.3305, + "step": 2642432 + }, + { + "epoch": 1.02, + "learning_rate": 6.732048667322256e-06, + "loss": 3.3262, + "step": 2642944 + }, + { + "epoch": 1.02, + "learning_rate": 6.723662719811735e-06, + "loss": 3.3414, + "step": 2643456 + }, + { + "epoch": 1.02, + "learning_rate": 6.715276772301216e-06, + "loss": 3.3264, + "step": 2643968 + }, + { + "epoch": 1.02, + "learning_rate": 6.706890824790696e-06, + "loss": 3.3224, + "step": 2644480 + }, + { + "epoch": 1.02, + "learning_rate": 6.6985212560839074e-06, + "loss": 3.3266, + "step": 2644992 + }, + { + "epoch": 1.02, + "learning_rate": 6.6901353085733865e-06, + "loss": 3.3349, + "step": 2645504 + }, + { + "epoch": 1.02, + "learning_rate": 6.6817493610628665e-06, + "loss": 3.3339, + "step": 2646016 + }, + { + "epoch": 1.02, + "learning_rate": 6.673363413552347e-06, + "loss": 3.3286, + "step": 2646528 + }, + { + "epoch": 1.02, + "learning_rate": 6.664993844845559e-06, + "loss": 3.3194, + "step": 2647040 + }, + { + "epoch": 1.02, + "learning_rate": 6.656607897335038e-06, + "loss": 3.3206, + "step": 2647552 + }, + { + "epoch": 1.02, + "learning_rate": 6.648221949824518e-06, + "loss": 3.3414, + "step": 2648064 + }, + { + "epoch": 1.02, + "learning_rate": 6.639836002313998e-06, + "loss": 3.3138, + "step": 2648576 + }, + { + "epoch": 1.02, + "learning_rate": 6.631466433607209e-06, + "loss": 3.3284, + "step": 2649088 + }, + { + "epoch": 1.02, + "learning_rate": 6.623080486096689e-06, + "loss": 3.3331, + "step": 2649600 + }, + { + "epoch": 1.02, + "learning_rate": 6.6146945385861695e-06, + "loss": 3.3275, + "step": 2650112 + }, + { + "epoch": 1.02, + "learning_rate": 6.606308591075648e-06, + "loss": 3.3223, + "step": 2650624 + }, + { + "epoch": 1.02, + "learning_rate": 6.597939022368859e-06, + "loss": 3.3327, + "step": 2651136 + }, + { + "epoch": 1.02, + "learning_rate": 6.58955307485834e-06, + "loss": 3.3265, + "step": 2651648 + }, + { + "epoch": 1.02, + "learning_rate": 6.58116712734782e-06, + "loss": 3.3305, + "step": 2652160 + }, + { + "epoch": 1.02, + "learning_rate": 6.572781179837299e-06, + "loss": 3.3269, + "step": 2652672 + }, + { + "epoch": 1.02, + "learning_rate": 6.564411611130511e-06, + "loss": 3.3257, + "step": 2653184 + }, + { + "epoch": 1.02, + "learning_rate": 6.556025663619991e-06, + "loss": 3.3356, + "step": 2653696 + }, + { + "epoch": 1.02, + "learning_rate": 6.547639716109472e-06, + "loss": 3.3388, + "step": 2654208 + }, + { + "epoch": 1.02, + "learning_rate": 6.539253768598951e-06, + "loss": 3.3325, + "step": 2654720 + }, + { + "epoch": 1.02, + "learning_rate": 6.530884199892162e-06, + "loss": 3.3213, + "step": 2655232 + }, + { + "epoch": 1.02, + "learning_rate": 6.522498252381642e-06, + "loss": 3.3286, + "step": 2655744 + }, + { + "epoch": 1.02, + "learning_rate": 6.5141123048711215e-06, + "loss": 3.3236, + "step": 2656256 + }, + { + "epoch": 1.02, + "learning_rate": 6.5057263573606014e-06, + "loss": 3.3154, + "step": 2656768 + }, + { + "epoch": 1.02, + "learning_rate": 6.497356788653813e-06, + "loss": 3.3309, + "step": 2657280 + }, + { + "epoch": 1.02, + "learning_rate": 6.488970841143294e-06, + "loss": 3.3217, + "step": 2657792 + }, + { + "epoch": 1.02, + "learning_rate": 6.480584893632773e-06, + "loss": 3.3312, + "step": 2658304 + }, + { + "epoch": 1.02, + "learning_rate": 6.472198946122253e-06, + "loss": 3.3214, + "step": 2658816 + }, + { + "epoch": 1.02, + "learning_rate": 6.463829377415465e-06, + "loss": 3.3308, + "step": 2659328 + }, + { + "epoch": 1.02, + "learning_rate": 6.4554434299049445e-06, + "loss": 3.3169, + "step": 2659840 + }, + { + "epoch": 1.02, + "learning_rate": 6.447057482394424e-06, + "loss": 3.3253, + "step": 2660352 + }, + { + "epoch": 1.02, + "learning_rate": 6.4386715348839044e-06, + "loss": 3.3201, + "step": 2660864 + }, + { + "epoch": 1.02, + "learning_rate": 6.430301966177116e-06, + "loss": 3.3355, + "step": 2661376 + }, + { + "epoch": 1.02, + "learning_rate": 6.421916018666594e-06, + "loss": 3.3344, + "step": 2661888 + }, + { + "epoch": 1.02, + "learning_rate": 6.413530071156075e-06, + "loss": 3.3283, + "step": 2662400 + }, + { + "epoch": 1.02, + "learning_rate": 6.405144123645555e-06, + "loss": 3.3187, + "step": 2662912 + }, + { + "epoch": 1.02, + "learning_rate": 6.396774554938767e-06, + "loss": 3.3259, + "step": 2663424 + }, + { + "epoch": 1.02, + "learning_rate": 6.388388607428246e-06, + "loss": 3.3374, + "step": 2663936 + }, + { + "epoch": 1.02, + "learning_rate": 6.380002659917726e-06, + "loss": 3.3345, + "step": 2664448 + }, + { + "epoch": 1.02, + "learning_rate": 6.371616712407207e-06, + "loss": 3.3292, + "step": 2664960 + }, + { + "epoch": 1.02, + "learning_rate": 6.363247143700418e-06, + "loss": 3.3397, + "step": 2665472 + }, + { + "epoch": 1.02, + "learning_rate": 6.354861196189897e-06, + "loss": 3.3282, + "step": 2665984 + }, + { + "epoch": 1.02, + "learning_rate": 6.346475248679377e-06, + "loss": 3.3311, + "step": 2666496 + }, + { + "epoch": 1.02, + "learning_rate": 6.338105679972589e-06, + "loss": 3.3236, + "step": 2667008 + }, + { + "epoch": 1.02, + "learning_rate": 6.329719732462068e-06, + "loss": 3.3274, + "step": 2667520 + }, + { + "epoch": 1.02, + "learning_rate": 6.321333784951548e-06, + "loss": 3.3278, + "step": 2668032 + }, + { + "epoch": 1.02, + "learning_rate": 6.312947837441029e-06, + "loss": 3.3163, + "step": 2668544 + }, + { + "epoch": 1.02, + "learning_rate": 6.3045782687342405e-06, + "loss": 3.3268, + "step": 2669056 + }, + { + "epoch": 1.02, + "learning_rate": 6.2961923212237196e-06, + "loss": 3.3274, + "step": 2669568 + }, + { + "epoch": 1.02, + "learning_rate": 6.2878063737131995e-06, + "loss": 3.3284, + "step": 2670080 + }, + { + "epoch": 1.02, + "learning_rate": 6.2794204262026795e-06, + "loss": 3.3189, + "step": 2670592 + }, + { + "epoch": 1.02, + "learning_rate": 6.271050857495891e-06, + "loss": 3.3215, + "step": 2671104 + }, + { + "epoch": 1.03, + "eval_loss": 3.867112159729004, + "eval_runtime": 308.1767, + "eval_samples_per_second": 1238.221, + "eval_steps_per_second": 38.695, + "step": 2671200 + }, + { + "epoch": 0.0, + "learning_rate": 6.26266490998537e-06, + "loss": 3.3165, + "step": 2671616 + }, + { + "epoch": 0.0, + "learning_rate": 6.254278962474851e-06, + "loss": 3.3229, + "step": 2672128 + }, + { + "epoch": 0.0, + "learning_rate": 6.24589301496433e-06, + "loss": 3.3312, + "step": 2672640 + }, + { + "epoch": 0.0, + "learning_rate": 6.237507067453811e-06, + "loss": 3.3251, + "step": 2673152 + }, + { + "epoch": 0.0, + "learning_rate": 6.229137498747022e-06, + "loss": 3.336, + "step": 2673664 + }, + { + "epoch": 0.0, + "learning_rate": 6.220751551236502e-06, + "loss": 3.3169, + "step": 2674176 + }, + { + "epoch": 0.0, + "learning_rate": 6.212365603725982e-06, + "loss": 3.3242, + "step": 2674688 + }, + { + "epoch": 0.0, + "learning_rate": 6.203979656215462e-06, + "loss": 3.3182, + "step": 2675200 + }, + { + "epoch": 0.0, + "learning_rate": 6.195610087508673e-06, + "loss": 3.3313, + "step": 2675712 + }, + { + "epoch": 0.0, + "learning_rate": 6.187224139998152e-06, + "loss": 3.3314, + "step": 2676224 + }, + { + "epoch": 0.0, + "learning_rate": 6.178838192487633e-06, + "loss": 3.3278, + "step": 2676736 + }, + { + "epoch": 0.0, + "learning_rate": 6.170468623780844e-06, + "loss": 3.3242, + "step": 2677248 + }, + { + "epoch": 0.0, + "learning_rate": 6.162082676270324e-06, + "loss": 3.3138, + "step": 2677760 + }, + { + "epoch": 0.0, + "learning_rate": 6.153696728759804e-06, + "loss": 3.3169, + "step": 2678272 + }, + { + "epoch": 0.0, + "learning_rate": 6.145310781249284e-06, + "loss": 3.3232, + "step": 2678784 + }, + { + "epoch": 0.0, + "learning_rate": 6.136941212542495e-06, + "loss": 3.3225, + "step": 2679296 + }, + { + "epoch": 0.0, + "learning_rate": 6.128555265031975e-06, + "loss": 3.3174, + "step": 2679808 + }, + { + "epoch": 0.0, + "learning_rate": 6.1201693175214545e-06, + "loss": 3.3228, + "step": 2680320 + }, + { + "epoch": 0.0, + "learning_rate": 6.1117833700109345e-06, + "loss": 3.3174, + "step": 2680832 + }, + { + "epoch": 0.0, + "learning_rate": 6.103413801304146e-06, + "loss": 3.3492, + "step": 2681344 + }, + { + "epoch": 0.0, + "learning_rate": 6.095027853793626e-06, + "loss": 3.3251, + "step": 2681856 + }, + { + "epoch": 0.0, + "learning_rate": 6.086641906283106e-06, + "loss": 3.3234, + "step": 2682368 + }, + { + "epoch": 0.0, + "learning_rate": 6.078255958772586e-06, + "loss": 3.3279, + "step": 2682880 + }, + { + "epoch": 0.0, + "learning_rate": 6.069886390065798e-06, + "loss": 3.3303, + "step": 2683392 + }, + { + "epoch": 0.0, + "learning_rate": 6.061500442555277e-06, + "loss": 3.317, + "step": 2683904 + }, + { + "epoch": 0.0, + "learning_rate": 6.0531144950447575e-06, + "loss": 3.3293, + "step": 2684416 + }, + { + "epoch": 0.0, + "learning_rate": 6.044728547534237e-06, + "loss": 3.3221, + "step": 2684928 + }, + { + "epoch": 0.0, + "learning_rate": 6.036358978827448e-06, + "loss": 3.3236, + "step": 2685440 + }, + { + "epoch": 0.0, + "learning_rate": 6.027973031316928e-06, + "loss": 3.3152, + "step": 2685952 + }, + { + "epoch": 0.01, + "learning_rate": 6.019587083806408e-06, + "loss": 3.3253, + "step": 2686464 + }, + { + "epoch": 0.01, + "learning_rate": 6.011201136295888e-06, + "loss": 3.3385, + "step": 2686976 + }, + { + "epoch": 0.01, + "learning_rate": 6.002831567589099e-06, + "loss": 3.3265, + "step": 2687488 + }, + { + "epoch": 0.01, + "learning_rate": 5.99444562007858e-06, + "loss": 3.3297, + "step": 2688000 + }, + { + "epoch": 0.01, + "learning_rate": 5.986059672568059e-06, + "loss": 3.3272, + "step": 2688512 + }, + { + "epoch": 0.01, + "learning_rate": 5.97767372505754e-06, + "loss": 3.3204, + "step": 2689024 + }, + { + "epoch": 0.01, + "learning_rate": 5.96930415635075e-06, + "loss": 3.3309, + "step": 2689536 + }, + { + "epoch": 0.01, + "learning_rate": 5.96091820884023e-06, + "loss": 3.3118, + "step": 2690048 + }, + { + "epoch": 0.01, + "learning_rate": 5.95253226132971e-06, + "loss": 3.3263, + "step": 2690560 + }, + { + "epoch": 0.01, + "learning_rate": 5.9441463138191894e-06, + "loss": 3.3115, + "step": 2691072 + }, + { + "epoch": 0.01, + "learning_rate": 5.935776745112401e-06, + "loss": 3.3236, + "step": 2691584 + }, + { + "epoch": 0.01, + "learning_rate": 5.927407176405613e-06, + "loss": 3.3202, + "step": 2692096 + }, + { + "epoch": 0.01, + "learning_rate": 5.919021228895093e-06, + "loss": 3.3325, + "step": 2692608 + }, + { + "epoch": 0.01, + "learning_rate": 5.910635281384573e-06, + "loss": 3.3259, + "step": 2693120 + }, + { + "epoch": 0.01, + "learning_rate": 5.902249333874053e-06, + "loss": 3.3184, + "step": 2693632 + }, + { + "epoch": 0.01, + "learning_rate": 5.8938633863635325e-06, + "loss": 3.329, + "step": 2694144 + }, + { + "epoch": 0.01, + "learning_rate": 5.8854774388530125e-06, + "loss": 3.3211, + "step": 2694656 + }, + { + "epoch": 0.01, + "learning_rate": 5.8770914913424924e-06, + "loss": 3.3245, + "step": 2695168 + }, + { + "epoch": 0.01, + "learning_rate": 5.8687055438319716e-06, + "loss": 3.317, + "step": 2695680 + }, + { + "epoch": 0.01, + "learning_rate": 5.860335975125183e-06, + "loss": 3.3102, + "step": 2696192 + }, + { + "epoch": 0.01, + "learning_rate": 5.851950027614663e-06, + "loss": 3.3249, + "step": 2696704 + }, + { + "epoch": 0.01, + "learning_rate": 5.843564080104143e-06, + "loss": 3.325, + "step": 2697216 + }, + { + "epoch": 0.01, + "learning_rate": 5.835178132593623e-06, + "loss": 3.3237, + "step": 2697728 + }, + { + "epoch": 0.01, + "learning_rate": 5.826808563886835e-06, + "loss": 3.31, + "step": 2698240 + }, + { + "epoch": 0.01, + "learning_rate": 5.818422616376315e-06, + "loss": 3.3301, + "step": 2698752 + }, + { + "epoch": 0.01, + "learning_rate": 5.810036668865795e-06, + "loss": 3.3062, + "step": 2699264 + }, + { + "epoch": 0.01, + "learning_rate": 5.8016507213552746e-06, + "loss": 3.3353, + "step": 2699776 + }, + { + "epoch": 0.01, + "learning_rate": 5.793281152648486e-06, + "loss": 3.3097, + "step": 2700288 + }, + { + "epoch": 0.01, + "learning_rate": 5.784895205137965e-06, + "loss": 3.3252, + "step": 2700800 + }, + { + "epoch": 0.01, + "learning_rate": 5.776509257627445e-06, + "loss": 3.319, + "step": 2701312 + }, + { + "epoch": 0.01, + "learning_rate": 5.768123310116925e-06, + "loss": 3.3186, + "step": 2701824 + }, + { + "epoch": 0.01, + "learning_rate": 5.759753741410136e-06, + "loss": 3.3153, + "step": 2702336 + }, + { + "epoch": 0.01, + "learning_rate": 5.751367793899617e-06, + "loss": 3.326, + "step": 2702848 + }, + { + "epoch": 0.01, + "learning_rate": 5.742981846389097e-06, + "loss": 3.3025, + "step": 2703360 + }, + { + "epoch": 0.01, + "learning_rate": 5.734595898878577e-06, + "loss": 3.3091, + "step": 2703872 + }, + { + "epoch": 0.01, + "learning_rate": 5.7262263301717875e-06, + "loss": 3.325, + "step": 2704384 + }, + { + "epoch": 0.01, + "learning_rate": 5.717840382661268e-06, + "loss": 3.3218, + "step": 2704896 + }, + { + "epoch": 0.01, + "learning_rate": 5.7094544351507474e-06, + "loss": 3.3157, + "step": 2705408 + }, + { + "epoch": 0.01, + "learning_rate": 5.701068487640227e-06, + "loss": 3.315, + "step": 2705920 + }, + { + "epoch": 0.01, + "learning_rate": 5.692698918933439e-06, + "loss": 3.3076, + "step": 2706432 + }, + { + "epoch": 0.01, + "learning_rate": 5.684312971422918e-06, + "loss": 3.3144, + "step": 2706944 + }, + { + "epoch": 0.01, + "learning_rate": 5.675927023912399e-06, + "loss": 3.3221, + "step": 2707456 + }, + { + "epoch": 0.01, + "learning_rate": 5.667541076401878e-06, + "loss": 3.3205, + "step": 2707968 + }, + { + "epoch": 0.01, + "learning_rate": 5.65917150769509e-06, + "loss": 3.3311, + "step": 2708480 + }, + { + "epoch": 0.01, + "learning_rate": 5.65078556018457e-06, + "loss": 3.3246, + "step": 2708992 + }, + { + "epoch": 0.01, + "learning_rate": 5.64239961267405e-06, + "loss": 3.3283, + "step": 2709504 + }, + { + "epoch": 0.01, + "learning_rate": 5.6340136651635295e-06, + "loss": 3.3116, + "step": 2710016 + }, + { + "epoch": 0.01, + "learning_rate": 5.62564409645674e-06, + "loss": 3.323, + "step": 2710528 + }, + { + "epoch": 0.01, + "learning_rate": 5.617258148946221e-06, + "loss": 3.3232, + "step": 2711040 + }, + { + "epoch": 0.01, + "learning_rate": 5.6088722014357e-06, + "loss": 3.3089, + "step": 2711552 + }, + { + "epoch": 0.01, + "learning_rate": 5.600486253925181e-06, + "loss": 3.3271, + "step": 2712064 + }, + { + "epoch": 0.01, + "learning_rate": 5.592116685218392e-06, + "loss": 3.318, + "step": 2712576 + }, + { + "epoch": 0.01, + "learning_rate": 5.583730737707872e-06, + "loss": 3.3271, + "step": 2713088 + }, + { + "epoch": 0.01, + "learning_rate": 5.575344790197352e-06, + "loss": 3.3195, + "step": 2713600 + }, + { + "epoch": 0.01, + "learning_rate": 5.566958842686832e-06, + "loss": 3.3061, + "step": 2714112 + }, + { + "epoch": 0.01, + "learning_rate": 5.558589273980043e-06, + "loss": 3.3165, + "step": 2714624 + }, + { + "epoch": 0.01, + "learning_rate": 5.5502033264695225e-06, + "loss": 3.3224, + "step": 2715136 + }, + { + "epoch": 0.01, + "learning_rate": 5.541817378959003e-06, + "loss": 3.3251, + "step": 2715648 + }, + { + "epoch": 0.01, + "learning_rate": 5.533431431448482e-06, + "loss": 3.3241, + "step": 2716160 + }, + { + "epoch": 0.01, + "learning_rate": 5.525061862741694e-06, + "loss": 3.3244, + "step": 2716672 + }, + { + "epoch": 0.02, + "learning_rate": 5.516675915231174e-06, + "loss": 3.3321, + "step": 2717184 + }, + { + "epoch": 0.02, + "learning_rate": 5.508289967720654e-06, + "loss": 3.309, + "step": 2717696 + }, + { + "epoch": 0.02, + "learning_rate": 5.499920399013865e-06, + "loss": 3.3244, + "step": 2718208 + }, + { + "epoch": 0.02, + "learning_rate": 5.4915344515033455e-06, + "loss": 3.3184, + "step": 2718720 + }, + { + "epoch": 0.02, + "learning_rate": 5.483148503992825e-06, + "loss": 3.3188, + "step": 2719232 + }, + { + "epoch": 0.02, + "learning_rate": 5.4747625564823046e-06, + "loss": 3.33, + "step": 2719744 + }, + { + "epoch": 0.02, + "learning_rate": 5.466392987775516e-06, + "loss": 3.322, + "step": 2720256 + }, + { + "epoch": 0.02, + "learning_rate": 5.458007040264996e-06, + "loss": 3.311, + "step": 2720768 + }, + { + "epoch": 0.02, + "learning_rate": 5.449621092754476e-06, + "loss": 3.3201, + "step": 2721280 + }, + { + "epoch": 0.02, + "learning_rate": 5.441235145243956e-06, + "loss": 3.324, + "step": 2721792 + }, + { + "epoch": 0.02, + "learning_rate": 5.432865576537168e-06, + "loss": 3.3257, + "step": 2722304 + }, + { + "epoch": 0.02, + "learning_rate": 5.424479629026647e-06, + "loss": 3.3191, + "step": 2722816 + }, + { + "epoch": 0.02, + "learning_rate": 5.416093681516128e-06, + "loss": 3.3127, + "step": 2723328 + }, + { + "epoch": 0.02, + "learning_rate": 5.407707734005607e-06, + "loss": 3.3159, + "step": 2723840 + }, + { + "epoch": 0.02, + "learning_rate": 5.399338165298818e-06, + "loss": 3.3314, + "step": 2724352 + }, + { + "epoch": 0.02, + "learning_rate": 5.390952217788298e-06, + "loss": 3.3055, + "step": 2724864 + }, + { + "epoch": 0.02, + "learning_rate": 5.382566270277778e-06, + "loss": 3.3183, + "step": 2725376 + }, + { + "epoch": 0.02, + "learning_rate": 5.374180322767258e-06, + "loss": 3.3236, + "step": 2725888 + }, + { + "epoch": 0.02, + "learning_rate": 5.365810754060469e-06, + "loss": 3.3228, + "step": 2726400 + }, + { + "epoch": 0.02, + "learning_rate": 5.35742480654995e-06, + "loss": 3.3134, + "step": 2726912 + }, + { + "epoch": 0.02, + "learning_rate": 5.349038859039429e-06, + "loss": 3.3248, + "step": 2727424 + }, + { + "epoch": 0.02, + "learning_rate": 5.34065291152891e-06, + "loss": 3.3173, + "step": 2727936 + }, + { + "epoch": 0.02, + "learning_rate": 5.3322833428221205e-06, + "loss": 3.3182, + "step": 2728448 + }, + { + "epoch": 0.02, + "learning_rate": 5.3238973953116005e-06, + "loss": 3.3192, + "step": 2728960 + }, + { + "epoch": 0.02, + "learning_rate": 5.3155114478010804e-06, + "loss": 3.3169, + "step": 2729472 + }, + { + "epoch": 0.02, + "learning_rate": 5.3071255002905596e-06, + "loss": 3.3307, + "step": 2729984 + }, + { + "epoch": 0.02, + "learning_rate": 5.298755931583772e-06, + "loss": 3.3239, + "step": 2730496 + }, + { + "epoch": 0.02, + "learning_rate": 5.290369984073251e-06, + "loss": 3.325, + "step": 2731008 + }, + { + "epoch": 0.02, + "learning_rate": 5.281984036562732e-06, + "loss": 3.3133, + "step": 2731520 + }, + { + "epoch": 0.02, + "learning_rate": 5.273598089052211e-06, + "loss": 3.3179, + "step": 2732032 + }, + { + "epoch": 0.02, + "learning_rate": 5.265228520345423e-06, + "loss": 3.3174, + "step": 2732544 + }, + { + "epoch": 0.02, + "learning_rate": 5.256842572834903e-06, + "loss": 3.3065, + "step": 2733056 + }, + { + "epoch": 0.02, + "learning_rate": 5.248456625324383e-06, + "loss": 3.3183, + "step": 2733568 + }, + { + "epoch": 0.02, + "learning_rate": 5.2400706778138626e-06, + "loss": 3.3156, + "step": 2734080 + }, + { + "epoch": 0.02, + "learning_rate": 5.231701109107074e-06, + "loss": 3.3213, + "step": 2734592 + }, + { + "epoch": 0.02, + "learning_rate": 5.223315161596553e-06, + "loss": 3.3148, + "step": 2735104 + }, + { + "epoch": 0.02, + "learning_rate": 5.214945592889765e-06, + "loss": 3.321, + "step": 2735616 + }, + { + "epoch": 0.02, + "learning_rate": 5.206559645379245e-06, + "loss": 3.3027, + "step": 2736128 + }, + { + "epoch": 0.02, + "learning_rate": 5.198173697868725e-06, + "loss": 3.3163, + "step": 2736640 + }, + { + "epoch": 0.02, + "learning_rate": 5.189787750358205e-06, + "loss": 3.316, + "step": 2737152 + }, + { + "epoch": 0.02, + "learning_rate": 5.181401802847685e-06, + "loss": 3.324, + "step": 2737664 + }, + { + "epoch": 0.02, + "learning_rate": 5.173015855337165e-06, + "loss": 3.3235, + "step": 2738176 + }, + { + "epoch": 0.02, + "learning_rate": 5.164629907826645e-06, + "loss": 3.3241, + "step": 2738688 + }, + { + "epoch": 0.02, + "learning_rate": 5.156243960316124e-06, + "loss": 3.3082, + "step": 2739200 + }, + { + "epoch": 0.02, + "learning_rate": 5.1478743916093354e-06, + "loss": 3.3204, + "step": 2739712 + }, + { + "epoch": 0.02, + "learning_rate": 5.139488444098815e-06, + "loss": 3.3237, + "step": 2740224 + }, + { + "epoch": 0.02, + "learning_rate": 5.131102496588295e-06, + "loss": 3.3259, + "step": 2740736 + }, + { + "epoch": 0.02, + "learning_rate": 5.122716549077775e-06, + "loss": 3.323, + "step": 2741248 + }, + { + "epoch": 0.02, + "learning_rate": 5.114346980370987e-06, + "loss": 3.3258, + "step": 2741760 + }, + { + "epoch": 0.02, + "learning_rate": 5.105961032860467e-06, + "loss": 3.3205, + "step": 2742272 + }, + { + "epoch": 0.02, + "learning_rate": 5.097575085349947e-06, + "loss": 3.326, + "step": 2742784 + }, + { + "epoch": 0.02, + "learning_rate": 5.089189137839427e-06, + "loss": 3.3137, + "step": 2743296 + }, + { + "epoch": 0.02, + "learning_rate": 5.0808195691326384e-06, + "loss": 3.3203, + "step": 2743808 + }, + { + "epoch": 0.02, + "learning_rate": 5.0724336216221175e-06, + "loss": 3.3207, + "step": 2744320 + }, + { + "epoch": 0.02, + "learning_rate": 5.0640476741115975e-06, + "loss": 3.3089, + "step": 2744832 + }, + { + "epoch": 0.02, + "learning_rate": 5.055678105404809e-06, + "loss": 3.3166, + "step": 2745344 + }, + { + "epoch": 0.02, + "learning_rate": 5.047292157894288e-06, + "loss": 3.322, + "step": 2745856 + }, + { + "epoch": 0.02, + "learning_rate": 5.038906210383769e-06, + "loss": 3.3165, + "step": 2746368 + }, + { + "epoch": 0.02, + "learning_rate": 5.030520262873248e-06, + "loss": 3.3097, + "step": 2746880 + }, + { + "epoch": 0.02, + "learning_rate": 5.02215069416646e-06, + "loss": 3.3212, + "step": 2747392 + }, + { + "epoch": 0.03, + "eval_loss": 3.867042064666748, + "eval_runtime": 303.8938, + "eval_samples_per_second": 1255.672, + "eval_steps_per_second": 39.241, + "step": 2747520 + }, + { + "epoch": 1.0, + "learning_rate": 5.01376474665594e-06, + "loss": 3.3102, + "step": 2747904 + }, + { + "epoch": 1.0, + "learning_rate": 5.00537879914542e-06, + "loss": 3.3139, + "step": 2748416 + }, + { + "epoch": 1.0, + "learning_rate": 4.9969928516349e-06, + "loss": 3.3206, + "step": 2748928 + }, + { + "epoch": 1.0, + "learning_rate": 4.9886232829281105e-06, + "loss": 3.3188, + "step": 2749440 + }, + { + "epoch": 1.0, + "learning_rate": 4.980237335417591e-06, + "loss": 3.3304, + "step": 2749952 + }, + { + "epoch": 1.0, + "learning_rate": 4.97185138790707e-06, + "loss": 3.3103, + "step": 2750464 + }, + { + "epoch": 1.0, + "learning_rate": 4.963465440396551e-06, + "loss": 3.314, + "step": 2750976 + }, + { + "epoch": 1.0, + "learning_rate": 4.955095871689762e-06, + "loss": 3.3072, + "step": 2751488 + }, + { + "epoch": 1.0, + "learning_rate": 4.946709924179242e-06, + "loss": 3.3219, + "step": 2752000 + }, + { + "epoch": 1.0, + "learning_rate": 4.938323976668722e-06, + "loss": 3.3232, + "step": 2752512 + }, + { + "epoch": 1.0, + "learning_rate": 4.929938029158202e-06, + "loss": 3.313, + "step": 2753024 + }, + { + "epoch": 1.0, + "learning_rate": 4.9215684604514135e-06, + "loss": 3.3238, + "step": 2753536 + }, + { + "epoch": 1.0, + "learning_rate": 4.9131825129408926e-06, + "loss": 3.3034, + "step": 2754048 + }, + { + "epoch": 1.0, + "learning_rate": 4.904796565430373e-06, + "loss": 3.3102, + "step": 2754560 + }, + { + "epoch": 1.0, + "learning_rate": 4.8964106179198525e-06, + "loss": 3.3155, + "step": 2755072 + }, + { + "epoch": 1.0, + "learning_rate": 4.888041049213064e-06, + "loss": 3.3113, + "step": 2755584 + }, + { + "epoch": 1.0, + "learning_rate": 4.879655101702544e-06, + "loss": 3.311, + "step": 2756096 + }, + { + "epoch": 1.0, + "learning_rate": 4.871269154192024e-06, + "loss": 3.3141, + "step": 2756608 + }, + { + "epoch": 1.0, + "learning_rate": 4.862883206681504e-06, + "loss": 3.3126, + "step": 2757120 + }, + { + "epoch": 1.0, + "learning_rate": 4.854513637974716e-06, + "loss": 3.3397, + "step": 2757632 + }, + { + "epoch": 1.0, + "learning_rate": 4.846127690464195e-06, + "loss": 3.3181, + "step": 2758144 + }, + { + "epoch": 1.0, + "learning_rate": 4.837741742953675e-06, + "loss": 3.3134, + "step": 2758656 + }, + { + "epoch": 1.0, + "learning_rate": 4.8293557954431555e-06, + "loss": 3.3216, + "step": 2759168 + }, + { + "epoch": 1.0, + "learning_rate": 4.820986226736366e-06, + "loss": 3.3228, + "step": 2759680 + }, + { + "epoch": 1.0, + "learning_rate": 4.812600279225846e-06, + "loss": 3.3082, + "step": 2760192 + }, + { + "epoch": 1.0, + "learning_rate": 4.804214331715326e-06, + "loss": 3.3206, + "step": 2760704 + }, + { + "epoch": 1.0, + "learning_rate": 4.795828384204806e-06, + "loss": 3.312, + "step": 2761216 + }, + { + "epoch": 1.0, + "learning_rate": 4.787458815498017e-06, + "loss": 3.3147, + "step": 2761728 + }, + { + "epoch": 1.0, + "learning_rate": 4.779072867987498e-06, + "loss": 3.3075, + "step": 2762240 + }, + { + "epoch": 1.0, + "learning_rate": 4.770686920476977e-06, + "loss": 3.3167, + "step": 2762752 + }, + { + "epoch": 1.01, + "learning_rate": 4.762300972966457e-06, + "loss": 3.3312, + "step": 2763264 + }, + { + "epoch": 1.01, + "learning_rate": 4.7539314042596684e-06, + "loss": 3.3201, + "step": 2763776 + }, + { + "epoch": 1.01, + "learning_rate": 4.745545456749148e-06, + "loss": 3.3191, + "step": 2764288 + }, + { + "epoch": 1.01, + "learning_rate": 4.737159509238628e-06, + "loss": 3.3211, + "step": 2764800 + }, + { + "epoch": 1.01, + "learning_rate": 4.728773561728108e-06, + "loss": 3.3151, + "step": 2765312 + }, + { + "epoch": 1.01, + "learning_rate": 4.72040399302132e-06, + "loss": 3.3213, + "step": 2765824 + }, + { + "epoch": 1.01, + "learning_rate": 4.712018045510799e-06, + "loss": 3.3053, + "step": 2766336 + }, + { + "epoch": 1.01, + "learning_rate": 4.70363209800028e-06, + "loss": 3.3163, + "step": 2766848 + }, + { + "epoch": 1.01, + "learning_rate": 4.695246150489759e-06, + "loss": 3.3074, + "step": 2767360 + }, + { + "epoch": 1.01, + "learning_rate": 4.686876581782971e-06, + "loss": 3.3088, + "step": 2767872 + }, + { + "epoch": 1.01, + "learning_rate": 4.6784906342724506e-06, + "loss": 3.3128, + "step": 2768384 + }, + { + "epoch": 1.01, + "learning_rate": 4.6701046867619305e-06, + "loss": 3.3227, + "step": 2768896 + }, + { + "epoch": 1.01, + "learning_rate": 4.6617187392514105e-06, + "loss": 3.3156, + "step": 2769408 + }, + { + "epoch": 1.01, + "learning_rate": 4.653349170544621e-06, + "loss": 3.3124, + "step": 2769920 + }, + { + "epoch": 1.01, + "learning_rate": 4.644963223034102e-06, + "loss": 3.3202, + "step": 2770432 + }, + { + "epoch": 1.01, + "learning_rate": 4.636577275523581e-06, + "loss": 3.3128, + "step": 2770944 + }, + { + "epoch": 1.01, + "learning_rate": 4.628191328013062e-06, + "loss": 3.3152, + "step": 2771456 + }, + { + "epoch": 1.01, + "learning_rate": 4.619821759306273e-06, + "loss": 3.3103, + "step": 2771968 + }, + { + "epoch": 1.01, + "learning_rate": 4.611435811795753e-06, + "loss": 3.3014, + "step": 2772480 + }, + { + "epoch": 1.01, + "learning_rate": 4.603049864285233e-06, + "loss": 3.32, + "step": 2772992 + }, + { + "epoch": 1.01, + "learning_rate": 4.594663916774712e-06, + "loss": 3.3114, + "step": 2773504 + }, + { + "epoch": 1.01, + "learning_rate": 4.5862943480679234e-06, + "loss": 3.3185, + "step": 2774016 + }, + { + "epoch": 1.01, + "learning_rate": 4.577908400557403e-06, + "loss": 3.3059, + "step": 2774528 + }, + { + "epoch": 1.01, + "learning_rate": 4.569522453046883e-06, + "loss": 3.3155, + "step": 2775040 + }, + { + "epoch": 1.01, + "learning_rate": 4.561136505536363e-06, + "loss": 3.2976, + "step": 2775552 + }, + { + "epoch": 1.01, + "learning_rate": 4.552783315633307e-06, + "loss": 3.3247, + "step": 2776064 + }, + { + "epoch": 1.01, + "learning_rate": 4.544397368122786e-06, + "loss": 3.3021, + "step": 2776576 + }, + { + "epoch": 1.01, + "learning_rate": 4.5360114206122665e-06, + "loss": 3.3103, + "step": 2777088 + }, + { + "epoch": 1.01, + "learning_rate": 4.527625473101746e-06, + "loss": 3.3133, + "step": 2777600 + }, + { + "epoch": 1.01, + "learning_rate": 4.5192395255912264e-06, + "loss": 3.309, + "step": 2778112 + }, + { + "epoch": 1.01, + "learning_rate": 4.5108535780807055e-06, + "loss": 3.3092, + "step": 2778624 + }, + { + "epoch": 1.01, + "learning_rate": 4.5024676305701855e-06, + "loss": 3.3129, + "step": 2779136 + }, + { + "epoch": 1.01, + "learning_rate": 4.4940816830596655e-06, + "loss": 3.3014, + "step": 2779648 + }, + { + "epoch": 1.01, + "learning_rate": 4.485712114352877e-06, + "loss": 3.3003, + "step": 2780160 + }, + { + "epoch": 1.01, + "learning_rate": 4.477326166842357e-06, + "loss": 3.3151, + "step": 2780672 + }, + { + "epoch": 1.01, + "learning_rate": 4.468940219331837e-06, + "loss": 3.3124, + "step": 2781184 + }, + { + "epoch": 1.01, + "learning_rate": 4.460554271821317e-06, + "loss": 3.3043, + "step": 2781696 + }, + { + "epoch": 1.01, + "learning_rate": 4.452184703114528e-06, + "loss": 3.3103, + "step": 2782208 + }, + { + "epoch": 1.01, + "learning_rate": 4.4437987556040086e-06, + "loss": 3.2988, + "step": 2782720 + }, + { + "epoch": 1.01, + "learning_rate": 4.435412808093488e-06, + "loss": 3.3062, + "step": 2783232 + }, + { + "epoch": 1.01, + "learning_rate": 4.427026860582968e-06, + "loss": 3.3132, + "step": 2783744 + }, + { + "epoch": 1.01, + "learning_rate": 4.418657291876179e-06, + "loss": 3.3078, + "step": 2784256 + }, + { + "epoch": 1.01, + "learning_rate": 4.410271344365658e-06, + "loss": 3.3219, + "step": 2784768 + }, + { + "epoch": 1.01, + "learning_rate": 4.401885396855139e-06, + "loss": 3.3131, + "step": 2785280 + }, + { + "epoch": 1.01, + "learning_rate": 4.393499449344618e-06, + "loss": 3.3251, + "step": 2785792 + }, + { + "epoch": 1.01, + "learning_rate": 4.38512988063783e-06, + "loss": 3.3041, + "step": 2786304 + }, + { + "epoch": 1.01, + "learning_rate": 4.37674393312731e-06, + "loss": 3.3158, + "step": 2786816 + }, + { + "epoch": 1.01, + "learning_rate": 4.36835798561679e-06, + "loss": 3.3159, + "step": 2787328 + }, + { + "epoch": 1.01, + "learning_rate": 4.35997203810627e-06, + "loss": 3.2981, + "step": 2787840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3516024693994806e-06, + "loss": 3.3196, + "step": 2788352 + }, + { + "epoch": 1.01, + "learning_rate": 4.343216521888961e-06, + "loss": 3.3097, + "step": 2788864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3348305743784405e-06, + "loss": 3.3166, + "step": 2789376 + }, + { + "epoch": 1.01, + "learning_rate": 4.326444626867921e-06, + "loss": 3.3131, + "step": 2789888 + }, + { + "epoch": 1.01, + "learning_rate": 4.318075058161132e-06, + "loss": 3.2977, + "step": 2790400 + }, + { + "epoch": 1.01, + "learning_rate": 4.309689110650612e-06, + "loss": 3.3071, + "step": 2790912 + }, + { + "epoch": 1.01, + "learning_rate": 4.301303163140092e-06, + "loss": 3.3123, + "step": 2791424 + }, + { + "epoch": 1.01, + "learning_rate": 4.292917215629572e-06, + "loss": 3.3164, + "step": 2791936 + }, + { + "epoch": 1.01, + "learning_rate": 4.284547646922784e-06, + "loss": 3.3141, + "step": 2792448 + }, + { + "epoch": 1.01, + "learning_rate": 4.276161699412263e-06, + "loss": 3.3166, + "step": 2792960 + }, + { + "epoch": 1.02, + "learning_rate": 4.2677757519017435e-06, + "loss": 3.3203, + "step": 2793472 + }, + { + "epoch": 1.02, + "learning_rate": 4.259406183194954e-06, + "loss": 3.3032, + "step": 2793984 + }, + { + "epoch": 1.02, + "learning_rate": 4.251020235684434e-06, + "loss": 3.3136, + "step": 2794496 + }, + { + "epoch": 1.02, + "learning_rate": 4.242634288173914e-06, + "loss": 3.3087, + "step": 2795008 + }, + { + "epoch": 1.02, + "learning_rate": 4.234248340663394e-06, + "loss": 3.3155, + "step": 2795520 + }, + { + "epoch": 1.02, + "learning_rate": 4.225878771956605e-06, + "loss": 3.3228, + "step": 2796032 + }, + { + "epoch": 1.02, + "learning_rate": 4.217492824446086e-06, + "loss": 3.3083, + "step": 2796544 + }, + { + "epoch": 1.02, + "learning_rate": 4.209106876935566e-06, + "loss": 3.3074, + "step": 2797056 + }, + { + "epoch": 1.02, + "learning_rate": 4.200720929425045e-06, + "loss": 3.3097, + "step": 2797568 + }, + { + "epoch": 1.02, + "learning_rate": 4.1923513607182565e-06, + "loss": 3.312, + "step": 2798080 + }, + { + "epoch": 1.02, + "learning_rate": 4.183965413207736e-06, + "loss": 3.3214, + "step": 2798592 + }, + { + "epoch": 1.02, + "learning_rate": 4.175579465697216e-06, + "loss": 3.3082, + "step": 2799104 + }, + { + "epoch": 1.02, + "learning_rate": 4.167193518186696e-06, + "loss": 3.3065, + "step": 2799616 + }, + { + "epoch": 1.02, + "learning_rate": 4.158823949479908e-06, + "loss": 3.3036, + "step": 2800128 + }, + { + "epoch": 1.02, + "learning_rate": 4.150438001969387e-06, + "loss": 3.3228, + "step": 2800640 + }, + { + "epoch": 1.02, + "learning_rate": 4.142052054458868e-06, + "loss": 3.3, + "step": 2801152 + }, + { + "epoch": 1.02, + "learning_rate": 4.133666106948347e-06, + "loss": 3.3103, + "step": 2801664 + }, + { + "epoch": 1.02, + "learning_rate": 4.125296538241559e-06, + "loss": 3.3149, + "step": 2802176 + }, + { + "epoch": 1.02, + "learning_rate": 4.1169105907310386e-06, + "loss": 3.3119, + "step": 2802688 + }, + { + "epoch": 1.02, + "learning_rate": 4.1085246432205185e-06, + "loss": 3.3063, + "step": 2803200 + }, + { + "epoch": 1.02, + "learning_rate": 4.1001386957099985e-06, + "loss": 3.3178, + "step": 2803712 + }, + { + "epoch": 1.02, + "learning_rate": 4.091769127003209e-06, + "loss": 3.3093, + "step": 2804224 + }, + { + "epoch": 1.02, + "learning_rate": 4.08338317949269e-06, + "loss": 3.306, + "step": 2804736 + }, + { + "epoch": 1.02, + "learning_rate": 4.074997231982169e-06, + "loss": 3.3123, + "step": 2805248 + }, + { + "epoch": 1.02, + "learning_rate": 4.06661128447165e-06, + "loss": 3.3099, + "step": 2805760 + }, + { + "epoch": 1.02, + "learning_rate": 4.058241715764861e-06, + "loss": 3.3231, + "step": 2806272 + }, + { + "epoch": 1.02, + "learning_rate": 4.049855768254341e-06, + "loss": 3.3171, + "step": 2806784 + }, + { + "epoch": 1.02, + "learning_rate": 4.041469820743821e-06, + "loss": 3.3126, + "step": 2807296 + }, + { + "epoch": 1.02, + "learning_rate": 4.033083873233301e-06, + "loss": 3.3013, + "step": 2807808 + }, + { + "epoch": 1.02, + "learning_rate": 4.024714304526512e-06, + "loss": 3.3116, + "step": 2808320 + }, + { + "epoch": 1.02, + "learning_rate": 4.016328357015991e-06, + "loss": 3.3076, + "step": 2808832 + }, + { + "epoch": 1.02, + "learning_rate": 4.007942409505472e-06, + "loss": 3.2983, + "step": 2809344 + }, + { + "epoch": 1.02, + "learning_rate": 3.999556461994951e-06, + "loss": 3.3132, + "step": 2809856 + }, + { + "epoch": 1.02, + "learning_rate": 3.991186893288163e-06, + "loss": 3.3044, + "step": 2810368 + }, + { + "epoch": 1.02, + "learning_rate": 3.982800945777643e-06, + "loss": 3.3118, + "step": 2810880 + }, + { + "epoch": 1.02, + "learning_rate": 3.974414998267123e-06, + "loss": 3.3077, + "step": 2811392 + }, + { + "epoch": 1.02, + "learning_rate": 3.966029050756603e-06, + "loss": 3.3131, + "step": 2811904 + }, + { + "epoch": 1.02, + "learning_rate": 3.9576594820498144e-06, + "loss": 3.298, + "step": 2812416 + }, + { + "epoch": 1.02, + "learning_rate": 3.9492735345392936e-06, + "loss": 3.3079, + "step": 2812928 + }, + { + "epoch": 1.02, + "learning_rate": 3.9408875870287735e-06, + "loss": 3.3072, + "step": 2813440 + }, + { + "epoch": 1.02, + "learning_rate": 3.9325016395182535e-06, + "loss": 3.3115, + "step": 2813952 + }, + { + "epoch": 1.02, + "learning_rate": 3.924132070811465e-06, + "loss": 3.3138, + "step": 2814464 + }, + { + "epoch": 1.02, + "learning_rate": 3.915746123300945e-06, + "loss": 3.3184, + "step": 2814976 + }, + { + "epoch": 1.02, + "learning_rate": 3.907360175790425e-06, + "loss": 3.2985, + "step": 2815488 + }, + { + "epoch": 1.02, + "learning_rate": 3.898974228279905e-06, + "loss": 3.314, + "step": 2816000 + }, + { + "epoch": 1.02, + "learning_rate": 3.890604659573116e-06, + "loss": 3.3202, + "step": 2816512 + }, + { + "epoch": 1.02, + "learning_rate": 3.8822187120625966e-06, + "loss": 3.3133, + "step": 2817024 + }, + { + "epoch": 1.02, + "learning_rate": 3.873832764552076e-06, + "loss": 3.3156, + "step": 2817536 + }, + { + "epoch": 1.02, + "learning_rate": 3.865446817041556e-06, + "loss": 3.3188, + "step": 2818048 + }, + { + "epoch": 1.02, + "learning_rate": 3.857077248334767e-06, + "loss": 3.3123, + "step": 2818560 + }, + { + "epoch": 1.02, + "learning_rate": 3.848691300824247e-06, + "loss": 3.3179, + "step": 2819072 + }, + { + "epoch": 1.02, + "learning_rate": 3.840305353313727e-06, + "loss": 3.302, + "step": 2819584 + }, + { + "epoch": 1.02, + "learning_rate": 3.831919405803207e-06, + "loss": 3.3166, + "step": 2820096 + }, + { + "epoch": 1.02, + "learning_rate": 3.823549837096419e-06, + "loss": 3.3064, + "step": 2820608 + }, + { + "epoch": 1.02, + "learning_rate": 3.815163889585898e-06, + "loss": 3.3049, + "step": 2821120 + }, + { + "epoch": 1.02, + "learning_rate": 3.8067779420753783e-06, + "loss": 3.3092, + "step": 2821632 + }, + { + "epoch": 1.02, + "learning_rate": 3.798391994564858e-06, + "loss": 3.3078, + "step": 2822144 + }, + { + "epoch": 1.02, + "learning_rate": 3.79002242585807e-06, + "loss": 3.314, + "step": 2822656 + }, + { + "epoch": 1.02, + "learning_rate": 3.7816364783475494e-06, + "loss": 3.2983, + "step": 2823168 + }, + { + "epoch": 1.02, + "learning_rate": 3.773250530837029e-06, + "loss": 3.3149, + "step": 2823680 + }, + { + "epoch": 1.03, + "eval_loss": 3.8664727210998535, + "eval_runtime": 303.7228, + "eval_samples_per_second": 1256.379, + "eval_steps_per_second": 39.263, + "step": 2823840 + }, + { + "epoch": 0.0, + "learning_rate": 3.7648645833265093e-06, + "loss": 3.3028, + "step": 2824192 + }, + { + "epoch": 0.0, + "learning_rate": 3.756478635815989e-06, + "loss": 3.303, + "step": 2824704 + }, + { + "epoch": 0.0, + "learning_rate": 3.748092688305469e-06, + "loss": 3.3107, + "step": 2825216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7397067407949487e-06, + "loss": 3.3162, + "step": 2825728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7313371720881604e-06, + "loss": 3.3139, + "step": 2826240 + }, + { + "epoch": 0.0, + "learning_rate": 3.72295122457764e-06, + "loss": 3.3066, + "step": 2826752 + }, + { + "epoch": 0.0, + "learning_rate": 3.71456527706712e-06, + "loss": 3.3047, + "step": 2827264 + }, + { + "epoch": 0.0, + "learning_rate": 3.7061793295566e-06, + "loss": 3.3034, + "step": 2827776 + }, + { + "epoch": 0.0, + "learning_rate": 3.697809760849811e-06, + "loss": 3.3106, + "step": 2828288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6894238133392914e-06, + "loss": 3.3174, + "step": 2828800 + }, + { + "epoch": 0.0, + "learning_rate": 3.681037865828771e-06, + "loss": 3.3043, + "step": 2829312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6726519183182505e-06, + "loss": 3.3134, + "step": 2829824 + }, + { + "epoch": 0.0, + "learning_rate": 3.664282349611462e-06, + "loss": 3.3013, + "step": 2830336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6558964021009416e-06, + "loss": 3.3002, + "step": 2830848 + }, + { + "epoch": 0.0, + "learning_rate": 3.647510454590422e-06, + "loss": 3.3081, + "step": 2831360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6391408858836332e-06, + "loss": 3.3009, + "step": 2831872 + }, + { + "epoch": 0.0, + "learning_rate": 3.630754938373113e-06, + "loss": 3.3025, + "step": 2832384 + }, + { + "epoch": 0.0, + "learning_rate": 3.622368990862593e-06, + "loss": 3.3056, + "step": 2832896 + }, + { + "epoch": 0.0, + "learning_rate": 3.613983043352073e-06, + "loss": 3.3016, + "step": 2833408 + }, + { + "epoch": 0.0, + "learning_rate": 3.6056134746452843e-06, + "loss": 3.3286, + "step": 2833920 + }, + { + "epoch": 0.0, + "learning_rate": 3.5972275271347647e-06, + "loss": 3.3126, + "step": 2834432 + }, + { + "epoch": 0.0, + "learning_rate": 3.5888415796242442e-06, + "loss": 3.307, + "step": 2834944 + }, + { + "epoch": 0.0, + "learning_rate": 3.5804556321137238e-06, + "loss": 3.3105, + "step": 2835456 + }, + { + "epoch": 0.0, + "learning_rate": 3.5720860634069354e-06, + "loss": 3.317, + "step": 2835968 + }, + { + "epoch": 0.0, + "learning_rate": 3.563700115896415e-06, + "loss": 3.3001, + "step": 2836480 + }, + { + "epoch": 0.0, + "learning_rate": 3.5553141683858953e-06, + "loss": 3.3101, + "step": 2836992 + }, + { + "epoch": 0.0, + "learning_rate": 3.546928220875375e-06, + "loss": 3.3083, + "step": 2837504 + }, + { + "epoch": 0.0, + "learning_rate": 3.5385586521685865e-06, + "loss": 3.303, + "step": 2838016 + }, + { + "epoch": 0.0, + "learning_rate": 3.5301727046580664e-06, + "loss": 3.296, + "step": 2838528 + }, + { + "epoch": 0.0, + "learning_rate": 3.5217867571475464e-06, + "loss": 3.3115, + "step": 2839040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5134008096370263e-06, + "loss": 3.3222, + "step": 2839552 + }, + { + "epoch": 0.01, + "learning_rate": 3.505031240930238e-06, + "loss": 3.3107, + "step": 2840064 + }, + { + "epoch": 0.01, + "learning_rate": 3.4966452934197175e-06, + "loss": 3.3159, + "step": 2840576 + }, + { + "epoch": 0.01, + "learning_rate": 3.488259345909197e-06, + "loss": 3.3107, + "step": 2841088 + }, + { + "epoch": 0.01, + "learning_rate": 3.4798733983986774e-06, + "loss": 3.3035, + "step": 2841600 + }, + { + "epoch": 0.01, + "learning_rate": 3.4715038296918882e-06, + "loss": 3.3102, + "step": 2842112 + }, + { + "epoch": 0.01, + "learning_rate": 3.4631178821813686e-06, + "loss": 3.3022, + "step": 2842624 + }, + { + "epoch": 0.01, + "learning_rate": 3.454731934670848e-06, + "loss": 3.3029, + "step": 2843136 + }, + { + "epoch": 0.01, + "learning_rate": 3.4463459871603285e-06, + "loss": 3.2996, + "step": 2843648 + }, + { + "epoch": 0.01, + "learning_rate": 3.4379764184535397e-06, + "loss": 3.3021, + "step": 2844160 + }, + { + "epoch": 0.01, + "learning_rate": 3.4295904709430197e-06, + "loss": 3.305, + "step": 2844672 + }, + { + "epoch": 0.01, + "learning_rate": 3.421220902236231e-06, + "loss": 3.3142, + "step": 2845184 + }, + { + "epoch": 0.01, + "learning_rate": 3.4128349547257113e-06, + "loss": 3.3077, + "step": 2845696 + }, + { + "epoch": 0.01, + "learning_rate": 3.404449007215191e-06, + "loss": 3.3058, + "step": 2846208 + }, + { + "epoch": 0.01, + "learning_rate": 3.3960630597046703e-06, + "loss": 3.3124, + "step": 2846720 + }, + { + "epoch": 0.01, + "learning_rate": 3.3876771121941507e-06, + "loss": 3.307, + "step": 2847232 + }, + { + "epoch": 0.01, + "learning_rate": 3.3792911646836302e-06, + "loss": 3.3084, + "step": 2847744 + }, + { + "epoch": 0.01, + "learning_rate": 3.3709052171731106e-06, + "loss": 3.302, + "step": 2848256 + }, + { + "epoch": 0.01, + "learning_rate": 3.3625356484663214e-06, + "loss": 3.2929, + "step": 2848768 + }, + { + "epoch": 0.01, + "learning_rate": 3.354149700955802e-06, + "loss": 3.3119, + "step": 2849280 + }, + { + "epoch": 0.01, + "learning_rate": 3.3457637534452813e-06, + "loss": 3.3052, + "step": 2849792 + }, + { + "epoch": 0.01, + "learning_rate": 3.3373778059347613e-06, + "loss": 3.3123, + "step": 2850304 + }, + { + "epoch": 0.01, + "learning_rate": 3.329008237227973e-06, + "loss": 3.2968, + "step": 2850816 + }, + { + "epoch": 0.01, + "learning_rate": 3.3206222897174525e-06, + "loss": 3.3076, + "step": 2851328 + }, + { + "epoch": 0.01, + "learning_rate": 3.312236342206933e-06, + "loss": 3.2907, + "step": 2851840 + }, + { + "epoch": 0.01, + "learning_rate": 3.3038667735001436e-06, + "loss": 3.3156, + "step": 2852352 + }, + { + "epoch": 0.01, + "learning_rate": 3.295480825989624e-06, + "loss": 3.2946, + "step": 2852864 + }, + { + "epoch": 0.01, + "learning_rate": 3.2870948784791035e-06, + "loss": 3.3049, + "step": 2853376 + }, + { + "epoch": 0.01, + "learning_rate": 3.278708930968584e-06, + "loss": 3.3058, + "step": 2853888 + }, + { + "epoch": 0.01, + "learning_rate": 3.2703229834580634e-06, + "loss": 3.2967, + "step": 2854400 + }, + { + "epoch": 0.01, + "learning_rate": 3.261937035947543e-06, + "loss": 3.3011, + "step": 2854912 + }, + { + "epoch": 0.01, + "learning_rate": 3.2535510884370234e-06, + "loss": 3.3106, + "step": 2855424 + }, + { + "epoch": 0.01, + "learning_rate": 3.2451651409265033e-06, + "loss": 3.2891, + "step": 2855936 + }, + { + "epoch": 0.01, + "learning_rate": 3.236795572219715e-06, + "loss": 3.2909, + "step": 2856448 + }, + { + "epoch": 0.01, + "learning_rate": 3.2284096247091945e-06, + "loss": 3.3059, + "step": 2856960 + }, + { + "epoch": 0.01, + "learning_rate": 3.220023677198675e-06, + "loss": 3.3064, + "step": 2857472 + }, + { + "epoch": 0.01, + "learning_rate": 3.2116377296881544e-06, + "loss": 3.2932, + "step": 2857984 + }, + { + "epoch": 0.01, + "learning_rate": 3.203268160981366e-06, + "loss": 3.3052, + "step": 2858496 + }, + { + "epoch": 0.01, + "learning_rate": 3.1948822134708456e-06, + "loss": 3.287, + "step": 2859008 + }, + { + "epoch": 0.01, + "learning_rate": 3.186496265960325e-06, + "loss": 3.2964, + "step": 2859520 + }, + { + "epoch": 0.01, + "learning_rate": 3.1781103184498055e-06, + "loss": 3.3068, + "step": 2860032 + }, + { + "epoch": 0.01, + "learning_rate": 3.1697407497430167e-06, + "loss": 3.3033, + "step": 2860544 + }, + { + "epoch": 0.01, + "learning_rate": 3.1613548022324966e-06, + "loss": 3.311, + "step": 2861056 + }, + { + "epoch": 0.01, + "learning_rate": 3.1529688547219766e-06, + "loss": 3.3081, + "step": 2861568 + }, + { + "epoch": 0.01, + "learning_rate": 3.1445829072114566e-06, + "loss": 3.3159, + "step": 2862080 + }, + { + "epoch": 0.01, + "learning_rate": 3.1362133385046678e-06, + "loss": 3.2934, + "step": 2862592 + }, + { + "epoch": 0.01, + "learning_rate": 3.127827390994148e-06, + "loss": 3.3095, + "step": 2863104 + }, + { + "epoch": 0.01, + "learning_rate": 3.1194414434836277e-06, + "loss": 3.308, + "step": 2863616 + }, + { + "epoch": 0.01, + "learning_rate": 3.1110554959731076e-06, + "loss": 3.2894, + "step": 2864128 + }, + { + "epoch": 0.01, + "learning_rate": 3.102685927266319e-06, + "loss": 3.3102, + "step": 2864640 + }, + { + "epoch": 0.01, + "learning_rate": 3.094299979755799e-06, + "loss": 3.3045, + "step": 2865152 + }, + { + "epoch": 0.01, + "learning_rate": 3.0859140322452783e-06, + "loss": 3.3059, + "step": 2865664 + }, + { + "epoch": 0.01, + "learning_rate": 3.0775280847347583e-06, + "loss": 3.3073, + "step": 2866176 + }, + { + "epoch": 0.01, + "learning_rate": 3.06915851602797e-06, + "loss": 3.2948, + "step": 2866688 + }, + { + "epoch": 0.01, + "learning_rate": 3.06077256851745e-06, + "loss": 3.2945, + "step": 2867200 + }, + { + "epoch": 0.01, + "learning_rate": 3.05238662100693e-06, + "loss": 3.3053, + "step": 2867712 + }, + { + "epoch": 0.01, + "learning_rate": 3.04400067349641e-06, + "loss": 3.3117, + "step": 2868224 + }, + { + "epoch": 0.01, + "learning_rate": 3.035631104789621e-06, + "loss": 3.3038, + "step": 2868736 + }, + { + "epoch": 0.01, + "learning_rate": 3.027245157279101e-06, + "loss": 3.3124, + "step": 2869248 + }, + { + "epoch": 0.02, + "learning_rate": 3.018859209768581e-06, + "loss": 3.3141, + "step": 2869760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0104732622580605e-06, + "loss": 3.2958, + "step": 2870272 + }, + { + "epoch": 0.02, + "learning_rate": 3.002103693551272e-06, + "loss": 3.3049, + "step": 2870784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9937177460407516e-06, + "loss": 3.2982, + "step": 2871296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9853317985302316e-06, + "loss": 3.3087, + "step": 2871808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9769458510197115e-06, + "loss": 3.3179, + "step": 2872320 + }, + { + "epoch": 0.02, + "learning_rate": 2.968576282312923e-06, + "loss": 3.2964, + "step": 2872832 + }, + { + "epoch": 0.02, + "learning_rate": 2.960190334802403e-06, + "loss": 3.3006, + "step": 2873344 + }, + { + "epoch": 0.02, + "learning_rate": 2.951804387291883e-06, + "loss": 3.2978, + "step": 2873856 + }, + { + "epoch": 0.02, + "learning_rate": 2.943418439781363e-06, + "loss": 3.3054, + "step": 2874368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9350488710745743e-06, + "loss": 3.3172, + "step": 2874880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9266629235640542e-06, + "loss": 3.3001, + "step": 2875392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9182769760535337e-06, + "loss": 3.2997, + "step": 2875904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9098910285430137e-06, + "loss": 3.2927, + "step": 2876416 + }, + { + "epoch": 0.02, + "learning_rate": 2.901521459836225e-06, + "loss": 3.3128, + "step": 2876928 + }, + { + "epoch": 0.02, + "learning_rate": 2.893135512325705e-06, + "loss": 3.289, + "step": 2877440 + }, + { + "epoch": 0.02, + "learning_rate": 2.884749564815185e-06, + "loss": 3.3037, + "step": 2877952 + }, + { + "epoch": 0.02, + "learning_rate": 2.876363617304665e-06, + "loss": 3.3026, + "step": 2878464 + }, + { + "epoch": 0.02, + "learning_rate": 2.8679940485978764e-06, + "loss": 3.3076, + "step": 2878976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8596081010873564e-06, + "loss": 3.2979, + "step": 2879488 + }, + { + "epoch": 0.02, + "learning_rate": 2.851222153576836e-06, + "loss": 3.3048, + "step": 2880000 + }, + { + "epoch": 0.02, + "learning_rate": 2.8428525848700475e-06, + "loss": 3.3049, + "step": 2880512 + }, + { + "epoch": 0.02, + "learning_rate": 2.834466637359527e-06, + "loss": 3.3003, + "step": 2881024 + }, + { + "epoch": 0.02, + "learning_rate": 2.826080689849007e-06, + "loss": 3.3045, + "step": 2881536 + }, + { + "epoch": 0.02, + "learning_rate": 2.817694742338487e-06, + "loss": 3.3034, + "step": 2882048 + }, + { + "epoch": 0.02, + "learning_rate": 2.809325173631698e-06, + "loss": 3.3119, + "step": 2882560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8009392261211786e-06, + "loss": 3.3152, + "step": 2883072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7925532786106585e-06, + "loss": 3.3025, + "step": 2883584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7841673311001385e-06, + "loss": 3.295, + "step": 2884096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7757977623933497e-06, + "loss": 3.3036, + "step": 2884608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7674118148828297e-06, + "loss": 3.3009, + "step": 2885120 + }, + { + "epoch": 0.02, + "learning_rate": 2.759025867372309e-06, + "loss": 3.2903, + "step": 2885632 + }, + { + "epoch": 0.02, + "learning_rate": 2.750639919861789e-06, + "loss": 3.3032, + "step": 2886144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7422703511550004e-06, + "loss": 3.2939, + "step": 2886656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7338844036444803e-06, + "loss": 3.3053, + "step": 2887168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7254984561339603e-06, + "loss": 3.3014, + "step": 2887680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7171125086234402e-06, + "loss": 3.304, + "step": 2888192 + }, + { + "epoch": 0.02, + "learning_rate": 2.708742939916652e-06, + "loss": 3.2963, + "step": 2888704 + }, + { + "epoch": 0.02, + "learning_rate": 2.700356992406132e-06, + "loss": 3.2967, + "step": 2889216 + }, + { + "epoch": 0.02, + "learning_rate": 2.6919710448956118e-06, + "loss": 3.3033, + "step": 2889728 + }, + { + "epoch": 0.02, + "learning_rate": 2.6835850973850913e-06, + "loss": 3.3056, + "step": 2890240 + }, + { + "epoch": 0.02, + "learning_rate": 2.675215528678303e-06, + "loss": 3.3016, + "step": 2890752 + }, + { + "epoch": 0.02, + "learning_rate": 2.6668295811677825e-06, + "loss": 3.3122, + "step": 2891264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6584436336572624e-06, + "loss": 3.2963, + "step": 2891776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6500576861467424e-06, + "loss": 3.3054, + "step": 2892288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6416881174399536e-06, + "loss": 3.3116, + "step": 2892800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6333021699294336e-06, + "loss": 3.3058, + "step": 2893312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6249162224189135e-06, + "loss": 3.3065, + "step": 2893824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6165302749083935e-06, + "loss": 3.3147, + "step": 2894336 + }, + { + "epoch": 0.02, + "learning_rate": 2.608160706201605e-06, + "loss": 3.3013, + "step": 2894848 + }, + { + "epoch": 0.02, + "learning_rate": 2.599774758691085e-06, + "loss": 3.3122, + "step": 2895360 + }, + { + "epoch": 0.02, + "learning_rate": 2.5913888111805646e-06, + "loss": 3.2933, + "step": 2895872 + }, + { + "epoch": 0.02, + "learning_rate": 2.5830028636700446e-06, + "loss": 3.3075, + "step": 2896384 + }, + { + "epoch": 0.02, + "learning_rate": 2.5746332949632558e-06, + "loss": 3.2999, + "step": 2896896 + }, + { + "epoch": 0.02, + "learning_rate": 2.5662473474527357e-06, + "loss": 3.2966, + "step": 2897408 + }, + { + "epoch": 0.02, + "learning_rate": 2.557877778745947e-06, + "loss": 3.3029, + "step": 2897920 + }, + { + "epoch": 0.02, + "learning_rate": 2.549491831235427e-06, + "loss": 3.2984, + "step": 2898432 + }, + { + "epoch": 0.02, + "learning_rate": 2.541105883724907e-06, + "loss": 3.3115, + "step": 2898944 + }, + { + "epoch": 0.02, + "learning_rate": 2.532719936214387e-06, + "loss": 3.2854, + "step": 2899456 + }, + { + "epoch": 0.02, + "learning_rate": 2.5243339887038668e-06, + "loss": 3.3114, + "step": 2899968 + }, + { + "epoch": 0.03, + "eval_loss": 3.8656840324401855, + "eval_runtime": 306.2937, + "eval_samples_per_second": 1245.834, + "eval_steps_per_second": 38.933, + "step": 2900160 + }, + { + "epoch": 0.0, + "learning_rate": 2.5159480411933467e-06, + "loss": 3.2923, + "step": 2900480 + }, + { + "epoch": 0.0, + "learning_rate": 2.5075620936828267e-06, + "loss": 3.2964, + "step": 2900992 + }, + { + "epoch": 0.0, + "learning_rate": 2.4991761461723066e-06, + "loss": 3.3049, + "step": 2901504 + }, + { + "epoch": 0.0, + "learning_rate": 2.4907901986617866e-06, + "loss": 3.3075, + "step": 2902016 + }, + { + "epoch": 0.0, + "learning_rate": 2.482420629954998e-06, + "loss": 3.3055, + "step": 2902528 + }, + { + "epoch": 0.0, + "learning_rate": 2.4740346824444778e-06, + "loss": 3.2979, + "step": 2903040 + }, + { + "epoch": 0.0, + "learning_rate": 2.4656487349339573e-06, + "loss": 3.2929, + "step": 2903552 + }, + { + "epoch": 0.0, + "learning_rate": 2.4572627874234372e-06, + "loss": 3.2987, + "step": 2904064 + }, + { + "epoch": 0.0, + "learning_rate": 2.4488932187166485e-06, + "loss": 3.303, + "step": 2904576 + }, + { + "epoch": 0.0, + "learning_rate": 2.4405072712061284e-06, + "loss": 3.3079, + "step": 2905088 + }, + { + "epoch": 0.0, + "learning_rate": 2.4321213236956084e-06, + "loss": 3.3011, + "step": 2905600 + }, + { + "epoch": 0.0, + "learning_rate": 2.4237353761850883e-06, + "loss": 3.3033, + "step": 2906112 + }, + { + "epoch": 0.0, + "learning_rate": 2.4153658074783e-06, + "loss": 3.295, + "step": 2906624 + }, + { + "epoch": 0.0, + "learning_rate": 2.40697985996778e-06, + "loss": 3.2913, + "step": 2907136 + }, + { + "epoch": 0.0, + "learning_rate": 2.39859391245726e-06, + "loss": 3.3016, + "step": 2907648 + }, + { + "epoch": 0.0, + "learning_rate": 2.3902079649467394e-06, + "loss": 3.2946, + "step": 2908160 + }, + { + "epoch": 0.0, + "learning_rate": 2.381838396239951e-06, + "loss": 3.2937, + "step": 2908672 + }, + { + "epoch": 0.0, + "learning_rate": 2.3734524487294306e-06, + "loss": 3.3035, + "step": 2909184 + }, + { + "epoch": 0.0, + "learning_rate": 2.3650665012189105e-06, + "loss": 3.2913, + "step": 2909696 + }, + { + "epoch": 0.0, + "learning_rate": 2.3566969325121217e-06, + "loss": 3.3186, + "step": 2910208 + }, + { + "epoch": 0.0, + "learning_rate": 2.3483109850016017e-06, + "loss": 3.3052, + "step": 2910720 + }, + { + "epoch": 0.0, + "learning_rate": 2.339925037491082e-06, + "loss": 3.2978, + "step": 2911232 + }, + { + "epoch": 0.0, + "learning_rate": 2.331539089980562e-06, + "loss": 3.3036, + "step": 2911744 + }, + { + "epoch": 0.0, + "learning_rate": 2.3231695212737733e-06, + "loss": 3.3105, + "step": 2912256 + }, + { + "epoch": 0.0, + "learning_rate": 2.314783573763253e-06, + "loss": 3.2901, + "step": 2912768 + }, + { + "epoch": 0.0, + "learning_rate": 2.306397626252733e-06, + "loss": 3.3051, + "step": 2913280 + }, + { + "epoch": 0.0, + "learning_rate": 2.2980116787422127e-06, + "loss": 3.2987, + "step": 2913792 + }, + { + "epoch": 0.0, + "learning_rate": 2.2896421100354243e-06, + "loss": 3.2971, + "step": 2914304 + }, + { + "epoch": 0.0, + "learning_rate": 2.281256162524904e-06, + "loss": 3.2903, + "step": 2914816 + }, + { + "epoch": 0.0, + "learning_rate": 2.272870215014384e-06, + "loss": 3.303, + "step": 2915328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2644842675038638e-06, + "loss": 3.313, + "step": 2915840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2561146987970754e-06, + "loss": 3.3037, + "step": 2916352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2477287512865554e-06, + "loss": 3.3099, + "step": 2916864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2393428037760353e-06, + "loss": 3.3028, + "step": 2917376 + }, + { + "epoch": 0.01, + "learning_rate": 2.230956856265515e-06, + "loss": 3.294, + "step": 2917888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2225872875587265e-06, + "loss": 3.3044, + "step": 2918400 + }, + { + "epoch": 0.01, + "learning_rate": 2.214201340048206e-06, + "loss": 3.2977, + "step": 2918912 + }, + { + "epoch": 0.01, + "learning_rate": 2.205815392537686e-06, + "loss": 3.2951, + "step": 2919424 + }, + { + "epoch": 0.01, + "learning_rate": 2.197429445027166e-06, + "loss": 3.2933, + "step": 2919936 + }, + { + "epoch": 0.01, + "learning_rate": 2.189059876320377e-06, + "loss": 3.2935, + "step": 2920448 + }, + { + "epoch": 0.01, + "learning_rate": 2.180673928809857e-06, + "loss": 3.2976, + "step": 2920960 + }, + { + "epoch": 0.01, + "learning_rate": 2.1723043601030687e-06, + "loss": 3.3053, + "step": 2921472 + }, + { + "epoch": 0.01, + "learning_rate": 2.1639184125925487e-06, + "loss": 3.2998, + "step": 2921984 + }, + { + "epoch": 0.01, + "learning_rate": 2.1555324650820287e-06, + "loss": 3.2985, + "step": 2922496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1471465175715086e-06, + "loss": 3.3046, + "step": 2923008 + }, + { + "epoch": 0.01, + "learning_rate": 2.138760570060988e-06, + "loss": 3.2975, + "step": 2923520 + }, + { + "epoch": 0.01, + "learning_rate": 2.130374622550468e-06, + "loss": 3.3033, + "step": 2924032 + }, + { + "epoch": 0.01, + "learning_rate": 2.121988675039948e-06, + "loss": 3.2951, + "step": 2924544 + }, + { + "epoch": 0.01, + "learning_rate": 2.1136191063331593e-06, + "loss": 3.2785, + "step": 2925056 + }, + { + "epoch": 0.01, + "learning_rate": 2.1052331588226392e-06, + "loss": 3.3085, + "step": 2925568 + }, + { + "epoch": 0.01, + "learning_rate": 2.096847211312119e-06, + "loss": 3.296, + "step": 2926080 + }, + { + "epoch": 0.01, + "learning_rate": 2.088461263801599e-06, + "loss": 3.3057, + "step": 2926592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0800916950948104e-06, + "loss": 3.2926, + "step": 2927104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0717057475842903e-06, + "loss": 3.2924, + "step": 2927616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0633198000737703e-06, + "loss": 3.2857, + "step": 2928128 + }, + { + "epoch": 0.01, + "learning_rate": 2.054950231366982e-06, + "loss": 3.3042, + "step": 2928640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0465642838564614e-06, + "loss": 3.2919, + "step": 2929152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0381783363459414e-06, + "loss": 3.2984, + "step": 2929664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0297923888354213e-06, + "loss": 3.3048, + "step": 2930176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0214064413249013e-06, + "loss": 3.2872, + "step": 2930688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0130204938143813e-06, + "loss": 3.2915, + "step": 2931200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0046345463038608e-06, + "loss": 3.3095, + "step": 2931712 + }, + { + "epoch": 0.01, + "learning_rate": 1.9962485987933407e-06, + "loss": 3.2781, + "step": 2932224 + }, + { + "epoch": 0.01, + "learning_rate": 1.987879030086552e-06, + "loss": 3.2842, + "step": 2932736 + }, + { + "epoch": 0.01, + "learning_rate": 1.979493082576032e-06, + "loss": 3.2973, + "step": 2933248 + }, + { + "epoch": 0.01, + "learning_rate": 1.971107135065512e-06, + "loss": 3.2986, + "step": 2933760 + }, + { + "epoch": 0.01, + "learning_rate": 1.962721187554992e-06, + "loss": 3.2892, + "step": 2934272 + }, + { + "epoch": 0.01, + "learning_rate": 1.9543516188482035e-06, + "loss": 3.2978, + "step": 2934784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9459656713376834e-06, + "loss": 3.2815, + "step": 2935296 + }, + { + "epoch": 0.01, + "learning_rate": 1.937579723827163e-06, + "loss": 3.2866, + "step": 2935808 + }, + { + "epoch": 0.01, + "learning_rate": 1.929193776316643e-06, + "loss": 3.3021, + "step": 2936320 + }, + { + "epoch": 0.01, + "learning_rate": 1.920824207609854e-06, + "loss": 3.293, + "step": 2936832 + }, + { + "epoch": 0.01, + "learning_rate": 1.912438260099334e-06, + "loss": 3.3024, + "step": 2937344 + }, + { + "epoch": 0.01, + "learning_rate": 1.904052312588814e-06, + "loss": 3.2997, + "step": 2937856 + }, + { + "epoch": 0.01, + "learning_rate": 1.8956663650782942e-06, + "loss": 3.3061, + "step": 2938368 + }, + { + "epoch": 0.01, + "learning_rate": 1.8872967963715054e-06, + "loss": 3.2877, + "step": 2938880 + }, + { + "epoch": 0.01, + "learning_rate": 1.8789108488609854e-06, + "loss": 3.2988, + "step": 2939392 + }, + { + "epoch": 0.01, + "learning_rate": 1.8705249013504653e-06, + "loss": 3.2991, + "step": 2939904 + }, + { + "epoch": 0.01, + "learning_rate": 1.8621389538399449e-06, + "loss": 3.2824, + "step": 2940416 + }, + { + "epoch": 0.01, + "learning_rate": 1.8537693851331567e-06, + "loss": 3.3023, + "step": 2940928 + }, + { + "epoch": 0.01, + "learning_rate": 1.8453834376226362e-06, + "loss": 3.3, + "step": 2941440 + }, + { + "epoch": 0.01, + "learning_rate": 1.8369974901121162e-06, + "loss": 3.299, + "step": 2941952 + }, + { + "epoch": 0.01, + "learning_rate": 1.8286115426015961e-06, + "loss": 3.2984, + "step": 2942464 + }, + { + "epoch": 0.01, + "learning_rate": 1.8202419738948074e-06, + "loss": 3.2889, + "step": 2942976 + }, + { + "epoch": 0.01, + "learning_rate": 1.8118560263842875e-06, + "loss": 3.2876, + "step": 2943488 + }, + { + "epoch": 0.01, + "learning_rate": 1.8034700788737675e-06, + "loss": 3.2975, + "step": 2944000 + }, + { + "epoch": 0.01, + "learning_rate": 1.7950841313632474e-06, + "loss": 3.2983, + "step": 2944512 + }, + { + "epoch": 0.01, + "learning_rate": 1.7867145626564587e-06, + "loss": 3.2992, + "step": 2945024 + }, + { + "epoch": 0.01, + "learning_rate": 1.7783286151459386e-06, + "loss": 3.303, + "step": 2945536 + }, + { + "epoch": 0.02, + "learning_rate": 1.7699426676354184e-06, + "loss": 3.3042, + "step": 2946048 + }, + { + "epoch": 0.02, + "learning_rate": 1.76157309892863e-06, + "loss": 3.2902, + "step": 2946560 + }, + { + "epoch": 0.02, + "learning_rate": 1.7531871514181095e-06, + "loss": 3.2997, + "step": 2947072 + }, + { + "epoch": 0.02, + "learning_rate": 1.7448012039075895e-06, + "loss": 3.2886, + "step": 2947584 + }, + { + "epoch": 0.02, + "learning_rate": 1.7364152563970694e-06, + "loss": 3.3047, + "step": 2948096 + }, + { + "epoch": 0.02, + "learning_rate": 1.7280293088865494e-06, + "loss": 3.3078, + "step": 2948608 + }, + { + "epoch": 0.02, + "learning_rate": 1.7196433613760293e-06, + "loss": 3.2939, + "step": 2949120 + }, + { + "epoch": 0.02, + "learning_rate": 1.711257413865509e-06, + "loss": 3.2922, + "step": 2949632 + }, + { + "epoch": 0.02, + "learning_rate": 1.702871466354989e-06, + "loss": 3.2893, + "step": 2950144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6945018976482003e-06, + "loss": 3.2985, + "step": 2950656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6861159501376802e-06, + "loss": 3.3095, + "step": 2951168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6777300026271602e-06, + "loss": 3.2932, + "step": 2951680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6693604339203716e-06, + "loss": 3.2956, + "step": 2952192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6609744864098516e-06, + "loss": 3.2889, + "step": 2952704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6525885388993315e-06, + "loss": 3.3019, + "step": 2953216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6442025913888115e-06, + "loss": 3.2873, + "step": 2953728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6358330226820227e-06, + "loss": 3.2972, + "step": 2954240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6274470751715026e-06, + "loss": 3.2896, + "step": 2954752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6190611276609824e-06, + "loss": 3.3035, + "step": 2955264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6106751801504623e-06, + "loss": 3.2912, + "step": 2955776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6023056114436735e-06, + "loss": 3.2966, + "step": 2956288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5939196639331535e-06, + "loss": 3.2967, + "step": 2956800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5855337164226335e-06, + "loss": 3.2894, + "step": 2957312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5771477689121134e-06, + "loss": 3.2998, + "step": 2957824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5687782002053248e-06, + "loss": 3.294, + "step": 2958336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5603922526948046e-06, + "loss": 3.3028, + "step": 2958848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5520063051842845e-06, + "loss": 3.3076, + "step": 2959360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5436203576737645e-06, + "loss": 3.291, + "step": 2959872 + }, + { + "epoch": 0.02, + "learning_rate": 1.535250788966976e-06, + "loss": 3.2973, + "step": 2960384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5268648414564557e-06, + "loss": 3.2932, + "step": 2960896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5184788939459356e-06, + "loss": 3.2963, + "step": 2961408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5100929464354156e-06, + "loss": 3.2904, + "step": 2961920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5017233777286268e-06, + "loss": 3.2931, + "step": 2962432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4933374302181067e-06, + "loss": 3.2834, + "step": 2962944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4849514827075867e-06, + "loss": 3.296, + "step": 2963456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4765655351970667e-06, + "loss": 3.2901, + "step": 2963968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4681959664902779e-06, + "loss": 3.2972, + "step": 2964480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4598100189797578e-06, + "loss": 3.2864, + "step": 2964992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4514240714692376e-06, + "loss": 3.2936, + "step": 2965504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4430381239587175e-06, + "loss": 3.2924, + "step": 2966016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4346521764481977e-06, + "loss": 3.3013, + "step": 2966528 + }, + { + "epoch": 0.02, + "learning_rate": 1.4262662289376774e-06, + "loss": 3.2933, + "step": 2967040 + }, + { + "epoch": 0.02, + "learning_rate": 1.4178802814271574e-06, + "loss": 3.3038, + "step": 2967552 + }, + { + "epoch": 0.02, + "learning_rate": 1.4094943339166371e-06, + "loss": 3.2862, + "step": 2968064 + }, + { + "epoch": 0.02, + "learning_rate": 1.4011247652098486e-06, + "loss": 3.3009, + "step": 2968576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3927388176993285e-06, + "loss": 3.3016, + "step": 2969088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3843528701888085e-06, + "loss": 3.2999, + "step": 2969600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3759669226782882e-06, + "loss": 3.2997, + "step": 2970112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3675973539714996e-06, + "loss": 3.3069, + "step": 2970624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3592114064609794e-06, + "loss": 3.2945, + "step": 2971136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3508254589504593e-06, + "loss": 3.307, + "step": 2971648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3424395114399393e-06, + "loss": 3.2851, + "step": 2972160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3340699427331507e-06, + "loss": 3.2993, + "step": 2972672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3256839952226307e-06, + "loss": 3.2912, + "step": 2973184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3172980477121104e-06, + "loss": 3.294, + "step": 2973696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3089284790053219e-06, + "loss": 3.2915, + "step": 2974208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3005425314948018e-06, + "loss": 3.2894, + "step": 2974720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2921565839842818e-06, + "loss": 3.3005, + "step": 2975232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2837706364737615e-06, + "loss": 3.2794, + "step": 2975744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2753846889632415e-06, + "loss": 3.3055, + "step": 2976256 + }, + { + "epoch": 0.03, + "eval_loss": 3.8651742935180664, + "eval_runtime": 317.1921, + "eval_samples_per_second": 1203.028, + "eval_steps_per_second": 37.596, + "step": 2976480 + }, + { + "epoch": 1.0, + "learning_rate": 1.2669987414527214e-06, + "loss": 3.289, + "step": 2976768 + }, + { + "epoch": 1.0, + "learning_rate": 1.2586127939422012e-06, + "loss": 3.2876, + "step": 2977280 + }, + { + "epoch": 1.0, + "learning_rate": 1.2502268464316811e-06, + "loss": 3.2958, + "step": 2977792 + }, + { + "epoch": 1.0, + "learning_rate": 1.2418572777248925e-06, + "loss": 3.2995, + "step": 2978304 + }, + { + "epoch": 1.0, + "learning_rate": 1.2334713302143725e-06, + "loss": 3.2961, + "step": 2978816 + }, + { + "epoch": 1.0, + "learning_rate": 1.2250853827038522e-06, + "loss": 3.2949, + "step": 2979328 + }, + { + "epoch": 1.0, + "learning_rate": 1.2166994351933322e-06, + "loss": 3.2883, + "step": 2979840 + }, + { + "epoch": 1.0, + "learning_rate": 1.2083298664865434e-06, + "loss": 3.2879, + "step": 2980352 + }, + { + "epoch": 1.0, + "learning_rate": 1.1999439189760236e-06, + "loss": 3.295, + "step": 2980864 + }, + { + "epoch": 1.0, + "learning_rate": 1.1915579714655033e-06, + "loss": 3.3014, + "step": 2981376 + }, + { + "epoch": 1.0, + "learning_rate": 1.1831720239549833e-06, + "loss": 3.2951, + "step": 2981888 + }, + { + "epoch": 1.0, + "learning_rate": 1.1748024552481945e-06, + "loss": 3.2916, + "step": 2982400 + }, + { + "epoch": 1.0, + "learning_rate": 1.1664165077376744e-06, + "loss": 3.2924, + "step": 2982912 + }, + { + "epoch": 1.0, + "learning_rate": 1.1580305602271544e-06, + "loss": 3.2842, + "step": 2983424 + }, + { + "epoch": 1.0, + "learning_rate": 1.1496446127166344e-06, + "loss": 3.293, + "step": 2983936 + }, + { + "epoch": 1.0, + "learning_rate": 1.1412750440098458e-06, + "loss": 3.2858, + "step": 2984448 + }, + { + "epoch": 1.0, + "learning_rate": 1.1328890964993255e-06, + "loss": 3.2915, + "step": 2984960 + }, + { + "epoch": 1.0, + "learning_rate": 1.1245031489888055e-06, + "loss": 3.2916, + "step": 2985472 + }, + { + "epoch": 1.0, + "learning_rate": 1.1161172014782852e-06, + "loss": 3.2869, + "step": 2985984 + }, + { + "epoch": 1.0, + "learning_rate": 1.1077476327714969e-06, + "loss": 3.3072, + "step": 2986496 + }, + { + "epoch": 1.0, + "learning_rate": 1.0993616852609766e-06, + "loss": 3.3037, + "step": 2987008 + }, + { + "epoch": 1.0, + "learning_rate": 1.0909757377504566e-06, + "loss": 3.2897, + "step": 2987520 + }, + { + "epoch": 1.0, + "learning_rate": 1.0825897902399365e-06, + "loss": 3.2971, + "step": 2988032 + }, + { + "epoch": 1.0, + "learning_rate": 1.0742202215331477e-06, + "loss": 3.3016, + "step": 2988544 + }, + { + "epoch": 1.0, + "learning_rate": 1.0658342740226277e-06, + "loss": 3.284, + "step": 2989056 + }, + { + "epoch": 1.0, + "learning_rate": 1.0574483265121076e-06, + "loss": 3.2965, + "step": 2989568 + }, + { + "epoch": 1.0, + "learning_rate": 1.0490623790015876e-06, + "loss": 3.2924, + "step": 2990080 + }, + { + "epoch": 1.0, + "learning_rate": 1.0406928102947988e-06, + "loss": 3.2885, + "step": 2990592 + }, + { + "epoch": 1.0, + "learning_rate": 1.0323068627842788e-06, + "loss": 3.2835, + "step": 2991104 + }, + { + "epoch": 1.0, + "learning_rate": 1.0239209152737585e-06, + "loss": 3.2984, + "step": 2991616 + }, + { + "epoch": 1.01, + "learning_rate": 1.0155349677632385e-06, + "loss": 3.302, + "step": 2992128 + }, + { + "epoch": 1.01, + "learning_rate": 1.00716539905645e-06, + "loss": 3.2989, + "step": 2992640 + }, + { + "epoch": 1.01, + "learning_rate": 9.987794515459299e-07, + "loss": 3.3043, + "step": 2993152 + }, + { + "epoch": 1.01, + "learning_rate": 9.903935040354096e-07, + "loss": 3.2914, + "step": 2993664 + }, + { + "epoch": 1.01, + "learning_rate": 9.820075565248896e-07, + "loss": 3.2875, + "step": 2994176 + }, + { + "epoch": 1.01, + "learning_rate": 9.73637987818101e-07, + "loss": 3.2975, + "step": 2994688 + }, + { + "epoch": 1.01, + "learning_rate": 9.65252040307581e-07, + "loss": 3.2897, + "step": 2995200 + }, + { + "epoch": 1.01, + "learning_rate": 9.568660927970609e-07, + "loss": 3.2845, + "step": 2995712 + }, + { + "epoch": 1.01, + "learning_rate": 9.484965240902721e-07, + "loss": 3.2844, + "step": 2996224 + }, + { + "epoch": 1.01, + "learning_rate": 9.401105765797522e-07, + "loss": 3.2865, + "step": 2996736 + }, + { + "epoch": 1.01, + "learning_rate": 9.317246290692319e-07, + "loss": 3.2904, + "step": 2997248 + }, + { + "epoch": 1.01, + "learning_rate": 9.233386815587119e-07, + "loss": 3.2964, + "step": 2997760 + }, + { + "epoch": 1.01, + "learning_rate": 9.149691128519232e-07, + "loss": 3.2955, + "step": 2998272 + }, + { + "epoch": 1.01, + "learning_rate": 9.065831653414031e-07, + "loss": 3.2863, + "step": 2998784 + }, + { + "epoch": 1.01, + "learning_rate": 8.98197217830883e-07, + "loss": 3.2971, + "step": 2999296 + }, + { + "epoch": 1.01, + "learning_rate": 8.89811270320363e-07, + "loss": 3.2923, + "step": 2999808 + }, + { + "epoch": 1.01, + "learning_rate": 8.814417016135743e-07, + "loss": 3.2931, + "step": 3000320 + }, + { + "epoch": 1.01, + "learning_rate": 8.730557541030542e-07, + "loss": 3.2894, + "step": 3000832 + }, + { + "epoch": 1.01, + "learning_rate": 8.64669806592534e-07, + "loss": 3.2698, + "step": 3001344 + }, + { + "epoch": 1.01, + "learning_rate": 8.562838590820139e-07, + "loss": 3.3032, + "step": 3001856 + }, + { + "epoch": 1.01, + "learning_rate": 8.479142903752252e-07, + "loss": 3.2875, + "step": 3002368 + }, + { + "epoch": 1.01, + "learning_rate": 8.395283428647052e-07, + "loss": 3.3014, + "step": 3002880 + }, + { + "epoch": 1.01, + "learning_rate": 8.311423953541852e-07, + "loss": 3.2844, + "step": 3003392 + }, + { + "epoch": 1.01, + "learning_rate": 8.22756447843665e-07, + "loss": 3.2896, + "step": 3003904 + }, + { + "epoch": 1.01, + "learning_rate": 8.143868791368764e-07, + "loss": 3.281, + "step": 3004416 + }, + { + "epoch": 1.01, + "learning_rate": 8.060009316263563e-07, + "loss": 3.2935, + "step": 3004928 + }, + { + "epoch": 1.01, + "learning_rate": 7.976149841158362e-07, + "loss": 3.2834, + "step": 3005440 + }, + { + "epoch": 1.01, + "learning_rate": 7.89229036605316e-07, + "loss": 3.2886, + "step": 3005952 + }, + { + "epoch": 1.01, + "learning_rate": 7.808594678985275e-07, + "loss": 3.2979, + "step": 3006464 + }, + { + "epoch": 1.01, + "learning_rate": 7.724735203880074e-07, + "loss": 3.283, + "step": 3006976 + }, + { + "epoch": 1.01, + "learning_rate": 7.640875728774872e-07, + "loss": 3.2817, + "step": 3007488 + }, + { + "epoch": 1.01, + "learning_rate": 7.557016253669672e-07, + "loss": 3.2973, + "step": 3008000 + }, + { + "epoch": 1.01, + "learning_rate": 7.473320566601785e-07, + "loss": 3.2756, + "step": 3008512 + }, + { + "epoch": 1.01, + "learning_rate": 7.389461091496584e-07, + "loss": 3.2735, + "step": 3009024 + }, + { + "epoch": 1.01, + "learning_rate": 7.305601616391383e-07, + "loss": 3.2916, + "step": 3009536 + }, + { + "epoch": 1.01, + "learning_rate": 7.221742141286181e-07, + "loss": 3.2898, + "step": 3010048 + }, + { + "epoch": 1.01, + "learning_rate": 7.138046454218296e-07, + "loss": 3.2828, + "step": 3010560 + }, + { + "epoch": 1.01, + "learning_rate": 7.054186979113094e-07, + "loss": 3.2895, + "step": 3011072 + }, + { + "epoch": 1.01, + "learning_rate": 6.970327504007894e-07, + "loss": 3.2731, + "step": 3011584 + }, + { + "epoch": 1.01, + "learning_rate": 6.886468028902693e-07, + "loss": 3.2821, + "step": 3012096 + }, + { + "epoch": 1.01, + "learning_rate": 6.802772341834805e-07, + "loss": 3.2944, + "step": 3012608 + }, + { + "epoch": 1.01, + "learning_rate": 6.718912866729606e-07, + "loss": 3.2848, + "step": 3013120 + }, + { + "epoch": 1.01, + "learning_rate": 6.635053391624405e-07, + "loss": 3.2983, + "step": 3013632 + }, + { + "epoch": 1.01, + "learning_rate": 6.551193916519203e-07, + "loss": 3.2931, + "step": 3014144 + }, + { + "epoch": 1.01, + "learning_rate": 6.467498229451317e-07, + "loss": 3.2978, + "step": 3014656 + }, + { + "epoch": 1.01, + "learning_rate": 6.383638754346116e-07, + "loss": 3.2799, + "step": 3015168 + }, + { + "epoch": 1.01, + "learning_rate": 6.299779279240914e-07, + "loss": 3.2947, + "step": 3015680 + }, + { + "epoch": 1.01, + "learning_rate": 6.215919804135714e-07, + "loss": 3.29, + "step": 3016192 + }, + { + "epoch": 1.01, + "learning_rate": 6.132224117067827e-07, + "loss": 3.2763, + "step": 3016704 + }, + { + "epoch": 1.01, + "learning_rate": 6.048364641962627e-07, + "loss": 3.2943, + "step": 3017216 + }, + { + "epoch": 1.01, + "learning_rate": 5.964505166857425e-07, + "loss": 3.2942, + "step": 3017728 + }, + { + "epoch": 1.01, + "learning_rate": 5.880645691752225e-07, + "loss": 3.2889, + "step": 3018240 + }, + { + "epoch": 1.01, + "learning_rate": 5.796950004684338e-07, + "loss": 3.2983, + "step": 3018752 + }, + { + "epoch": 1.01, + "learning_rate": 5.713090529579137e-07, + "loss": 3.2783, + "step": 3019264 + }, + { + "epoch": 1.01, + "learning_rate": 5.629231054473936e-07, + "loss": 3.2791, + "step": 3019776 + }, + { + "epoch": 1.01, + "learning_rate": 5.545371579368735e-07, + "loss": 3.2906, + "step": 3020288 + }, + { + "epoch": 1.01, + "learning_rate": 5.461675892300849e-07, + "loss": 3.2909, + "step": 3020800 + }, + { + "epoch": 1.01, + "learning_rate": 5.377816417195648e-07, + "loss": 3.2941, + "step": 3021312 + }, + { + "epoch": 1.01, + "learning_rate": 5.293956942090447e-07, + "loss": 3.2925, + "step": 3021824 + }, + { + "epoch": 1.02, + "learning_rate": 5.210097466985245e-07, + "loss": 3.2979, + "step": 3022336 + }, + { + "epoch": 1.02, + "learning_rate": 5.12640177991736e-07, + "loss": 3.2891, + "step": 3022848 + }, + { + "epoch": 1.02, + "learning_rate": 5.042542304812158e-07, + "loss": 3.2885, + "step": 3023360 + }, + { + "epoch": 1.02, + "learning_rate": 4.958682829706956e-07, + "loss": 3.2808, + "step": 3023872 + }, + { + "epoch": 1.02, + "learning_rate": 4.874823354601756e-07, + "loss": 3.2959, + "step": 3024384 + }, + { + "epoch": 1.02, + "learning_rate": 4.791127667533869e-07, + "loss": 3.2988, + "step": 3024896 + }, + { + "epoch": 1.02, + "learning_rate": 4.7072681924286693e-07, + "loss": 3.2897, + "step": 3025408 + }, + { + "epoch": 1.02, + "learning_rate": 4.623408717323468e-07, + "loss": 3.2836, + "step": 3025920 + }, + { + "epoch": 1.02, + "learning_rate": 4.539713030255582e-07, + "loss": 3.285, + "step": 3026432 + }, + { + "epoch": 1.02, + "learning_rate": 4.4558535551503806e-07, + "loss": 3.2876, + "step": 3026944 + }, + { + "epoch": 1.02, + "learning_rate": 4.3719940800451796e-07, + "loss": 3.3042, + "step": 3027456 + }, + { + "epoch": 1.02, + "learning_rate": 4.2881346049399786e-07, + "loss": 3.2837, + "step": 3027968 + }, + { + "epoch": 1.02, + "learning_rate": 4.2044389178720924e-07, + "loss": 3.2898, + "step": 3028480 + }, + { + "epoch": 1.02, + "learning_rate": 4.120579442766891e-07, + "loss": 3.2831, + "step": 3028992 + }, + { + "epoch": 1.02, + "learning_rate": 4.03671996766169e-07, + "loss": 3.2903, + "step": 3029504 + }, + { + "epoch": 1.02, + "learning_rate": 3.952860492556489e-07, + "loss": 3.2813, + "step": 3030016 + }, + { + "epoch": 1.02, + "learning_rate": 3.8691648054886027e-07, + "loss": 3.2914, + "step": 3030528 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853053303834017e-07, + "loss": 3.2791, + "step": 3031040 + }, + { + "epoch": 1.02, + "learning_rate": 3.7014458552782007e-07, + "loss": 3.2947, + "step": 3031552 + }, + { + "epoch": 1.02, + "learning_rate": 3.617586380173e-07, + "loss": 3.2869, + "step": 3032064 + }, + { + "epoch": 1.02, + "learning_rate": 3.5338906931051135e-07, + "loss": 3.2888, + "step": 3032576 + }, + { + "epoch": 1.02, + "learning_rate": 3.450031217999912e-07, + "loss": 3.2889, + "step": 3033088 + }, + { + "epoch": 1.02, + "learning_rate": 3.3661717428947115e-07, + "loss": 3.2902, + "step": 3033600 + }, + { + "epoch": 1.02, + "learning_rate": 3.28231226778951e-07, + "loss": 3.2892, + "step": 3034112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1986165807216243e-07, + "loss": 3.2861, + "step": 3034624 + }, + { + "epoch": 1.02, + "learning_rate": 3.114757105616423e-07, + "loss": 3.293, + "step": 3035136 + }, + { + "epoch": 1.02, + "learning_rate": 3.030897630511222e-07, + "loss": 3.3012, + "step": 3035648 + }, + { + "epoch": 1.02, + "learning_rate": 2.947038155406021e-07, + "loss": 3.2844, + "step": 3036160 + }, + { + "epoch": 1.02, + "learning_rate": 2.8633424683381346e-07, + "loss": 3.2905, + "step": 3036672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7794829932329336e-07, + "loss": 3.2857, + "step": 3037184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6956235181277326e-07, + "loss": 3.2872, + "step": 3037696 + }, + { + "epoch": 1.02, + "learning_rate": 2.611764043022531e-07, + "loss": 3.2835, + "step": 3038208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280683559546454e-07, + "loss": 3.2874, + "step": 3038720 + }, + { + "epoch": 1.02, + "learning_rate": 2.444208880849444e-07, + "loss": 3.28, + "step": 3039232 + }, + { + "epoch": 1.02, + "learning_rate": 2.3603494057442434e-07, + "loss": 3.2859, + "step": 3039744 + }, + { + "epoch": 1.02, + "learning_rate": 2.2764899306390422e-07, + "loss": 3.2892, + "step": 3040256 + }, + { + "epoch": 1.02, + "learning_rate": 2.192794243571156e-07, + "loss": 3.2903, + "step": 3040768 + }, + { + "epoch": 1.02, + "learning_rate": 2.108934768465955e-07, + "loss": 3.2762, + "step": 3041280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0250752933607537e-07, + "loss": 3.2876, + "step": 3041792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9412158182555527e-07, + "loss": 3.2848, + "step": 3042304 + }, + { + "epoch": 1.02, + "learning_rate": 1.8575201311876665e-07, + "loss": 3.2942, + "step": 3042816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736606560824655e-07, + "loss": 3.287, + "step": 3043328 + }, + { + "epoch": 1.02, + "learning_rate": 1.6898011809772645e-07, + "loss": 3.2964, + "step": 3043840 + }, + { + "epoch": 1.02, + "learning_rate": 1.6059417058720633e-07, + "loss": 3.2802, + "step": 3044352 + }, + { + "epoch": 1.02, + "learning_rate": 1.522246018804177e-07, + "loss": 3.296, + "step": 3044864 + }, + { + "epoch": 1.02, + "learning_rate": 1.438386543698976e-07, + "loss": 3.2947, + "step": 3045376 + }, + { + "epoch": 1.02, + "learning_rate": 1.354527068593775e-07, + "loss": 3.2926, + "step": 3045888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2706675934885738e-07, + "loss": 3.2936, + "step": 3046400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1869719064206877e-07, + "loss": 3.2943, + "step": 3046912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1031124313154867e-07, + "loss": 3.2906, + "step": 3047424 + }, + { + "epoch": 1.02, + "learning_rate": 1.0192529562102855e-07, + "loss": 3.2982, + "step": 3047936 + }, + { + "epoch": 1.02, + "learning_rate": 9.353934811050845e-08, + "loss": 3.2816, + "step": 3048448 + }, + { + "epoch": 1.02, + "learning_rate": 8.516977940371982e-08, + "loss": 3.2955, + "step": 3048960 + }, + { + "epoch": 1.02, + "learning_rate": 7.678383189319973e-08, + "loss": 3.2856, + "step": 3049472 + }, + { + "epoch": 1.02, + "learning_rate": 6.839788438267962e-08, + "loss": 3.2901, + "step": 3049984 + }, + { + "epoch": 1.02, + "learning_rate": 6.0028315675891e-08, + "loss": 3.2812, + "step": 3050496 + }, + { + "epoch": 1.02, + "learning_rate": 5.1642368165370886e-08, + "loss": 3.2848, + "step": 3051008 + }, + { + "epoch": 1.02, + "learning_rate": 4.325642065485078e-08, + "loss": 3.2897, + "step": 3051520 + }, + { + "epoch": 1.02, + "learning_rate": 3.487047314433067e-08, + "loss": 3.2781, + "step": 3052032 + }, + { + "epoch": 1.02, + "learning_rate": 2.648452563381057e-08, + "loss": 3.2981, + "step": 3052544 + }, + { + "epoch": 1.02, + "eval_loss": 3.8636128902435303, + "eval_runtime": 317.3077, + "eval_samples_per_second": 1202.59, + "eval_steps_per_second": 37.582, + "step": 3052726 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 2.11091157358225e+18, + "trial_name": null, + "trial_params": null +}