diff --git "a/checkpoint-2747512/trainer_state.json" "b/checkpoint-2747512/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2747512/trainer_state.json" @@ -0,0 +1,32509 @@ +{ + "best_metric": 3.8455798625946045, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/transformer/4/checkpoints/checkpoint-915832", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2747512, + "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": 11.029, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8404, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1927, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9723, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8266, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7094, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6055, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5396, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4816, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4052, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.37, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3294, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2682, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.2185, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.1914, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.1621, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 5.1269, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0824, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0643, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0336, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0079, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.991, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.971, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9444, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9248, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9093, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.8848, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8758, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8413, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.844, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8119, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.8013, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.8054, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7875, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7611, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 4.7497, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 4.7519, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7328, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7225, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.7064, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6896, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6788, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6652, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6668, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.658, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6515, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6365, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6329, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6361, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.6124, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6073, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5957, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.6055, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.5713, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5885, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5631, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5613, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5631, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5521, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5384, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5301, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5188, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5323, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.5162, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5061, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5068, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.497, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4784, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4989, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4788, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4718, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4837, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4629, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.475, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4723, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4627, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4649, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4411, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4346, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4397, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4399, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4329, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4182, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4086, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4121, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4112, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4136, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4133, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.4103, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3964, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3856, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3843, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3899, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3846, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.368, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.3717, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3727, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3754, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3713, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3657, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3689, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3575, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3558, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3629, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3457, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.352, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.3323, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.3288, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3283, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3371, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.333, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3099, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3137, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3214, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3294, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3155, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3216, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.3114, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.3141, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.3047, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.3, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2944, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.3025, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.2873, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2973, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2901, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2974, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2737, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2843, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2938, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.273, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2906, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.277, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2788, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.272, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2642, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2681, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2727, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2771, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2662, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2701, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2618, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2498, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2565, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2448, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2476, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2473, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2398, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2388, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2388, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.204409122467041, + "eval_runtime": 570.6558, + "eval_samples_per_second": 668.689, + "eval_steps_per_second": 20.897, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2439, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2382, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2318, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2303, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.229, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2065, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2219, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.2209, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2114, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2214, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2207, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2069, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.2041, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.2063, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.2052, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.196, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.1959, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.1975, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.1948, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.858326623483405e-05, + "loss": 4.1986, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.1964, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.1982, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.192, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.1916, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.854135287608518e-05, + "loss": 4.1881, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.853296692857466e-05, + "loss": 4.1835, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.852458098106414e-05, + "loss": 4.19, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851619503355362e-05, + "loss": 4.1696, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850782546484683e-05, + "loss": 4.1848, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.849943951733631e-05, + "loss": 4.1681, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849105356982579e-05, + "loss": 4.172, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.848266762231527e-05, + "loss": 4.1821, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847428167480475e-05, + "loss": 4.1801, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.8465912106097964e-05, + "loss": 4.1667, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.8457526158587444e-05, + "loss": 4.1603, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.8449140211076924e-05, + "loss": 4.1751, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.8440754263566404e-05, + "loss": 4.1665, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.8432368316055884e-05, + "loss": 4.1672, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.8423982368545363e-05, + "loss": 4.161, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.8415596421034843e-05, + "loss": 4.1476, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840721047352432e-05, + "loss": 4.1472, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.1481, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839045495730701e-05, + "loss": 4.1568, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.1476, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.1501, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836531349357918e-05, + "loss": 4.1476, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.835692754606866e-05, + "loss": 4.1481, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834854159855814e-05, + "loss": 4.1576, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.1364, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833178608234084e-05, + "loss": 4.1401, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.1323, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.83150141873198e-05, + "loss": 4.1535, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.830662823980928e-05, + "loss": 4.1264, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.8298258671102486e-05, + "loss": 4.1429, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.8289872723591966e-05, + "loss": 4.124, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.8281486776081446e-05, + "loss": 4.1348, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273100828570926e-05, + "loss": 4.1357, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.8264714881060406e-05, + "loss": 4.1331, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256328933549886e-05, + "loss": 4.1225, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.1246, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.1114, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.1297, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.1224, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.821443195360475e-05, + "loss": 4.1149, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.1166, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.1172, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.0991, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.1235, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.1051, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.108, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.815574669983483e-05, + "loss": 4.1184, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814736075232432e-05, + "loss": 4.1035, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.8138991183617535e-05, + "loss": 4.1157, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813060523610701e-05, + "loss": 4.1213, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812221928859649e-05, + "loss": 4.1123, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811383334108597e-05, + "loss": 4.1176, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.8105463772379184e-05, + "loss": 4.0999, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809707782486866e-05, + "loss": 4.0918, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808869187735814e-05, + "loss": 4.1019, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808030592984762e-05, + "loss": 4.1095, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.1003, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.8063550413630307e-05, + "loss": 4.0928, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.8055164466119786e-05, + "loss": 4.0827, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804677851860927e-05, + "loss": 4.0874, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.0887, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.803002300239196e-05, + "loss": 4.0922, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.802163705488144e-05, + "loss": 4.1003, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801325110737092e-05, + "loss": 4.099, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800488153866413e-05, + "loss": 4.087, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.799649559115361e-05, + "loss": 4.0837, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.798810964364309e-05, + "loss": 4.0785, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797972369613257e-05, + "loss": 4.0835, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797135412742578e-05, + "loss": 4.0859, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796296817991526e-05, + "loss": 4.078, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795458223240474e-05, + "loss": 4.0754, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.794619628489423e-05, + "loss": 4.0838, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.7937826716187436e-05, + "loss": 4.0864, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.7929440768676916e-05, + "loss": 4.08, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.7921054821166396e-05, + "loss": 4.0812, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.7912668873655876e-05, + "loss": 4.0875, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.7904299304949085e-05, + "loss": 4.0769, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.7895913357438565e-05, + "loss": 4.0741, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.7887527409928045e-05, + "loss": 4.0884, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.072, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.0823, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.7862385946200214e-05, + "loss": 4.0681, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7853999998689694e-05, + "loss": 4.0584, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.784561405117918e-05, + "loss": 4.066, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.783722810366866e-05, + "loss": 4.0724, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.782885853496187e-05, + "loss": 4.068, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.782047258745135e-05, + "loss": 4.0535, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781208663994083e-05, + "loss": 4.0514, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780370069243031e-05, + "loss": 4.0653, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779531474491979e-05, + "loss": 4.0726, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778692879740927e-05, + "loss": 4.0607, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.777855922870248e-05, + "loss": 4.0738, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777017328119196e-05, + "loss": 4.0617, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776178733368144e-05, + "loss": 4.0631, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775340138617092e-05, + "loss": 4.0612, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.77450154386604e-05, + "loss": 4.0544, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773662949114988e-05, + "loss": 4.0496, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772824354363936e-05, + "loss": 4.0605, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.7719857596128845e-05, + "loss": 4.0495, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.7711488027422054e-05, + "loss": 4.0516, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.7703102079911534e-05, + "loss": 4.0555, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.7694716132401014e-05, + "loss": 4.0632, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.7686330184890494e-05, + "loss": 4.0425, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.76779606161837e-05, + "loss": 4.0454, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.766957466867318e-05, + "loss": 4.0645, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.766118872116266e-05, + "loss": 4.0426, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.7652802773652136e-05, + "loss": 4.0625, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764443320494535e-05, + "loss": 4.0456, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.763604725743483e-05, + "loss": 4.0541, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762766130992431e-05, + "loss": 4.0463, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761927536241379e-05, + "loss": 4.0399, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761090579370701e-05, + "loss": 4.0453, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760251984619649e-05, + "loss": 4.0497, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759413389868596e-05, + "loss": 4.06, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.758574795117544e-05, + "loss": 4.0497, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757737838246866e-05, + "loss": 4.0504, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.7568992434958137e-05, + "loss": 4.0442, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756060648744761e-05, + "loss": 4.0322, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755222053993709e-05, + "loss": 4.0462, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.7543850971230306e-05, + "loss": 4.0332, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.7535465023719786e-05, + "loss": 4.0356, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.7527079076209266e-05, + "loss": 4.041, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.7518693128698745e-05, + "loss": 4.0264, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751032355999196e-05, + "loss": 4.0344, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.7501937612481435e-05, + "loss": 4.0326, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.0317535400390625, + "eval_runtime": 576.2911, + "eval_samples_per_second": 662.15, + "eval_steps_per_second": 20.693, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 4.0391, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0369, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.031, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.0281, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0324, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 4.0124, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.0282, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 4.0237, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0141, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.74181108949837e-05, + "loss": 4.0292, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740972494747318e-05, + "loss": 4.0306, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.0161, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 4.0123, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 4.0177, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 4.0181, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 4.0094, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735940926241006e-05, + "loss": 4.0083, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735103969370327e-05, + "loss": 4.0108, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734265374619275e-05, + "loss": 4.0134, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733426779868223e-05, + "loss": 4.0159, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732588185117171e-05, + "loss": 4.0139, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 4.0184, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 4.0157, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300740387443884e-05, + "loss": 4.0101, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292354439933364e-05, + "loss": 4.0126, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 4.0103, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 4.0139, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726721297620553e-05, + "loss": 3.9983, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725882702869501e-05, + "loss": 4.0085, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9964, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 4.0009, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723368556496718e-05, + "loss": 4.0126, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722529961745666e-05, + "loss": 4.0076, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9989, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.994, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720015815372884e-05, + "loss": 4.0111, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719177220621832e-05, + "loss": 3.9951, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 4.0015, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9963, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166630742490486e-05, + "loss": 3.9836, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158244794979966e-05, + "loss": 3.9841, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149858847469446e-05, + "loss": 3.9829, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714147289995892e-05, + "loss": 4.0007, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71330869524484e-05, + "loss": 3.9882, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712470100493788e-05, + "loss": 3.9886, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116331436231095e-05, + "loss": 3.987, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107945488720575e-05, + "loss": 3.9874, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099559541210055e-05, + "loss": 4.0021, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709118997250327e-05, + "loss": 3.98, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082804024992744e-05, + "loss": 3.9808, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074418077482224e-05, + "loss": 3.9784, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706604850877544e-05, + "loss": 3.9992, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705766256126492e-05, + "loss": 3.9739, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704927661375439e-05, + "loss": 3.9897, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704089066624387e-05, + "loss": 3.9676, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703250471873335e-05, + "loss": 3.9834, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702411877122283e-05, + "loss": 3.9875, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701573282371232e-05, + "loss": 3.9758, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.70073468762018e-05, + "loss": 3.9812, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699897730749501e-05, + "loss": 3.976, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699059135998449e-05, + "loss": 3.959, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698220541247397e-05, + "loss": 3.9791, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697381946496345e-05, + "loss": 3.9782, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696544989625666e-05, + "loss": 3.9702, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695708032754987e-05, + "loss": 3.9666, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694869438003935e-05, + "loss": 3.9725, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694030843252883e-05, + "loss": 3.9555, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931922485018307e-05, + "loss": 3.9807, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.6923536537507787e-05, + "loss": 3.957, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915150589997267e-05, + "loss": 3.9655, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.975, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689839507377996e-05, + "loss": 3.9647, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689000912626944e-05, + "loss": 3.9717, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688162317875892e-05, + "loss": 3.9861, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.68732372312484e-05, + "loss": 3.9699, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686485128373788e-05, + "loss": 3.9807, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685646533622736e-05, + "loss": 3.9626, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684807938871684e-05, + "loss": 3.9519, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683970982001005e-05, + "loss": 3.9639, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683132387249953e-05, + "loss": 3.9751, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682293792498901e-05, + "loss": 3.964, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681455197747849e-05, + "loss": 3.9544, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680618240877171e-05, + "loss": 3.9526, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679779646126119e-05, + "loss": 3.952, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678941051375067e-05, + "loss": 3.9514, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678102456624015e-05, + "loss": 3.9573, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772654997533356e-05, + "loss": 3.966, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764269050022836e-05, + "loss": 3.9652, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755883102512316e-05, + "loss": 3.9546, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9523, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.9475, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730741638784485e-05, + "loss": 3.9547, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722355691273965e-05, + "loss": 3.9508, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713969743763445e-05, + "loss": 3.9518, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705583796252925e-05, + "loss": 3.9457, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697197848742405e-05, + "loss": 3.957, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688811901231885e-05, + "loss": 3.9555, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9544, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9546, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.9595, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9527, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664691492128675e-05, + "loss": 3.946, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663852897377623e-05, + "loss": 3.9651, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9425, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9643, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9391, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660500156253788e-05, + "loss": 3.9347, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9415, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588246046320574e-05, + "loss": 3.952, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579860098810054e-05, + "loss": 3.9462, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657147415129953e-05, + "loss": 3.934, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656308820378901e-05, + "loss": 3.9313, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655470225627849e-05, + "loss": 3.9414, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654631630876797e-05, + "loss": 3.9525, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653793036125745e-05, + "loss": 3.9393, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.9548, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521174845040136e-05, + "loss": 3.9428, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512788897529616e-05, + "loss": 3.9427, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504402950019096e-05, + "loss": 3.9483, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649601700250858e-05, + "loss": 3.9332, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648764743380179e-05, + "loss": 3.9353, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647926148629127e-05, + "loss": 3.9403, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647087553878075e-05, + "loss": 3.9319, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646248959127023e-05, + "loss": 3.9371, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645410364375971e-05, + "loss": 3.9382, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644571769624919e-05, + "loss": 3.9448, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643733174873867e-05, + "loss": 3.9284, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642894580122815e-05, + "loss": 3.9284, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642057623252136e-05, + "loss": 3.9516, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641220666381457e-05, + "loss": 3.9316, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640382071630405e-05, + "loss": 3.9442, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395434768793536e-05, + "loss": 3.9354, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387048821283016e-05, + "loss": 3.9389, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378662873772496e-05, + "loss": 3.934, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370276926261976e-05, + "loss": 3.9293, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361907357555185e-05, + "loss": 3.9355, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353521410044665e-05, + "loss": 3.935, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345135462534145e-05, + "loss": 3.9472, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336749515023625e-05, + "loss": 3.9415, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328379946316834e-05, + "loss": 3.9384, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319993998806314e-05, + "loss": 3.9323, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311608051295794e-05, + "loss": 3.9246, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303222103785274e-05, + "loss": 3.9352, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629485253507848e-05, + "loss": 3.9236, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628646658756797e-05, + "loss": 3.9282, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627808064005745e-05, + "loss": 3.928, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626969469254693e-05, + "loss": 3.9206, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626130874503641e-05, + "loss": 3.9266, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625292279752589e-05, + "loss": 3.9236, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.957977533340454, + "eval_runtime": 576.5675, + "eval_samples_per_second": 661.832, + "eval_steps_per_second": 20.683, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.62445532288191e-05, + "loss": 3.929, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623616728130858e-05, + "loss": 3.9328, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622778133379806e-05, + "loss": 3.9226, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621939538628753e-05, + "loss": 3.9227, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621100943877701e-05, + "loss": 3.9275, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620262349126649e-05, + "loss": 3.9079, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619423754375597e-05, + "loss": 3.9209, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618585159624545e-05, + "loss": 3.921, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617748202753867e-05, + "loss": 3.9127, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.6169112458831884e-05, + "loss": 3.9246, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.6160726511321364e-05, + "loss": 3.9256, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615234056381084e-05, + "loss": 3.9092, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614395461630032e-05, + "loss": 3.91, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.61355686687898e-05, + "loss": 3.9146, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612718272127928e-05, + "loss": 3.9173, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611879677376876e-05, + "loss": 3.9046, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.6110410826258237e-05, + "loss": 3.9058, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.6102024878747717e-05, + "loss": 3.909, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.6093655310040926e-05, + "loss": 3.9126, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085269362530406e-05, + "loss": 3.9198, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607688341501989e-05, + "loss": 3.91, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.606849746750937e-05, + "loss": 3.9201, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.606011151999885e-05, + "loss": 3.9144, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605174195129206e-05, + "loss": 3.9119, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604335600378154e-05, + "loss": 3.9093, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603497005627102e-05, + "loss": 3.9108, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.60265841087605e-05, + "loss": 3.9188, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.601819816124998e-05, + "loss": 3.9024, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.600981221373946e-05, + "loss": 3.9095, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.600144264503267e-05, + "loss": 3.8993, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599305669752215e-05, + "loss": 3.9018, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598467075001163e-05, + "loss": 3.9156, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597628480250111e-05, + "loss": 3.9103, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.5967915233794326e-05, + "loss": 3.9055, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959529286283806e-05, + "loss": 3.8994, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.5951143338773286e-05, + "loss": 3.9121, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.5942757391262766e-05, + "loss": 3.8998, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.5934387822555975e-05, + "loss": 3.9086, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.5926001875045455e-05, + "loss": 3.9007, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.5917615927534935e-05, + "loss": 3.8865, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.5909229980024415e-05, + "loss": 3.8944, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.5900844032513895e-05, + "loss": 3.8906, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.5892474463807104e-05, + "loss": 3.9037, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.5884088516296584e-05, + "loss": 3.8957, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.5875702568786064e-05, + "loss": 3.8946, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.5867316621275544e-05, + "loss": 3.8939, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.5858930673765024e-05, + "loss": 3.8983, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.5850544726254504e-05, + "loss": 3.9068, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.5842158778743984e-05, + "loss": 3.8886, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.58337892100372e-05, + "loss": 3.8883, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582540326252667e-05, + "loss": 3.8925, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581701731501615e-05, + "loss": 3.902, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580863136750563e-05, + "loss": 3.885, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580026179879884e-05, + "loss": 3.8966, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579187585128832e-05, + "loss": 3.8794, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.57834899037778e-05, + "loss": 3.8884, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577510395626728e-05, + "loss": 3.8989, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576671800875677e-05, + "loss": 3.881, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575834844004998e-05, + "loss": 3.8979, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.574996249253946e-05, + "loss": 3.8904, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.574157654502894e-05, + "loss": 3.8697, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.573319059751842e-05, + "loss": 3.8865, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.5724821028811626e-05, + "loss": 3.8896, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.5716435081301106e-05, + "loss": 3.8876, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.5708049133790586e-05, + "loss": 3.8803, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.5699663186280066e-05, + "loss": 3.8831, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.5691293617573275e-05, + "loss": 3.8679, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.5682907670062755e-05, + "loss": 3.8934, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.5674521722552235e-05, + "loss": 3.871, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.5666135775041715e-05, + "loss": 3.8799, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.56577498275312e-05, + "loss": 3.8894, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564938025882441e-05, + "loss": 3.876, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564099431131389e-05, + "loss": 3.8842, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563260836380337e-05, + "loss": 3.8949, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.562422241629285e-05, + "loss": 3.8865, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561585284758606e-05, + "loss": 3.8951, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560746690007554e-05, + "loss": 3.8749, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559908095256502e-05, + "loss": 3.8699, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.55906950050545e-05, + "loss": 3.8747, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558230905754398e-05, + "loss": 3.8942, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557393948883719e-05, + "loss": 3.8781, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556555354132667e-05, + "loss": 3.8712, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557167593816156e-05, + "loss": 3.8653, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548781646305635e-05, + "loss": 3.871, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.5540412077598845e-05, + "loss": 3.8674, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.5532026130088325e-05, + "loss": 3.8717, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.5523640182577804e-05, + "loss": 3.8796, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.5515254235067284e-05, + "loss": 3.8852, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.5506868287556764e-05, + "loss": 3.8725, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.5498498718849973e-05, + "loss": 3.8736, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.5490112771339453e-05, + "loss": 3.8636, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.5481726823828933e-05, + "loss": 3.8705, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547334087631841e-05, + "loss": 3.872, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546498768641536e-05, + "loss": 3.8696, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545660173890484e-05, + "loss": 3.8643, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544821579139432e-05, + "loss": 3.8753, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.54398298438838e-05, + "loss": 3.8705, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543144389637328e-05, + "loss": 3.8829, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542305794886276e-05, + "loss": 3.872, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541467200135224e-05, + "loss": 3.8794, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.540628605384172e-05, + "loss": 3.872, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539791648513493e-05, + "loss": 3.8665, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.538953053762441e-05, + "loss": 3.8852, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538114459011389e-05, + "loss": 3.8648, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.537275864260337e-05, + "loss": 3.8857, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.5364389073896576e-05, + "loss": 3.859, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535600312638606e-05, + "loss": 3.8594, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.534761717887554e-05, + "loss": 3.8617, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533923123136502e-05, + "loss": 3.8759, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.533087804146196e-05, + "loss": 3.8677, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532249209395144e-05, + "loss": 3.8563, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531410614644092e-05, + "loss": 3.8502, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.53057201989304e-05, + "loss": 3.861, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529733425141988e-05, + "loss": 3.8782, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528894830390936e-05, + "loss": 3.8612, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528056235639884e-05, + "loss": 3.8784, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527217640888832e-05, + "loss": 3.8657, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.52637904613778e-05, + "loss": 3.8684, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255420892671017e-05, + "loss": 3.8687, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5247034945160496e-05, + "loss": 3.8573, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.5238648997649976e-05, + "loss": 3.8572, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523026305013945e-05, + "loss": 3.8597, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.5221893481432665e-05, + "loss": 3.8576, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.5213507533922145e-05, + "loss": 3.8595, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.5205121586411625e-05, + "loss": 3.8648, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.51967356389011e-05, + "loss": 3.8646, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.5188366070194314e-05, + "loss": 3.8544, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.5179980122683794e-05, + "loss": 3.8523, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.5171594175173274e-05, + "loss": 3.8751, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.5163208227662754e-05, + "loss": 3.8545, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515483865895597e-05, + "loss": 3.8688, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514645271144545e-05, + "loss": 3.8628, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513806676393492e-05, + "loss": 3.8645, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.51296808164244e-05, + "loss": 3.8577, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512131124771762e-05, + "loss": 3.859, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.51129253002071e-05, + "loss": 3.8588, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510453935269657e-05, + "loss": 3.8605, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509615340518605e-05, + "loss": 3.8752, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508778383647927e-05, + "loss": 3.8621, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507939788896874e-05, + "loss": 3.8664, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507101194145822e-05, + "loss": 3.8631, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506262599394771e-05, + "loss": 3.8515, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.5054256425240924e-05, + "loss": 3.8602, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.50458704777304e-05, + "loss": 3.8511, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503748453021988e-05, + "loss": 3.8551, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502909858270936e-05, + "loss": 3.8536, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502072901400257e-05, + "loss": 3.8515, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.5012343066492046e-05, + "loss": 3.8484, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.5003957118981526e-05, + "loss": 3.8544, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9165520668029785, + "eval_runtime": 561.5936, + "eval_samples_per_second": 679.479, + "eval_steps_per_second": 21.234, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995571171471006e-05, + "loss": 3.8605, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987185223960486e-05, + "loss": 3.8589, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978799276449966e-05, + "loss": 3.8537, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970413328939446e-05, + "loss": 3.8502, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962027381428926e-05, + "loss": 3.8588, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953641433918406e-05, + "loss": 3.8356, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945255486407886e-05, + "loss": 3.8538, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493686953889737e-05, + "loss": 3.8467, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492849997019058e-05, + "loss": 3.8442, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492013040148379e-05, + "loss": 3.8515, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491174445397327e-05, + "loss": 3.856, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490335850646275e-05, + "loss": 3.8372, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489497255895223e-05, + "loss": 3.8443, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488658661144171e-05, + "loss": 3.844, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487820066393119e-05, + "loss": 3.848, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486981471642067e-05, + "loss": 3.8325, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486142876891015e-05, + "loss": 3.8362, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485304282139963e-05, + "loss": 3.84, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484467325269284e-05, + "loss": 3.8426, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836287305182326e-05, + "loss": 3.8523, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827901357671806e-05, + "loss": 3.8399, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819515410161286e-05, + "loss": 3.8532, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811145841454495e-05, + "loss": 3.8484, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802759893943975e-05, + "loss": 3.8458, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794373946433455e-05, + "loss": 3.8389, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.4786004377726664e-05, + "loss": 3.8416, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.4777618430216144e-05, + "loss": 3.8503, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.4769232482705624e-05, + "loss": 3.8374, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760846535195104e-05, + "loss": 3.838, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475246058768458e-05, + "loss": 3.8389, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474409101897779e-05, + "loss": 3.8287, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473570507146728e-05, + "loss": 3.8455, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472731912395676e-05, + "loss": 3.848, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471893317644623e-05, + "loss": 3.8393, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471056360773945e-05, + "loss": 3.8344, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470217766022893e-05, + "loss": 3.8413, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469379171271841e-05, + "loss": 3.8398, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468542214401162e-05, + "loss": 3.8377, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.46770361965011e-05, + "loss": 3.836, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466865024899058e-05, + "loss": 3.8237, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466026430148005e-05, + "loss": 3.8285, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465189473277327e-05, + "loss": 3.8222, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464350878526275e-05, + "loss": 3.8392, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463512283775223e-05, + "loss": 3.8282, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626736890241707e-05, + "loss": 3.8286, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461836732153492e-05, + "loss": 3.8288, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.46099813740244e-05, + "loss": 3.8309, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460159542651388e-05, + "loss": 3.8446, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593209479003356e-05, + "loss": 3.8246, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458483991029657e-05, + "loss": 3.8224, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457645396278605e-05, + "loss": 3.8307, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568068015275525e-05, + "loss": 3.8324, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559682067765004e-05, + "loss": 3.8239, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455131249905822e-05, + "loss": 3.8291, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.45429265515477e-05, + "loss": 3.8203, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453454060403718e-05, + "loss": 3.8252, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452615465652666e-05, + "loss": 3.8345, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8168, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509399140309356e-05, + "loss": 3.8378, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450101319279883e-05, + "loss": 3.8245, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449262724528831e-05, + "loss": 3.8095, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8213, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.8255, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446748578156048e-05, + "loss": 3.8308, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445909983404996e-05, + "loss": 3.8162, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.8231, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.8018, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433958370322134e-05, + "loss": 3.8318, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425572422811614e-05, + "loss": 3.811, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441720285410482e-05, + "loss": 3.8181, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088169065943e-05, + "loss": 3.8258, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440043095908378e-05, + "loss": 3.8167, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439204501157326e-05, + "loss": 3.8203, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438367544286647e-05, + "loss": 3.833, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437528949535595e-05, + "loss": 3.8236, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436690354784543e-05, + "loss": 3.8298, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435851760033491e-05, + "loss": 3.8169, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435014803162813e-05, + "loss": 3.8085, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434176208411761e-05, + "loss": 3.8168, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433337613660709e-05, + "loss": 3.8316, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432499018909657e-05, + "loss": 3.8171, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431662062038978e-05, + "loss": 3.8121, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308234672879257e-05, + "loss": 3.8029, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299848725368737e-05, + "loss": 3.8121, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291462777858217e-05, + "loss": 3.8048, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283093209151426e-05, + "loss": 3.8169, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274707261640906e-05, + "loss": 3.8156, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266321314130386e-05, + "loss": 3.8268, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257935366619865e-05, + "loss": 3.8136, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424956579791308e-05, + "loss": 3.8154, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424117985040256e-05, + "loss": 3.8048, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423279390289204e-05, + "loss": 3.8111, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422440795538152e-05, + "loss": 3.8155, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421603838667473e-05, + "loss": 3.808, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420765243916421e-05, + "loss": 3.8054, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419926649165369e-05, + "loss": 3.8195, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419088054414317e-05, + "loss": 3.8074, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418251097543638e-05, + "loss": 3.8296, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417412502792586e-05, + "loss": 3.809, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416573908041534e-05, + "loss": 3.821, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415735313290482e-05, + "loss": 3.8094, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148983564198035e-05, + "loss": 3.8088, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140597616687515e-05, + "loss": 3.8273, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132211669176995e-05, + "loss": 3.8075, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123825721666475e-05, + "loss": 3.824, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115456152959684e-05, + "loss": 3.8024, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107070205449164e-05, + "loss": 3.8054, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098684257938644e-05, + "loss": 3.8014, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090298310428124e-05, + "loss": 3.8153, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408192874172133e-05, + "loss": 3.8132, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407354279421081e-05, + "loss": 3.8013, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406515684670029e-05, + "loss": 3.7906, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405677089918977e-05, + "loss": 3.8043, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404838495167925e-05, + "loss": 3.8202, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403999900416873e-05, + "loss": 3.8017, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403161305665822e-05, + "loss": 3.8216, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.40232271091477e-05, + "loss": 3.8089, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401485754044091e-05, + "loss": 3.8106, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400647159293039e-05, + "loss": 3.8131, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399808564541987e-05, + "loss": 3.7998, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398969969790935e-05, + "loss": 3.8001, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398133012920256e-05, + "loss": 3.8036, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397294418169204e-05, + "loss": 3.8039, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396455823418152e-05, + "loss": 3.8045, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956172286671e-05, + "loss": 3.8075, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947802717964206e-05, + "loss": 3.8082, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939416770453686e-05, + "loss": 3.7975, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393103082294317e-05, + "loss": 3.7989, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392266125423638e-05, + "loss": 3.8149, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391427530672586e-05, + "loss": 3.7996, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390588935921534e-05, + "loss": 3.8141, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389750341170482e-05, + "loss": 3.8091, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388913384299803e-05, + "loss": 3.806, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388074789548751e-05, + "loss": 3.8033, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387236194797699e-05, + "loss": 3.8035, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386397600046647e-05, + "loss": 3.8039, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385560643175968e-05, + "loss": 3.8044, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384722048424916e-05, + "loss": 3.8191, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383883453673864e-05, + "loss": 3.811, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383044858922813e-05, + "loss": 3.8108, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822079020521336e-05, + "loss": 3.8073, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813693073010816e-05, + "loss": 3.7986, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805307125500296e-05, + "loss": 3.8044, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796921177989776e-05, + "loss": 3.7968, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788551609282985e-05, + "loss": 3.8004, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780165661772465e-05, + "loss": 3.802, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771779714261945e-05, + "loss": 3.7979, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763393766751425e-05, + "loss": 3.7918, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755024198044634e-05, + "loss": 3.8024, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.89079213142395, + "eval_runtime": 570.9046, + "eval_samples_per_second": 668.397, + "eval_steps_per_second": 20.888, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746638250534114e-05, + "loss": 3.8119, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738252303023594e-05, + "loss": 3.8034, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372986635551308e-05, + "loss": 3.8012, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721480408002554e-05, + "loss": 3.8007, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3713094460492034e-05, + "loss": 3.7992, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704708512981514e-05, + "loss": 3.7869, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.3696322565470993e-05, + "loss": 3.8004, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.3687936617960473e-05, + "loss": 3.7881, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367956704925368e-05, + "loss": 3.7954, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.36711974805469e-05, + "loss": 3.8001, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366281153303637e-05, + "loss": 3.7999, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365442558552585e-05, + "loss": 3.7849, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364603963801533e-05, + "loss": 3.7928, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363765369050482e-05, + "loss": 3.7893, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.36292677429943e-05, + "loss": 3.7947, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362088179548378e-05, + "loss": 3.782, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361249584797326e-05, + "loss": 3.7811, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360412627926647e-05, + "loss": 3.7884, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359574033175595e-05, + "loss": 3.7914, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358735438424543e-05, + "loss": 3.7991, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357896843673491e-05, + "loss": 3.7862, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.3570598868028116e-05, + "loss": 3.8044, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562212920517596e-05, + "loss": 3.7914, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553826973007076e-05, + "loss": 3.7962, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545441025496556e-05, + "loss": 3.786, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353707145678977e-05, + "loss": 3.7883, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352868550927925e-05, + "loss": 3.8, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.352029956176873e-05, + "loss": 3.7862, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351191361425821e-05, + "loss": 3.7903, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350354404555142e-05, + "loss": 3.7883, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.34951580980409e-05, + "loss": 3.7754, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348677215053038e-05, + "loss": 3.7967, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347838620301986e-05, + "loss": 3.7925, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347001663431307e-05, + "loss": 3.7916, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346163068680255e-05, + "loss": 3.7817, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345324473929203e-05, + "loss": 3.7932, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344485879178151e-05, + "loss": 3.7842, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436489223074726e-05, + "loss": 3.7888, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3428103275564206e-05, + "loss": 3.7858, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.3419717328053685e-05, + "loss": 3.7712, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411331380543165e-05, + "loss": 3.7794, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402961811836375e-05, + "loss": 3.7704, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394575864325854e-05, + "loss": 3.793, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3386189916815334e-05, + "loss": 3.7807, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377803969304814e-05, + "loss": 3.7761, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369434400598024e-05, + "loss": 3.7832, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361048453087503e-05, + "loss": 3.7815, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352662505576983e-05, + "loss": 3.7937, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334427655806646e-05, + "loss": 3.7728, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333590698935968e-05, + "loss": 3.7743, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332752104184916e-05, + "loss": 3.7833, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331913509433864e-05, + "loss": 3.7823, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331074914682812e-05, + "loss": 3.7744, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330237957812133e-05, + "loss": 3.7763, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329399363061081e-05, + "loss": 3.7722, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328560768310029e-05, + "loss": 3.7783, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327722173558977e-05, + "loss": 3.7814, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326885216688298e-05, + "loss": 3.7749, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326046621937246e-05, + "loss": 3.7872, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325208027186194e-05, + "loss": 3.7744, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.3243710703155146e-05, + "loss": 3.7645, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.3235324755644626e-05, + "loss": 3.7716, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322693880813411e-05, + "loss": 3.7711, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321855286062359e-05, + "loss": 3.7909, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.32101832919168e-05, + "loss": 3.7679, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320179734440628e-05, + "loss": 3.7759, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319341139689576e-05, + "loss": 3.7587, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318502544938524e-05, + "loss": 3.7785, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317665588067845e-05, + "loss": 3.7645, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316826993316793e-05, + "loss": 3.7679, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315988398565741e-05, + "loss": 3.7777, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315149803814689e-05, + "loss": 3.7715, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.31431284694401e-05, + "loss": 3.7722, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313474252192958e-05, + "loss": 3.7841, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.3126356574419067e-05, + "loss": 3.7751, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.3117970626908546e-05, + "loss": 3.7857, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109601058201756e-05, + "loss": 3.7709, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101215110691236e-05, + "loss": 3.7611, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.3092829163180715e-05, + "loss": 3.7667, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.3084443215670195e-05, + "loss": 3.7853, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.3076073646963405e-05, + "loss": 3.7689, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067687699452885e-05, + "loss": 3.7672, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.3059301751942364e-05, + "loss": 3.7549, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.3050915804431844e-05, + "loss": 3.7684, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042546235725054e-05, + "loss": 3.7553, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034160288214533e-05, + "loss": 3.7695, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302577434070402e-05, + "loss": 3.7697, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.30173883931935e-05, + "loss": 3.7767, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300901882448671e-05, + "loss": 3.7684, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300063287697619e-05, + "loss": 3.7698, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299224692946567e-05, + "loss": 3.7585, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298386098195515e-05, + "loss": 3.7643, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297549141324836e-05, + "loss": 3.7667, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296710546573784e-05, + "loss": 3.7647, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295871951822732e-05, + "loss": 3.7578, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.29503335707168e-05, + "loss": 3.7749, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294196400201001e-05, + "loss": 3.7598, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293357805449949e-05, + "loss": 3.7856, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.29252084857927e-05, + "loss": 3.7596, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291682253828218e-05, + "loss": 3.7752, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290843659077166e-05, + "loss": 3.7634, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290005064326114e-05, + "loss": 3.764, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289166469575062e-05, + "loss": 3.7839, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.28832787482401e-05, + "loss": 3.7581, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.2874892800729576e-05, + "loss": 3.7798, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286652323202279e-05, + "loss": 3.7572, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285813728451227e-05, + "loss": 3.7585, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284975133700175e-05, + "loss": 3.7563, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.2841365389491225e-05, + "loss": 3.7683, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283299582078444e-05, + "loss": 3.7681, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282460987327393e-05, + "loss": 3.7599, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.28162239257634e-05, + "loss": 3.7425, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280783797825288e-05, + "loss": 3.7606, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279945203074236e-05, + "loss": 3.7735, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279106608323184e-05, + "loss": 3.764, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278268013572132e-05, + "loss": 3.7729, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.27742941882108e-05, + "loss": 3.7652, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276592461950401e-05, + "loss": 3.7648, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275753867199349e-05, + "loss": 3.7688, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274915272448297e-05, + "loss": 3.7598, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274076677697245e-05, + "loss": 3.7537, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2732397208265665e-05, + "loss": 3.7589, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2724011260755145e-05, + "loss": 3.7598, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715625313244625e-05, + "loss": 3.7612, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2707239365734105e-05, + "loss": 3.7612, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269888617583105e-05, + "loss": 3.7643, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690500228320523e-05, + "loss": 3.7577, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268211428081e-05, + "loss": 3.752, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267372833329948e-05, + "loss": 3.7702, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266534238578896e-05, + "loss": 3.7553, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265695643827844e-05, + "loss": 3.767, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264857049076792e-05, + "loss": 3.7693, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.26401845432574e-05, + "loss": 3.7603, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263181497455062e-05, + "loss": 3.7618, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.26234290270401e-05, + "loss": 3.7603, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261504307952958e-05, + "loss": 3.7587, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260667351082279e-05, + "loss": 3.7577, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259828756331227e-05, + "loss": 3.7748, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258990161580175e-05, + "loss": 3.7715, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258153204709496e-05, + "loss": 3.7629, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257314609958444e-05, + "loss": 3.7644, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256476015207392e-05, + "loss": 3.7567, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.25563742045634e-05, + "loss": 3.7634, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254798825705288e-05, + "loss": 3.7572, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253960230954236e-05, + "loss": 3.7513, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253123274083557e-05, + "loss": 3.7615, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252284679332505e-05, + "loss": 3.7548, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251446084581453e-05, + "loss": 3.748, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250607489830401e-05, + "loss": 3.7553, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8751182556152344, + "eval_runtime": 570.4198, + "eval_samples_per_second": 668.965, + "eval_steps_per_second": 20.906, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249768895079349e-05, + "loss": 3.7668, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248930300328297e-05, + "loss": 3.759, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248091705577245e-05, + "loss": 3.7574, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247253110826193e-05, + "loss": 3.7576, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246414516075141e-05, + "loss": 3.7584, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455759213240885e-05, + "loss": 3.7461, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447373265730365e-05, + "loss": 3.7567, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438987318219845e-05, + "loss": 3.7442, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430617749513054e-05, + "loss": 3.7544, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242224818080627e-05, + "loss": 3.7571, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241386223329575e-05, + "loss": 3.7617, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240547628578524e-05, + "loss": 3.7373, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239709033827471e-05, + "loss": 3.7542, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238870439076419e-05, + "loss": 3.7454, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238031844325367e-05, + "loss": 3.7558, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237193249574315e-05, + "loss": 3.738, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236354654823263e-05, + "loss": 3.7397, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235517697952584e-05, + "loss": 3.7498, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346807410819055e-05, + "loss": 3.7469, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233842146330853e-05, + "loss": 3.7573, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233003551579801e-05, + "loss": 3.7476, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232164956828749e-05, + "loss": 3.7617, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313279999580704e-05, + "loss": 3.7535, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304894052070184e-05, + "loss": 3.7521, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296508104559664e-05, + "loss": 3.744, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288122157049144e-05, + "loss": 3.7494, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279736209538624e-05, + "loss": 3.7579, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271350262028104e-05, + "loss": 3.7482, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262964314517584e-05, + "loss": 3.7451, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254578367007064e-05, + "loss": 3.7492, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224620879830027e-05, + "loss": 3.7373, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223782285078975e-05, + "loss": 3.7548, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222943690327923e-05, + "loss": 3.7549, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222105095576871e-05, + "loss": 3.7517, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221268138706193e-05, + "loss": 3.7405, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220429543955141e-05, + "loss": 3.754, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219590949204089e-05, + "loss": 3.7422, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218752354453037e-05, + "loss": 3.7499, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217915397582358e-05, + "loss": 3.746, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217076802831306e-05, + "loss": 3.7342, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216238208080254e-05, + "loss": 3.7336, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215399613329202e-05, + "loss": 3.7272, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145626564585226e-05, + "loss": 3.7586, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137256995878436e-05, + "loss": 3.7387, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128871048367915e-05, + "loss": 3.7356, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120485100857395e-05, + "loss": 3.7447, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211209915334688e-05, + "loss": 3.7416, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210371320583636e-05, + "loss": 3.7499, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209532725832584e-05, + "loss": 3.7353, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208694131081532e-05, + "loss": 3.7385, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.20785553633048e-05, + "loss": 3.7368, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207018579459801e-05, + "loss": 3.7427, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206181622589122e-05, + "loss": 3.7362, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.20534302783807e-05, + "loss": 3.7326, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204504433087018e-05, + "loss": 3.7362, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203665838335966e-05, + "loss": 3.7398, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202827243584914e-05, + "loss": 3.7395, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201988648833862e-05, + "loss": 3.734, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.20115005408281e-05, + "loss": 3.7474, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003130972121316e-05, + "loss": 3.7364, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994761403414525e-05, + "loss": 3.7261, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986375455904005e-05, + "loss": 3.7326, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977989508393485e-05, + "loss": 3.7321, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969603560882965e-05, + "loss": 3.7511, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961217613372445e-05, + "loss": 3.7304, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952848044665654e-05, + "loss": 3.7336, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944462097155134e-05, + "loss": 3.72, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936076149644614e-05, + "loss": 3.7379, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927690202134094e-05, + "loss": 3.725, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919304254623574e-05, + "loss": 3.7326, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910918307113054e-05, + "loss": 3.7366, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190254873840627e-05, + "loss": 3.7322, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189416279089575e-05, + "loss": 3.7375, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188577684338523e-05, + "loss": 3.7426, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187739089587471e-05, + "loss": 3.7389, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186902132716792e-05, + "loss": 3.7431, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.18606353796574e-05, + "loss": 3.7383, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185224943214688e-05, + "loss": 3.7224, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184386348463636e-05, + "loss": 3.7287, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183547753712584e-05, + "loss": 3.7415, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182710796841905e-05, + "loss": 3.7358, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181872202090853e-05, + "loss": 3.7315, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181033607339801e-05, + "loss": 3.7128, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180195012588749e-05, + "loss": 3.7315, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17935805571807e-05, + "loss": 3.7175, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178519460967018e-05, + "loss": 3.7338, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177680866215966e-05, + "loss": 3.7296, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768422714649136e-05, + "loss": 3.7386, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760036767138616e-05, + "loss": 3.7302, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751650819628096e-05, + "loss": 3.7314, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174328125092131e-05, + "loss": 3.721, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734895303410785e-05, + "loss": 3.7318, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726509355900265e-05, + "loss": 3.7245, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718123408389745e-05, + "loss": 3.7277, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709737460879225e-05, + "loss": 3.7195, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701351513368705e-05, + "loss": 3.7326, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169298194466192e-05, + "loss": 3.723, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.16845959971514e-05, + "loss": 3.7499, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167621004964088e-05, + "loss": 3.7239, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166782410213036e-05, + "loss": 3.7379, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165943815461984e-05, + "loss": 3.7284, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165105220710932e-05, + "loss": 3.7242, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164268263840253e-05, + "loss": 3.7431, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163429669089201e-05, + "loss": 3.725, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162591074338149e-05, + "loss": 3.7406, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161752479587097e-05, + "loss": 3.7247, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160913884836045e-05, + "loss": 3.7182, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160075290084993e-05, + "loss": 3.7195, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592383332143145e-05, + "loss": 3.7324, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1583997384632625e-05, + "loss": 3.7305, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575611437122105e-05, + "loss": 3.7274, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567225489611585e-05, + "loss": 3.7024, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558839542101065e-05, + "loss": 3.7243, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1550469973394274e-05, + "loss": 3.7358, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.1542084025883754e-05, + "loss": 3.7253, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.1533698078373234e-05, + "loss": 3.7355, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.1525312130862714e-05, + "loss": 3.7294, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1516926183352194e-05, + "loss": 3.7294, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508540235841674e-05, + "loss": 3.7312, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150015428833115e-05, + "loss": 3.7243, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149178471962436e-05, + "loss": 3.717, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148339877211384e-05, + "loss": 3.7223, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147501282460333e-05, + "loss": 3.7248, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.14666268770928e-05, + "loss": 3.7244, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145824092958228e-05, + "loss": 3.7248, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.14498713608755e-05, + "loss": 3.7286, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144148541336497e-05, + "loss": 3.72, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143309946585445e-05, + "loss": 3.7166, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142471351834393e-05, + "loss": 3.7337, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141632757083341e-05, + "loss": 3.7175, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140795800212662e-05, + "loss": 3.7336, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13995720546161e-05, + "loss": 3.7313, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139118610710558e-05, + "loss": 3.7254, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138280015959507e-05, + "loss": 3.7277, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137441421208455e-05, + "loss": 3.7271, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136602826457403e-05, + "loss": 3.7207, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135764231706351e-05, + "loss": 3.7208, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349272748356717e-05, + "loss": 3.7396, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340886800846197e-05, + "loss": 3.7337, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332517232139406e-05, + "loss": 3.7303, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324131284628886e-05, + "loss": 3.7294, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315745337118366e-05, + "loss": 3.7198, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307359389607845e-05, + "loss": 3.7251, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298973442097325e-05, + "loss": 3.7196, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290603873390535e-05, + "loss": 3.7136, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128221792588002e-05, + "loss": 3.7298, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.12738319783695e-05, + "loss": 3.7194, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126544603085898e-05, + "loss": 3.7127, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125706008334846e-05, + "loss": 3.7234, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8647923469543457, + "eval_runtime": 311.9235, + "eval_samples_per_second": 1223.348, + "eval_steps_per_second": 38.231, + "step": 534233 + }, + { + "epoch": 1.0, + "learning_rate": 4.124869051464167e-05, + "loss": 3.7242, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124030456713115e-05, + "loss": 3.7211, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123191861962063e-05, + "loss": 3.7279, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122353267211011e-05, + "loss": 3.7213, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121516310340332e-05, + "loss": 3.7213, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.12067771558928e-05, + "loss": 3.7143, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119839120838228e-05, + "loss": 3.7211, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119000526087176e-05, + "loss": 3.7126, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118163569216497e-05, + "loss": 3.7175, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1173249744654455e-05, + "loss": 3.7159, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1164863797143935e-05, + "loss": 3.7272, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156477849633415e-05, + "loss": 3.7084, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148091902122895e-05, + "loss": 3.7188, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139705954612375e-05, + "loss": 3.7079, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131336385905584e-05, + "loss": 3.7235, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1122950438395064e-05, + "loss": 3.7042, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114564490884544e-05, + "loss": 3.7061, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1106178543374024e-05, + "loss": 3.7133, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109780897466723e-05, + "loss": 3.711, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108942302715671e-05, + "loss": 3.7232, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108103707964619e-05, + "loss": 3.7116, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107265113213567e-05, + "loss": 3.7275, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106428156342889e-05, + "loss": 3.7143, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105589561591837e-05, + "loss": 3.7189, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104750966840785e-05, + "loss": 3.7126, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103912372089733e-05, + "loss": 3.7151, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103073777338681e-05, + "loss": 3.7198, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102236820468002e-05, + "loss": 3.7135, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.10139822571695e-05, + "loss": 3.7129, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100559630965898e-05, + "loss": 3.7142, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099721036214846e-05, + "loss": 3.702, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098882441463793e-05, + "loss": 3.7186, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980454845931146e-05, + "loss": 3.7223, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972068898420626e-05, + "loss": 3.7156, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963682950910106e-05, + "loss": 3.7088, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955297003399586e-05, + "loss": 3.7159, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946911055889066e-05, + "loss": 3.7103, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093854148718228e-05, + "loss": 3.7164, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930155539671755e-05, + "loss": 3.7116, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921769592161235e-05, + "loss": 3.7038, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913383644650715e-05, + "loss": 3.7006, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0904997697140195e-05, + "loss": 3.6944, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896628128433404e-05, + "loss": 3.7198, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888242180922884e-05, + "loss": 3.7069, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879856233412364e-05, + "loss": 3.7016, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871470285901844e-05, + "loss": 3.7115, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086308433839133e-05, + "loss": 3.7076, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085471476968454e-05, + "loss": 3.7159, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084632882217402e-05, + "loss": 3.7002, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.08379428746635e-05, + "loss": 3.7063, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082955692715298e-05, + "loss": 3.7028, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082117097964246e-05, + "loss": 3.7089, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081280141093567e-05, + "loss": 3.7077, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080441546342515e-05, + "loss": 3.6978, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079602951591463e-05, + "loss": 3.7058, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078764356840411e-05, + "loss": 3.705, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077927399969732e-05, + "loss": 3.7075, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.07708880521868e-05, + "loss": 3.7025, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762502104676284e-05, + "loss": 3.716, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754116157165764e-05, + "loss": 3.6986, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745746588458974e-05, + "loss": 3.6967, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737360640948453e-05, + "loss": 3.6988, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728974693437933e-05, + "loss": 3.7021, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072058874592741e-05, + "loss": 3.7139, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071220279841689e-05, + "loss": 3.6967, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.07038332297101e-05, + "loss": 3.7014, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069544728219958e-05, + "loss": 3.6913, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068706133468906e-05, + "loss": 3.7057, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067867538717854e-05, + "loss": 3.6937, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067030581847175e-05, + "loss": 3.6999, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066191987096124e-05, + "loss": 3.7027, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065353392345072e-05, + "loss": 3.7002, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.06451479759402e-05, + "loss": 3.7025, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063676202842968e-05, + "loss": 3.7134, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062839245972289e-05, + "loss": 3.7034, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062000651221237e-05, + "loss": 3.7089, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061162056470185e-05, + "loss": 3.7055, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060323461719133e-05, + "loss": 3.6943, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594865048484536e-05, + "loss": 3.6966, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586479100974016e-05, + "loss": 3.7098, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578093153463496e-05, + "loss": 3.7049, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569707205952976e-05, + "loss": 3.6967, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056133763724619e-05, + "loss": 3.6846, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055295168973567e-05, + "loss": 3.6971, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054456574222515e-05, + "loss": 3.6863, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053617979471463e-05, + "loss": 3.7003, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052781022600784e-05, + "loss": 3.6969, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051942427849732e-05, + "loss": 3.7062, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.05110383309868e-05, + "loss": 3.7038, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050265238347628e-05, + "loss": 3.6946, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049426643596576e-05, + "loss": 3.6936, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048589686725897e-05, + "loss": 3.6979, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047751091974845e-05, + "loss": 3.6909, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046912497223793e-05, + "loss": 3.6973, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046073902472741e-05, + "loss": 3.6897, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045235307721689e-05, + "loss": 3.7014, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0443983508510105e-05, + "loss": 3.694, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435597560999585e-05, + "loss": 3.7193, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427211613489065e-05, + "loss": 3.6878, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041882566597854e-05, + "loss": 3.7058, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041043971846802e-05, + "loss": 3.6994, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0402070149761234e-05, + "loss": 3.6923, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039368420225071e-05, + "loss": 3.7068, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038529825474019e-05, + "loss": 3.6977, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037691230722967e-05, + "loss": 3.7058, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036854273852288e-05, + "loss": 3.6941, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036015679101236e-05, + "loss": 3.687, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035177084350184e-05, + "loss": 3.6894, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034338489599132e-05, + "loss": 3.7005, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033501532728454e-05, + "loss": 3.7002, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032662937977401e-05, + "loss": 3.6933, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031824343226349e-05, + "loss": 3.6709, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030985748475297e-05, + "loss": 3.694, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030148791604618e-05, + "loss": 3.7048, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029310196853566e-05, + "loss": 3.6944, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028471602102514e-05, + "loss": 3.7058, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027633007351462e-05, + "loss": 3.6993, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.02679441260041e-05, + "loss": 3.6942, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025957455729732e-05, + "loss": 3.7036, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.02511886097868e-05, + "loss": 3.6951, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024280266227628e-05, + "loss": 3.6878, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023441671476576e-05, + "loss": 3.6902, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022603076725524e-05, + "loss": 3.6931, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217661198548446e-05, + "loss": 3.6918, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209275251037926e-05, + "loss": 3.6893, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200889303527406e-05, + "loss": 3.702, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192503356016886e-05, + "loss": 3.6933, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184133787310095e-05, + "loss": 3.6828, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175747839799575e-05, + "loss": 3.7054, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167361892289055e-05, + "loss": 3.6866, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158975944778535e-05, + "loss": 3.7008, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015060637607175e-05, + "loss": 3.705, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014222042856123e-05, + "loss": 3.6942, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013383448105071e-05, + "loss": 3.6933, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012544853354019e-05, + "loss": 3.6946, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.01170789648334e-05, + "loss": 3.691, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010869301732288e-05, + "loss": 3.6926, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010030706981236e-05, + "loss": 3.7081, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009192112230184e-05, + "loss": 3.7008, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008355155359505e-05, + "loss": 3.7015, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007516560608453e-05, + "loss": 3.697, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006677965857401e-05, + "loss": 3.689, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005839371106349e-05, + "loss": 3.698, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005000776355297e-05, + "loss": 3.6861, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041638194846184e-05, + "loss": 3.6852, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033252247335664e-05, + "loss": 3.6953, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024866299825144e-05, + "loss": 3.693, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016480352314624e-05, + "loss": 3.6793, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000811078360783e-05, + "loss": 3.6968, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.858268976211548, + "eval_runtime": 314.2337, + "eval_samples_per_second": 1214.354, + "eval_steps_per_second": 37.949, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.999972483609731e-05, + "loss": 3.7022, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999133888858679e-05, + "loss": 3.6902, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998295294107627e-05, + "loss": 3.6963, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997456699356575e-05, + "loss": 3.6988, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996618104605523e-05, + "loss": 3.7044, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995781147734844e-05, + "loss": 3.6969, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994942552983792e-05, + "loss": 3.7002, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994103958232741e-05, + "loss": 3.6882, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993265363481689e-05, + "loss": 3.6848, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.99242840661101e-05, + "loss": 3.7, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991589811859958e-05, + "loss": 3.6948, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990751217108906e-05, + "loss": 3.6867, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989912622357854e-05, + "loss": 3.695, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989075665487175e-05, + "loss": 3.6813, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882370707361227e-05, + "loss": 3.6865, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873984759850707e-05, + "loss": 3.677, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865598812340187e-05, + "loss": 3.6825, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857212864829666e-05, + "loss": 3.6912, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848843296122876e-05, + "loss": 3.6844, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840457348612356e-05, + "loss": 3.7017, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983207140110184e-05, + "loss": 3.6989, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823685453591315e-05, + "loss": 3.6972, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981531588488453e-05, + "loss": 3.6875, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980692993737401e-05, + "loss": 3.691, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979854398986349e-05, + "loss": 3.6924, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790158042352964e-05, + "loss": 3.699, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978178847364618e-05, + "loss": 3.6832, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977340252613566e-05, + "loss": 3.6935, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976501657862514e-05, + "loss": 3.6775, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975663063111461e-05, + "loss": 3.6899, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974826106240783e-05, + "loss": 3.6868, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973987511489731e-05, + "loss": 3.6933, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973148916738679e-05, + "loss": 3.6965, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972310321987627e-05, + "loss": 3.7004, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971471727236575e-05, + "loss": 3.6826, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706347703658965e-05, + "loss": 3.6894, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969796175614844e-05, + "loss": 3.6945, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968957580863792e-05, + "loss": 3.6788, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.96811898611274e-05, + "loss": 3.6802, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672820292420614e-05, + "loss": 3.6724, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966443434491009e-05, + "loss": 3.6773, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965604839739957e-05, + "loss": 3.6824, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964766244988905e-05, + "loss": 3.691, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963929288118226e-05, + "loss": 3.6858, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963090693367174e-05, + "loss": 3.6795, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962252098616122e-05, + "loss": 3.6829, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.96141350386507e-05, + "loss": 3.6894, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960576546994391e-05, + "loss": 3.6737, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959737952243339e-05, + "loss": 3.6606, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958899357492287e-05, + "loss": 3.6931, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958060762741235e-05, + "loss": 3.6862, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957223805870556e-05, + "loss": 3.6931, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956385211119504e-05, + "loss": 3.6827, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955546616368452e-05, + "loss": 3.6838, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547080216174e-05, + "loss": 3.6754, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538710647467217e-05, + "loss": 3.6756, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530324699956696e-05, + "loss": 3.6879, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9521938752446176e-05, + "loss": 3.6711, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513552804935656e-05, + "loss": 3.7021, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505183236228865e-05, + "loss": 3.681, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496797288718345e-05, + "loss": 3.6644, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488411341207825e-05, + "loss": 3.6933, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480025393697305e-05, + "loss": 3.6724, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471655824990514e-05, + "loss": 3.6635, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463269877479994e-05, + "loss": 3.6883, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454883929969474e-05, + "loss": 3.6849, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446497982458954e-05, + "loss": 3.6754, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943812841375217e-05, + "loss": 3.6748, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942974246624165e-05, + "loss": 3.6616, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942135651873113e-05, + "loss": 3.6733, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941297057122061e-05, + "loss": 3.6854, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940460100251382e-05, + "loss": 3.6724, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.93962150550033e-05, + "loss": 3.681, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938782910749278e-05, + "loss": 3.677, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937944315998226e-05, + "loss": 3.6892, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937107359127547e-05, + "loss": 3.6792, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936268764376495e-05, + "loss": 3.6803, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935430169625443e-05, + "loss": 3.6757, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934591574874391e-05, + "loss": 3.6705, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337529801233395e-05, + "loss": 3.6849, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329160232526604e-05, + "loss": 3.6789, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320774285016084e-05, + "loss": 3.6706, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312388337505564e-05, + "loss": 3.6867, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304002389995044e-05, + "loss": 3.6594, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929563282128825e-05, + "loss": 3.6702, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928724687377773e-05, + "loss": 3.6776, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927886092626721e-05, + "loss": 3.6779, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927047497875669e-05, + "loss": 3.6663, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621054100499e-05, + "loss": 3.6803, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925371946253938e-05, + "loss": 3.6685, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924533351502886e-05, + "loss": 3.6727, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923694756751835e-05, + "loss": 3.6644, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922857799881156e-05, + "loss": 3.6721, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922019205130104e-05, + "loss": 3.6871, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921180610379052e-05, + "loss": 3.6787, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920342015628e-05, + "loss": 3.679, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195050587573206e-05, + "loss": 3.6699, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186664640062686e-05, + "loss": 3.6683, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178278692552166e-05, + "loss": 3.6719, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169892745041646e-05, + "loss": 3.6799, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161523176334855e-05, + "loss": 3.6763, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153137228824335e-05, + "loss": 3.677, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144751281313815e-05, + "loss": 3.6718, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.91363653338033e-05, + "loss": 3.6767, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912797938629278e-05, + "loss": 3.6738, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911960981758599e-05, + "loss": 3.6713, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911122387007547e-05, + "loss": 3.6595, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910283792256495e-05, + "loss": 3.6829, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909445197505443e-05, + "loss": 3.6654, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908608240634764e-05, + "loss": 3.6696, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907769645883712e-05, + "loss": 3.6665, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.90693105113266e-05, + "loss": 3.6671, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906092456381608e-05, + "loss": 3.6748, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905255499510929e-05, + "loss": 3.6687, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904416904759877e-05, + "loss": 3.6788, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035783100088256e-05, + "loss": 3.6833, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027397152577736e-05, + "loss": 3.6804, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019027583870945e-05, + "loss": 3.6748, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010641636360425e-05, + "loss": 3.6695, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002255688849905e-05, + "loss": 3.6664, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993869741339385e-05, + "loss": 3.6715, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985500172632594e-05, + "loss": 3.6748, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977114225122074e-05, + "loss": 3.6628, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968728277611554e-05, + "loss": 3.671, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960342330101034e-05, + "loss": 3.6744, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895197276139424e-05, + "loss": 3.6716, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894358681388372e-05, + "loss": 3.6707, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.89352008663732e-05, + "loss": 3.6731, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892681491886269e-05, + "loss": 3.6654, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.89184453501559e-05, + "loss": 3.6757, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891005940264538e-05, + "loss": 3.6726, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890167345513486e-05, + "loss": 3.6863, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889328750762434e-05, + "loss": 3.6592, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888491793891755e-05, + "loss": 3.6707, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887653199140703e-05, + "loss": 3.6735, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886814604389651e-05, + "loss": 3.6713, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885976009638599e-05, + "loss": 3.6728, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885137414887546e-05, + "loss": 3.6726, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843004580168676e-05, + "loss": 3.6747, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8834618632658156e-05, + "loss": 3.6877, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882623268514764e-05, + "loss": 3.6675, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817846737637116e-05, + "loss": 3.6747, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880947716893033e-05, + "loss": 3.6758, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880109122141981e-05, + "loss": 3.6647, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792705273909285e-05, + "loss": 3.6658, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784319326398765e-05, + "loss": 3.6656, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877594975769198e-05, + "loss": 3.667, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876756381018146e-05, + "loss": 3.6605, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759177862670934e-05, + "loss": 3.6689, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8498642444610596, + "eval_runtime": 303.0057, + "eval_samples_per_second": 1259.353, + "eval_steps_per_second": 39.356, + "step": 686872 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750791915160414e-05, + "loss": 3.6701, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742405967649894e-05, + "loss": 3.6629, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873403639894311e-05, + "loss": 3.6675, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872565045143259e-05, + "loss": 3.6714, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871726450392207e-05, + "loss": 3.678, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6688, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870050898770476e-05, + "loss": 3.6703, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869212304019424e-05, + "loss": 3.6578, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868373709268372e-05, + "loss": 3.6593, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675367523976935e-05, + "loss": 3.6693, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866698157646641e-05, + "loss": 3.665, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865859562895589e-05, + "loss": 3.6625, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6675, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.653, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633454165228064e-05, + "loss": 3.6568, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625068217717544e-05, + "loss": 3.6479, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616682270207024e-05, + "loss": 3.6586, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608296322696503e-05, + "loss": 3.6629, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859992675398971e-05, + "loss": 3.6532, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859154080647919e-05, + "loss": 3.6726, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858315485896867e-05, + "loss": 3.6718, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857476891145815e-05, + "loss": 3.6672, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856639934275136e-05, + "loss": 3.66, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855801339524084e-05, + "loss": 3.6613, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854962744773032e-05, + "loss": 3.6642, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854125787902354e-05, + "loss": 3.6695, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853287193151302e-05, + "loss": 3.6511, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.85244859840025e-05, + "loss": 3.6624, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851610003649198e-05, + "loss": 3.6521, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850771408898146e-05, + "loss": 3.6586, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499344520274666e-05, + "loss": 3.6619, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8490958572764146e-05, + "loss": 3.6611, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482572625253626e-05, + "loss": 3.6644, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474186677743106e-05, + "loss": 3.6755, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465817109036315e-05, + "loss": 3.6565, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457431161525795e-05, + "loss": 3.6598, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449045214015275e-05, + "loss": 3.6673, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440659266504755e-05, + "loss": 3.6512, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843228969779797e-05, + "loss": 3.6515, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842390375028745e-05, + "loss": 3.6498, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841551780277693e-05, + "loss": 3.6491, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840713185526641e-05, + "loss": 3.6522, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839876228655962e-05, + "loss": 3.6672, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.83903763390491e-05, + "loss": 3.6546, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838199039153858e-05, + "loss": 3.6551, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837360444402806e-05, + "loss": 3.6521, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836523487532127e-05, + "loss": 3.6615, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835684892781075e-05, + "loss": 3.6448, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834846298030023e-05, + "loss": 3.637, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834007703278971e-05, + "loss": 3.6645, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331707464082925e-05, + "loss": 3.6597, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323321516572405e-05, + "loss": 3.6683, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314935569061885e-05, + "loss": 3.6517, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306549621551364e-05, + "loss": 3.6548, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298180052844574e-05, + "loss": 3.6474, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289794105334054e-05, + "loss": 3.6465, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281408157823533e-05, + "loss": 3.6644, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8273022210313013e-05, + "loss": 3.6422, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826465264160622e-05, + "loss": 3.6751, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.82562666940957e-05, + "loss": 3.6577, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824788074658518e-05, + "loss": 3.6329, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823949479907466e-05, + "loss": 3.6656, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823112523036788e-05, + "loss": 3.6485, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822273928285736e-05, + "loss": 3.6355, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821435333534684e-05, + "loss": 3.6603, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820596738783632e-05, + "loss": 3.6599, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819759781912953e-05, + "loss": 3.6466, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818921187161901e-05, + "loss": 3.6507, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818082592410849e-05, + "loss": 3.6323, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817243997659797e-05, + "loss": 3.6486, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164070407891176e-05, + "loss": 3.6568, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155684460380656e-05, + "loss": 3.6441, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147298512870136e-05, + "loss": 3.6573, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138912565359616e-05, + "loss": 3.646, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130526617849096e-05, + "loss": 3.6639, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812215704914231e-05, + "loss": 3.6521, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811377110163179e-05, + "loss": 3.6539, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810538515412127e-05, + "loss": 3.6466, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809699920661075e-05, + "loss": 3.6456, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808862963790396e-05, + "loss": 3.6571, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808024369039344e-05, + "loss": 3.6515, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807185774288292e-05, + "loss": 3.6502, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.80634717953724e-05, + "loss": 3.6534, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805510222666561e-05, + "loss": 3.6412, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804671627915509e-05, + "loss": 3.6373, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803833033164457e-05, + "loss": 3.6488, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802994438413405e-05, + "loss": 3.6558, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021558436623536e-05, + "loss": 3.6377, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013188867916746e-05, + "loss": 3.6507, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004802920406225e-05, + "loss": 3.6454, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996416972895705e-05, + "loss": 3.6454, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7988031025385185e-05, + "loss": 3.6398, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979661456678394e-05, + "loss": 3.6451, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971275509167874e-05, + "loss": 3.6611, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962889561657354e-05, + "loss": 3.6536, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954503614146834e-05, + "loss": 3.6517, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946134045440043e-05, + "loss": 3.643, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937748097929523e-05, + "loss": 3.6418, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929362150419e-05, + "loss": 3.6447, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792099258171222e-05, + "loss": 3.656, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.79126066342017e-05, + "loss": 3.6504, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790422068669118e-05, + "loss": 3.6526, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789583473918066e-05, + "loss": 3.6472, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788744879167013e-05, + "loss": 3.6471, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787907922296335e-05, + "loss": 3.6495, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787069327545283e-05, + "loss": 3.6458, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786230732794231e-05, + "loss": 3.6374, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785393775923552e-05, + "loss": 3.6503, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845551811725e-05, + "loss": 3.6421, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783716586421448e-05, + "loss": 3.6422, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782877991670396e-05, + "loss": 3.6447, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782041034799717e-05, + "loss": 3.6377, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781202440048665e-05, + "loss": 3.6513, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780363845297613e-05, + "loss": 3.6428, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795252505465606e-05, + "loss": 3.6521, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778688293675882e-05, + "loss": 3.6581, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.77784969892483e-05, + "loss": 3.6538, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777011104173778e-05, + "loss": 3.6495, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761725094227255e-05, + "loss": 3.6443, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775335552552047e-05, + "loss": 3.6399, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774496957800995e-05, + "loss": 3.646, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773658363049943e-05, + "loss": 3.6495, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772819768298891e-05, + "loss": 3.6356, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771981173547839e-05, + "loss": 3.6455, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711442166771607e-05, + "loss": 3.6473, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770305621926108e-05, + "loss": 3.6475, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769467027175056e-05, + "loss": 3.6449, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768628432424004e-05, + "loss": 3.6459, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7677914755533255e-05, + "loss": 3.6384, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766952880802273e-05, + "loss": 3.6533, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766114286051221e-05, + "loss": 3.6459, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765275691300169e-05, + "loss": 3.6618, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644387344294904e-05, + "loss": 3.6357, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7636001396784384e-05, + "loss": 3.6445, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627615449273864e-05, + "loss": 3.6541, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619229501763344e-05, + "loss": 3.6409, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610859933056553e-05, + "loss": 3.6481, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760247398554603e-05, + "loss": 3.6443, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759408803803551e-05, + "loss": 3.6522, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758570209052499e-05, + "loss": 3.6596, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.75773325218182e-05, + "loss": 3.6461, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756894657430768e-05, + "loss": 3.6467, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756056062679716e-05, + "loss": 3.649, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755217467928664e-05, + "loss": 3.6441, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754380511057986e-05, + "loss": 3.6408, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753541916306934e-05, + "loss": 3.641, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752703321555882e-05, + "loss": 3.6438, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.75186472680483e-05, + "loss": 3.6369, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751027769934151e-05, + "loss": 3.6414, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8469488620758057, + "eval_runtime": 303.0358, + "eval_samples_per_second": 1259.227, + "eval_steps_per_second": 39.352, + "step": 763192 + }, + { + "epoch": 0.0, + "learning_rate": 3.750189175183099e-05, + "loss": 3.6456, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749350580432047e-05, + "loss": 3.6363, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748511985680995e-05, + "loss": 3.6442, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747673390929943e-05, + "loss": 3.6466, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7468364340592636e-05, + "loss": 3.6544, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459978393082116e-05, + "loss": 3.6414, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451592445571596e-05, + "loss": 3.6482, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7443206498061076e-05, + "loss": 3.6364, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743483692935429e-05, + "loss": 3.632, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742645098184377e-05, + "loss": 3.6394, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741806503433325e-05, + "loss": 3.6451, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740967908682273e-05, + "loss": 3.6372, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740130951811594e-05, + "loss": 3.6415, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739292357060542e-05, + "loss": 3.6281, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.73845376230949e-05, + "loss": 3.6344, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737615167558438e-05, + "loss": 3.6189, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736776572807386e-05, + "loss": 3.6369, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735937978056334e-05, + "loss": 3.6407, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735099383305282e-05, + "loss": 3.6264, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.73426078855423e-05, + "loss": 3.6476, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733423831683551e-05, + "loss": 3.6469, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325852369324996e-05, + "loss": 3.6437, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317466421814476e-05, + "loss": 3.6372, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309080474303956e-05, + "loss": 3.6374, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300710905597165e-05, + "loss": 3.6423, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292324958086645e-05, + "loss": 3.6473, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283939010576125e-05, + "loss": 3.6273, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275553063065605e-05, + "loss": 3.6388, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267183494358814e-05, + "loss": 3.6304, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258797546848294e-05, + "loss": 3.6325, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250411599337774e-05, + "loss": 3.6385, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7242025651827254e-05, + "loss": 3.6394, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723365608312046e-05, + "loss": 3.638, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722527013560994e-05, + "loss": 3.6521, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721688418809943e-05, + "loss": 3.6348, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720849824058891e-05, + "loss": 3.6382, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720012867188212e-05, + "loss": 3.6453, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.71917427243716e-05, + "loss": 3.6226, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718335677686108e-05, + "loss": 3.628, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717497082935056e-05, + "loss": 3.6293, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716660126064377e-05, + "loss": 3.6215, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715821531313325e-05, + "loss": 3.6309, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714982936562273e-05, + "loss": 3.6426, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714144341811221e-05, + "loss": 3.632, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713307384940542e-05, + "loss": 3.6311, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.71246879018949e-05, + "loss": 3.631, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116301954384384e-05, + "loss": 3.6378, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107916006873863e-05, + "loss": 3.6228, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709954643816707e-05, + "loss": 3.6123, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709116049065655e-05, + "loss": 3.6403, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708277454314603e-05, + "loss": 3.6368, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707438859563551e-05, + "loss": 3.6432, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706601902692872e-05, + "loss": 3.6291, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.70576330794182e-05, + "loss": 3.6291, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704924713190768e-05, + "loss": 3.6264, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040861184397155e-05, + "loss": 3.6237, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703249161569037e-05, + "loss": 3.6416, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702410566817985e-05, + "loss": 3.6131, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701571972066934e-05, + "loss": 3.6567, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700733377315881e-05, + "loss": 3.6348, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998964204452026e-05, + "loss": 3.6137, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990578256941506e-05, + "loss": 3.6383, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982192309430986e-05, + "loss": 3.6256, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697380636192046e-05, + "loss": 3.6156, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6965436793213675e-05, + "loss": 3.6361, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6957050845703155e-05, + "loss": 3.6366, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694866489819263e-05, + "loss": 3.6184, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694027895068211e-05, + "loss": 3.6328, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6931909381975324e-05, + "loss": 3.6087, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923523434464804e-05, + "loss": 3.6223, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915137486954284e-05, + "loss": 3.6302, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906751539443764e-05, + "loss": 3.6259, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689838197073698e-05, + "loss": 3.6297, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688999602322646e-05, + "loss": 3.6261, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688161007571593e-05, + "loss": 3.6406, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687322412820541e-05, + "loss": 3.6279, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686485455949863e-05, + "loss": 3.6355, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.68564686119881e-05, + "loss": 3.6226, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684808266447758e-05, + "loss": 3.6209, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683969671696706e-05, + "loss": 3.6328, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683132714826028e-05, + "loss": 3.6279, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682294120074976e-05, + "loss": 3.6273, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681455525323924e-05, + "loss": 3.6346, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680616930572872e-05, + "loss": 3.6214, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679779973702193e-05, + "loss": 3.6106, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678941378951141e-05, + "loss": 3.6265, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678102784200089e-05, + "loss": 3.6314, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677264189449037e-05, + "loss": 3.616, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764272325783576e-05, + "loss": 3.6294, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755886378273056e-05, + "loss": 3.6251, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747500430762536e-05, + "loss": 3.6189, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6739114483252016e-05, + "loss": 3.6164, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673074491454523e-05, + "loss": 3.6238, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672235896703471e-05, + "loss": 3.6407, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671397301952419e-05, + "loss": 3.6307, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670558707201367e-05, + "loss": 3.6284, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669721750330688e-05, + "loss": 3.6215, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668883155579636e-05, + "loss": 3.6189, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668044560828584e-05, + "loss": 3.6207, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667205966077532e-05, + "loss": 3.632, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666369009206853e-05, + "loss": 3.6297, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665530414455801e-05, + "loss": 3.6299, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664691819704749e-05, + "loss": 3.6248, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663853224953697e-05, + "loss": 3.6192, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630162680830185e-05, + "loss": 3.6283, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621776733319665e-05, + "loss": 3.6257, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613390785809145e-05, + "loss": 3.6151, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6605004838298625e-05, + "loss": 3.6261, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596635269591834e-05, + "loss": 3.6229, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588249322081314e-05, + "loss": 3.6212, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579863374570794e-05, + "loss": 3.6171, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571477427060274e-05, + "loss": 3.6157, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656310785835348e-05, + "loss": 3.6267, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655472191084296e-05, + "loss": 3.6272, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654633596333244e-05, + "loss": 3.625, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653795001582192e-05, + "loss": 3.6331, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652958044711514e-05, + "loss": 3.6343, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652119449960462e-05, + "loss": 3.6251, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.65128085520941e-05, + "loss": 3.6237, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650442260458358e-05, + "loss": 3.615, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649605303587679e-05, + "loss": 3.6277, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648766708836627e-05, + "loss": 3.6238, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647928114085575e-05, + "loss": 3.6152, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647089519334523e-05, + "loss": 3.6205, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646252562463844e-05, + "loss": 3.6276, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645413967712792e-05, + "loss": 3.627, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.64457537296174e-05, + "loss": 3.6188, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643736778210688e-05, + "loss": 3.6235, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642899821340009e-05, + "loss": 3.6218, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642061226588957e-05, + "loss": 3.6269, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641222631837905e-05, + "loss": 3.6282, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640384037086853e-05, + "loss": 3.6362, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639547080216174e-05, + "loss": 3.6176, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638708485465122e-05, + "loss": 3.6233, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.63786989071407e-05, + "loss": 3.6284, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637031295963018e-05, + "loss": 3.6168, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636194339092339e-05, + "loss": 3.6268, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635355744341287e-05, + "loss": 3.6247, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634517149590235e-05, + "loss": 3.63, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633678554839183e-05, + "loss": 3.6367, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328415979685046e-05, + "loss": 3.6243, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6320030032174526e-05, + "loss": 3.6256, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311644084664006e-05, + "loss": 3.6258, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303258137153486e-05, + "loss": 3.6208, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294888568446695e-05, + "loss": 3.6184, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286502620936175e-05, + "loss": 3.6215, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278116673425655e-05, + "loss": 3.6183, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269730725915135e-05, + "loss": 3.6207, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261361157208344e-05, + "loss": 3.6187, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.846691131591797, + "eval_runtime": 310.3465, + "eval_samples_per_second": 1229.564, + "eval_steps_per_second": 38.425, + "step": 839512 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252975209697824e-05, + "loss": 3.6215, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244589262187304e-05, + "loss": 3.6167, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236203314676784e-05, + "loss": 3.623, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622783374597e-05, + "loss": 3.626, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621944779845948e-05, + "loss": 3.6315, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621106185094896e-05, + "loss": 3.622, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620267590343844e-05, + "loss": 3.6282, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619430633473165e-05, + "loss": 3.6165, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618592038722113e-05, + "loss": 3.6095, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617753443971061e-05, + "loss": 3.6141, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616914849220009e-05, + "loss": 3.6308, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.61607789234933e-05, + "loss": 3.6133, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615240935478651e-05, + "loss": 3.6221, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614402340727599e-05, + "loss": 3.6049, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613563745976547e-05, + "loss": 3.6098, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127251512254953e-05, + "loss": 3.6021, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118865564744433e-05, + "loss": 3.6179, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110479617233913e-05, + "loss": 3.616, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610209366972339e-05, + "loss": 3.6119, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609370772221287e-05, + "loss": 3.6182, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608532177470235e-05, + "loss": 3.6311, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607695220599556e-05, + "loss": 3.621, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606856625848504e-05, + "loss": 3.6164, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606018031097452e-05, + "loss": 3.6131, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051794363464e-05, + "loss": 3.6279, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604342479475721e-05, + "loss": 3.6219, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603503884724669e-05, + "loss": 3.61, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602665289973617e-05, + "loss": 3.6176, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601826695222565e-05, + "loss": 3.6113, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600989738351887e-05, + "loss": 3.607, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600151143600835e-05, + "loss": 3.6187, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599312548849783e-05, + "loss": 3.6173, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598473954098731e-05, + "loss": 3.6201, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5976369972280516e-05, + "loss": 3.6303, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.5967984024769996e-05, + "loss": 3.61, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.5959598077259476e-05, + "loss": 3.6193, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5951228508552685e-05, + "loss": 3.6202, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942842561042165e-05, + "loss": 3.6058, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934456613531645e-05, + "loss": 3.6108, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5926070666021125e-05, + "loss": 3.6012, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591770109731434e-05, + "loss": 3.6022, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590931514980382e-05, + "loss": 3.6081, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.59009292022933e-05, + "loss": 3.6236, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589254325478278e-05, + "loss": 3.6119, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588417368607599e-05, + "loss": 3.6081, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587578773856547e-05, + "loss": 3.6155, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586740179105495e-05, + "loss": 3.6124, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585901584354442e-05, + "loss": 3.6031, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585064627483764e-05, + "loss": 3.5919, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584226032732712e-05, + "loss": 3.6176, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.58338743798166e-05, + "loss": 3.618, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582548843230608e-05, + "loss": 3.6215, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5817118863599294e-05, + "loss": 3.6115, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808732916088774e-05, + "loss": 3.6066, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800346968578254e-05, + "loss": 3.6042, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579196102106773e-05, + "loss": 3.6018, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783591452360943e-05, + "loss": 3.6191, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577520550485042e-05, + "loss": 3.5968, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766819557339897e-05, + "loss": 3.6321, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758433609829377e-05, + "loss": 3.6116, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.575006404112259e-05, + "loss": 3.5978, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574167809361207e-05, + "loss": 3.6132, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573329214610155e-05, + "loss": 3.6033, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572490619859103e-05, + "loss": 3.5956, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571653662988425e-05, + "loss": 3.612, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570815068237373e-05, + "loss": 3.6175, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.56997647348632e-05, + "loss": 3.603, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569137878735268e-05, + "loss": 3.6095, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.56830092186459e-05, + "loss": 3.587, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567462327113537e-05, + "loss": 3.604, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566623732362485e-05, + "loss": 3.606, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565785137611433e-05, + "loss": 3.6094, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649481807407546e-05, + "loss": 3.6079, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564109585989702e-05, + "loss": 3.6059, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632709912386506e-05, + "loss": 3.6241, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624323964875986e-05, + "loss": 3.6089, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.56159543961692e-05, + "loss": 3.6126, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607568448658675e-05, + "loss": 3.6046, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599182501148155e-05, + "loss": 3.6036, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590796553637635e-05, + "loss": 3.6116, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582426984930844e-05, + "loss": 3.6082, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5574041037420324e-05, + "loss": 3.6043, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565655089909804e-05, + "loss": 3.613, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557269142399284e-05, + "loss": 3.6036, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554889957369249e-05, + "loss": 3.5899, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554051362618197e-05, + "loss": 3.6035, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553212767867146e-05, + "loss": 3.6101, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552374173116094e-05, + "loss": 3.5984, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551537216245415e-05, + "loss": 3.6068, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550698621494363e-05, + "loss": 3.6043, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549860026743311e-05, + "loss": 3.5961, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549021431992259e-05, + "loss": 3.5995, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.54818447512158e-05, + "loss": 3.6003, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547345880370528e-05, + "loss": 3.617, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546507285619476e-05, + "loss": 3.6139, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545668690868424e-05, + "loss": 3.61, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448317339977447e-05, + "loss": 3.5966, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439931392466927e-05, + "loss": 3.5982, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543154544495641e-05, + "loss": 3.6053, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542315949744589e-05, + "loss": 3.6105, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.54147899287391e-05, + "loss": 3.6081, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540640398122858e-05, + "loss": 3.6089, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539801803371806e-05, + "loss": 3.6041, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538963208620754e-05, + "loss": 3.6003, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538126251750075e-05, + "loss": 3.6102, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537287656999023e-05, + "loss": 3.6031, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536449062247971e-05, + "loss": 3.6007, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535610467496919e-05, + "loss": 3.6035, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.53477351062624e-05, + "loss": 3.604, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533934915875188e-05, + "loss": 3.6013, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533096321124136e-05, + "loss": 3.5959, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532257726373085e-05, + "loss": 3.5957, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5314207695024056e-05, + "loss": 3.6083, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305821747513536e-05, + "loss": 3.6063, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5297435800003016e-05, + "loss": 3.6032, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5289049852492496e-05, + "loss": 3.6111, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280680283785705e-05, + "loss": 3.6192, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5272294336275185e-05, + "loss": 3.6026, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5263908388764665e-05, + "loss": 3.6025, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5255522441254145e-05, + "loss": 3.5992, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5247152872547354e-05, + "loss": 3.6038, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238766925036834e-05, + "loss": 3.6029, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230380977526314e-05, + "loss": 3.6014, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.52219950300158e-05, + "loss": 3.6004, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521362546130901e-05, + "loss": 3.6089, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520523951379849e-05, + "loss": 3.605, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519685356628797e-05, + "loss": 3.6002, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518846761877745e-05, + "loss": 3.6051, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.518009805007066e-05, + "loss": 3.6022, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517171210256014e-05, + "loss": 3.6028, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516332615504962e-05, + "loss": 3.6067, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.51549402075391e-05, + "loss": 3.6148, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514657063883231e-05, + "loss": 3.597, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513818469132179e-05, + "loss": 3.6031, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512979874381127e-05, + "loss": 3.6068, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121412796300754e-05, + "loss": 3.6001, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511304322759396e-05, + "loss": 3.6013, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510465728008344e-05, + "loss": 3.605, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509627133257292e-05, + "loss": 3.6151, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.50878853850624e-05, + "loss": 3.613, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507951581635561e-05, + "loss": 3.6045, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507112986884509e-05, + "loss": 3.6057, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506274392133457e-05, + "loss": 3.6077, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505435797382405e-05, + "loss": 3.6025, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504598840511726e-05, + "loss": 3.598, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503760245760674e-05, + "loss": 3.6048, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502921651009622e-05, + "loss": 3.5939, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502083056258571e-05, + "loss": 3.6012, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501246099387892e-05, + "loss": 3.5985, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8455798625946045, + "eval_runtime": 310.8509, + "eval_samples_per_second": 1227.569, + "eval_steps_per_second": 38.362, + "step": 915832 + }, + { + "epoch": 0.0, + "learning_rate": 3.50040750463684e-05, + "loss": 3.6122, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499568909885788e-05, + "loss": 3.5938, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498730315134736e-05, + "loss": 3.6026, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497891720383684e-05, + "loss": 3.6082, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970547635130046e-05, + "loss": 3.6081, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4962161687619526e-05, + "loss": 3.6035, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953775740109006e-05, + "loss": 3.6108, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945389792598486e-05, + "loss": 3.5947, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4937020223891695e-05, + "loss": 3.5919, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928634276381175e-05, + "loss": 3.6001, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492024832887066e-05, + "loss": 3.6041, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491186238136014e-05, + "loss": 3.5953, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490349281265335e-05, + "loss": 3.6065, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489510686514283e-05, + "loss": 3.5853, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488672091763231e-05, + "loss": 3.5922, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487833497012179e-05, + "loss": 3.5784, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869965401415e-05, + "loss": 3.6, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486157945390448e-05, + "loss": 3.5939, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485319350639396e-05, + "loss": 3.5944, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484480755888344e-05, + "loss": 3.5998, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483643799017665e-05, + "loss": 3.6093, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482805204266613e-05, + "loss": 3.6042, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819666095155615e-05, + "loss": 3.5974, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4811280147645095e-05, + "loss": 3.5934, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4802910578938304e-05, + "loss": 3.6091, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794524631427784e-05, + "loss": 3.5997, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4786138683917264e-05, + "loss": 3.5911, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777752736406744e-05, + "loss": 3.5983, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476938316769995e-05, + "loss": 3.5875, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476099722018943e-05, + "loss": 3.5927, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475261127267891e-05, + "loss": 3.5989, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474422532516839e-05, + "loss": 3.5967, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.47358557564616e-05, + "loss": 3.6024, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472746980895108e-05, + "loss": 3.6079, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471908386144057e-05, + "loss": 3.592, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471069791393005e-05, + "loss": 3.6005, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470232834522326e-05, + "loss": 3.6041, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469394239771274e-05, + "loss": 3.5862, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468555645020222e-05, + "loss": 3.5929, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467717050269169e-05, + "loss": 3.5809, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466880093398491e-05, + "loss": 3.5827, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466041498647439e-05, + "loss": 3.5908, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465202903896387e-05, + "loss": 3.6026, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464364309145334e-05, + "loss": 3.5894, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4635273522746556e-05, + "loss": 3.5911, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626887575236036e-05, + "loss": 3.5913, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618501627725516e-05, + "loss": 3.5965, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4610115680214996e-05, + "loss": 3.5827, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460174611150821e-05, + "loss": 3.5748, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459336016399769e-05, + "loss": 3.5933, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584974216487165e-05, + "loss": 3.6044, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576588268976645e-05, + "loss": 3.6025, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456821870026986e-05, + "loss": 3.5844, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455983275275934e-05, + "loss": 3.5923, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551446805248814e-05, + "loss": 3.5852, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4543060857738294e-05, + "loss": 3.5796, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453469128903151e-05, + "loss": 3.6063, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452630534152099e-05, + "loss": 3.5776, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451791939401047e-05, + "loss": 3.6112, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450953344649995e-05, + "loss": 3.593, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4501163877793165e-05, + "loss": 3.5792, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449277793028264e-05, + "loss": 3.595, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448439198277212e-05, + "loss": 3.5882, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.44760060352616e-05, + "loss": 3.5759, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467636466554814e-05, + "loss": 3.5922, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445925051904429e-05, + "loss": 3.5961, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445086457153377e-05, + "loss": 3.5834, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444247862402325e-05, + "loss": 3.5921, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443410905531646e-05, + "loss": 3.5672, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442572310780594e-05, + "loss": 3.5859, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441733716029542e-05, + "loss": 3.589, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.44089512127849e-05, + "loss": 3.5924, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440058164407811e-05, + "loss": 3.5844, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439219569656759e-05, + "loss": 3.5887, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438380974905707e-05, + "loss": 3.6031, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437542380154655e-05, + "loss": 3.5916, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436705423283976e-05, + "loss": 3.5917, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435866828532924e-05, + "loss": 3.5854, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435028233781872e-05, + "loss": 3.5843, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.43418963903082e-05, + "loss": 3.5948, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433352682160142e-05, + "loss": 3.5883, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.43251408740909e-05, + "loss": 3.587, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431675492658038e-05, + "loss": 3.5935, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430836897906986e-05, + "loss": 3.5898, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4299999410363066e-05, + "loss": 3.569, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291613462852546e-05, + "loss": 3.5889, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4283227515342026e-05, + "loss": 3.5902, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274841567831506e-05, + "loss": 3.5802, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266471999124715e-05, + "loss": 3.5863, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4258086051614195e-05, + "loss": 3.5859, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249700104103675e-05, + "loss": 3.5806, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4241314156593155e-05, + "loss": 3.5801, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423294458788637e-05, + "loss": 3.5849, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422455864037585e-05, + "loss": 3.5919, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421617269286533e-05, + "loss": 3.593, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420778674535481e-05, + "loss": 3.5961, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419941717664802e-05, + "loss": 3.5802, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.41910312291375e-05, + "loss": 3.5808, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418264528162698e-05, + "loss": 3.5836, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417425933411646e-05, + "loss": 3.5935, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416588976540967e-05, + "loss": 3.5895, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415750381789915e-05, + "loss": 3.5882, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414911787038863e-05, + "loss": 3.5855, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414073192287811e-05, + "loss": 3.5841, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132362354171324e-05, + "loss": 3.5927, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123976406660804e-05, + "loss": 3.5842, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115590459150284e-05, + "loss": 3.5836, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410722089044349e-05, + "loss": 3.5864, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409883494293297e-05, + "loss": 3.5804, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409044899542245e-05, + "loss": 3.5835, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408206304791193e-05, + "loss": 3.5822, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407369347920514e-05, + "loss": 3.5759, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406530753169462e-05, + "loss": 3.5888, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.40569215841841e-05, + "loss": 3.5912, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404853563667358e-05, + "loss": 3.5796, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404016606796679e-05, + "loss": 3.5933, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403178012045628e-05, + "loss": 3.6015, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402339417294576e-05, + "loss": 3.5814, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401500822543524e-05, + "loss": 3.5848, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400663865672845e-05, + "loss": 3.5818, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399825270921793e-05, + "loss": 3.5864, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398986676170741e-05, + "loss": 3.5817, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398148081419689e-05, + "loss": 3.5823, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3973111245490096e-05, + "loss": 3.5805, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3964725297979576e-05, + "loss": 3.5895, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3956339350469056e-05, + "loss": 3.5824, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947953402958536e-05, + "loss": 3.5874, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939583834251745e-05, + "loss": 3.5861, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393119788674123e-05, + "loss": 3.5844, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392281193923071e-05, + "loss": 3.5796, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391442599172019e-05, + "loss": 3.5932, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.39060564230134e-05, + "loss": 3.5924, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389767047550288e-05, + "loss": 3.5839, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388928452799236e-05, + "loss": 3.5806, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388089858048184e-05, + "loss": 3.5909, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387252901177505e-05, + "loss": 3.5782, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386414306426453e-05, + "loss": 3.59, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385575711675401e-05, + "loss": 3.5861, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384737116924349e-05, + "loss": 3.598, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.38390016005367e-05, + "loss": 3.5917, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830615653026185e-05, + "loss": 3.5939, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3822229705515665e-05, + "loss": 3.5813, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3813843758005145e-05, + "loss": 3.5931, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805474189298354e-05, + "loss": 3.5841, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3797088241787834e-05, + "loss": 3.5794, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788702294277314e-05, + "loss": 3.5871, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780316346766794e-05, + "loss": 3.5765, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377194677806e-05, + "loss": 3.5875, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376356083054948e-05, + "loss": 3.5764, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8459322452545166, + "eval_runtime": 302.7544, + "eval_samples_per_second": 1260.398, + "eval_steps_per_second": 39.388, + "step": 992152 + }, + { + "epoch": 1.0, + "learning_rate": 3.375517488303896e-05, + "loss": 3.5877, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374678893552844e-05, + "loss": 3.5752, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373841936682165e-05, + "loss": 3.5829, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.373003341931114e-05, + "loss": 3.5954, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372164747180062e-05, + "loss": 3.5846, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.37132615242901e-05, + "loss": 3.5935, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370489195558331e-05, + "loss": 3.5845, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369650600807279e-05, + "loss": 3.5808, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368812006056227e-05, + "loss": 3.5718, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367973411305175e-05, + "loss": 3.5816, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367136454434496e-05, + "loss": 3.5857, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366297859683444e-05, + "loss": 3.5792, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365459264932392e-05, + "loss": 3.59, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.36462067018134e-05, + "loss": 3.5633, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637837133106606e-05, + "loss": 3.5739, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362945118559609e-05, + "loss": 3.5682, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362106523808557e-05, + "loss": 3.5794, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361267929057505e-05, + "loss": 3.5727, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360430972186826e-05, + "loss": 3.5781, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359592377435774e-05, + "loss": 3.5835, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358753782684722e-05, + "loss": 3.5864, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.35791518793367e-05, + "loss": 3.5883, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357078231062991e-05, + "loss": 3.5773, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356239636311939e-05, + "loss": 3.5774, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355401041560887e-05, + "loss": 3.5931, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354562446809835e-05, + "loss": 3.5801, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353725489939156e-05, + "loss": 3.5735, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352886895188104e-05, + "loss": 3.5803, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3520483004370526e-05, + "loss": 3.57, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3512097056860006e-05, + "loss": 3.5752, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3503727488153215e-05, + "loss": 3.5842, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3495341540642695e-05, + "loss": 3.579, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486955593132175e-05, + "loss": 3.5834, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3478569645621655e-05, + "loss": 3.5912, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3470200076914864e-05, + "loss": 3.5755, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461814129404344e-05, + "loss": 3.5828, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453428181893824e-05, + "loss": 3.5872, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344505861318703e-05, + "loss": 3.5668, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343667266567651e-05, + "loss": 3.5761, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342828671816599e-05, + "loss": 3.5612, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341990077065548e-05, + "loss": 3.5703, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341153120194869e-05, + "loss": 3.5693, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340314525443817e-05, + "loss": 3.5905, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339475930692765e-05, + "loss": 3.5703, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338637335941713e-05, + "loss": 3.5745, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337800379071034e-05, + "loss": 3.5744, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336961784319982e-05, + "loss": 3.5763, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.33612318956893e-05, + "loss": 3.5677, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335284594817878e-05, + "loss": 3.5552, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334447637947199e-05, + "loss": 3.5778, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333609043196147e-05, + "loss": 3.5884, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332770448445095e-05, + "loss": 3.58, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3319318536940434e-05, + "loss": 3.5716, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331094896823364e-05, + "loss": 3.5709, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330256302072312e-05, + "loss": 3.5725, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.32941770732126e-05, + "loss": 3.5586, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328579112570208e-05, + "loss": 3.5902, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327742155699529e-05, + "loss": 3.5613, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326903560948477e-05, + "loss": 3.5927, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326064966197425e-05, + "loss": 3.5785, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325226371446373e-05, + "loss": 3.5614, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324389414575694e-05, + "loss": 3.5773, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323550819824642e-05, + "loss": 3.572, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.32271222507359e-05, + "loss": 3.5599, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321873630322538e-05, + "loss": 3.5668, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3210366734518596e-05, + "loss": 3.585, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3201980787008076e-05, + "loss": 3.5694, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193594839497556e-05, + "loss": 3.5697, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318520889198703e-05, + "loss": 3.552, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176839323280245e-05, + "loss": 3.5687, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3168453375769725e-05, + "loss": 3.5695, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3160067428259205e-05, + "loss": 3.5717, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315168148074868e-05, + "loss": 3.5664, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3143311912041894e-05, + "loss": 3.575, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3134925964531374e-05, + "loss": 3.5836, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126540017020854e-05, + "loss": 3.5714, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3118154069510334e-05, + "loss": 3.5746, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310978450080355e-05, + "loss": 3.5732, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310139855329303e-05, + "loss": 3.5669, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.30930126057825e-05, + "loss": 3.575, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308462665827198e-05, + "loss": 3.568, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.30762570895652e-05, + "loss": 3.571, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306787114205468e-05, + "loss": 3.5777, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305948519454415e-05, + "loss": 3.5696, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305109924703363e-05, + "loss": 3.5507, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304272967832685e-05, + "loss": 3.5724, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303434373081633e-05, + "loss": 3.569, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302595778330581e-05, + "loss": 3.568, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301757183579529e-05, + "loss": 3.5678, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3009202267088504e-05, + "loss": 3.5724, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300081631957798e-05, + "loss": 3.5597, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299243037206746e-05, + "loss": 3.563, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298404442455694e-05, + "loss": 3.566, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297567485585015e-05, + "loss": 3.5777, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2967288908339626e-05, + "loss": 3.575, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2958902960829106e-05, + "loss": 3.5772, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2950517013318586e-05, + "loss": 3.5598, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.29421474446118e-05, + "loss": 3.568, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293376149710128e-05, + "loss": 3.566, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292537554959076e-05, + "loss": 3.576, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291698960208024e-05, + "loss": 3.5703, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290862003337345e-05, + "loss": 3.5724, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290023408586293e-05, + "loss": 3.569, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289184813835241e-05, + "loss": 3.5642, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288346219084189e-05, + "loss": 3.5771, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.28750926221351e-05, + "loss": 3.5637, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286670667462458e-05, + "loss": 3.5673, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285832072711406e-05, + "loss": 3.5691, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284995115840727e-05, + "loss": 3.5652, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2841565210896755e-05, + "loss": 3.5641, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2833179263386235e-05, + "loss": 3.5678, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824793315875715e-05, + "loss": 3.5573, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2816423747168924e-05, + "loss": 3.5703, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2808037799658404e-05, + "loss": 3.5754, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799651852147884e-05, + "loss": 3.5626, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2791265904637364e-05, + "loss": 3.578, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278289633593057e-05, + "loss": 3.5847, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277451038842005e-05, + "loss": 3.5657, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276612444090953e-05, + "loss": 3.5681, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275773849339901e-05, + "loss": 3.5654, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274936892469222e-05, + "loss": 3.5664, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274098297718171e-05, + "loss": 3.5636, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273259702967119e-05, + "loss": 3.5655, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272421108216067e-05, + "loss": 3.566, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271584151345388e-05, + "loss": 3.5726, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270745556594336e-05, + "loss": 3.5666, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269906961843284e-05, + "loss": 3.5674, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269068367092232e-05, + "loss": 3.5673, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268231410221553e-05, + "loss": 3.5673, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267392815470501e-05, + "loss": 3.5615, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266554220719449e-05, + "loss": 3.5778, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265715625968397e-05, + "loss": 3.5784, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2648786690977176e-05, + "loss": 3.57, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264040074346666e-05, + "loss": 3.562, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263201479595614e-05, + "loss": 3.5727, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262362884844562e-05, + "loss": 3.5651, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261525927973883e-05, + "loss": 3.5714, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260687333222831e-05, + "loss": 3.5701, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259848738471779e-05, + "loss": 3.5833, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.259010143720727e-05, + "loss": 3.5713, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258173186850048e-05, + "loss": 3.5747, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257334592098996e-05, + "loss": 3.5672, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256495997347944e-05, + "loss": 3.5782, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255657402596892e-05, + "loss": 3.5634, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254820445726213e-05, + "loss": 3.5615, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539818509751616e-05, + "loss": 3.5736, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531432562241096e-05, + "loss": 3.5577, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2523046614730576e-05, + "loss": 3.5715, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514677046023785e-05, + "loss": 3.5579, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8475773334503174, + "eval_runtime": 302.8034, + "eval_samples_per_second": 1260.194, + "eval_steps_per_second": 39.382, + "step": 1068472 + }, + { + "epoch": 0.0, + "learning_rate": 3.2506291098513265e-05, + "loss": 3.5756, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497905151002745e-05, + "loss": 3.5625, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489519203492225e-05, + "loss": 3.5623, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2481133255981705e-05, + "loss": 3.5797, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472763687274914e-05, + "loss": 3.5675, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2464377739764394e-05, + "loss": 3.5797, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2455991792253874e-05, + "loss": 3.565, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2447605844743354e-05, + "loss": 3.5622, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243923627603656e-05, + "loss": 3.5581, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243085032852605e-05, + "loss": 3.5663, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242246438101553e-05, + "loss": 3.5629, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241407843350501e-05, + "loss": 3.5646, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240570886479822e-05, + "loss": 3.5718, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.23973229172877e-05, + "loss": 3.549, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238893696977718e-05, + "loss": 3.5557, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238055102226666e-05, + "loss": 3.5536, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237218145355987e-05, + "loss": 3.5593, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236379550604935e-05, + "loss": 3.5607, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235540955853883e-05, + "loss": 3.5623, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234702361102831e-05, + "loss": 3.5645, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233865404232152e-05, + "loss": 3.5719, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330268094811004e-05, + "loss": 3.5668, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321882147300483e-05, + "loss": 3.5672, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313496199789963e-05, + "loss": 3.5581, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230512663108317e-05, + "loss": 3.5763, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229674068357265e-05, + "loss": 3.5633, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228835473606213e-05, + "loss": 3.5624, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227996878855161e-05, + "loss": 3.5615, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227159921984482e-05, + "loss": 3.5551, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.22632132723343e-05, + "loss": 3.5594, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225482732482378e-05, + "loss": 3.563, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224644137731326e-05, + "loss": 3.5654, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223807180860647e-05, + "loss": 3.5666, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222968586109596e-05, + "loss": 3.5719, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222129991358544e-05, + "loss": 3.5603, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221291396607492e-05, + "loss": 3.5667, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.2204544397368126e-05, + "loss": 3.5694, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2196158449857606e-05, + "loss": 3.5518, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187772502347086e-05, + "loss": 3.5596, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2179386554836566e-05, + "loss": 3.5445, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2171016986129775e-05, + "loss": 3.5575, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162631038619255e-05, + "loss": 3.5524, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2154245091108735e-05, + "loss": 3.5725, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145859143598215e-05, + "loss": 3.5539, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2137489574891424e-05, + "loss": 3.5574, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212910362738091e-05, + "loss": 3.5612, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212071767987039e-05, + "loss": 3.5581, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211233173235987e-05, + "loss": 3.5565, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210396216365308e-05, + "loss": 3.5369, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209557621614256e-05, + "loss": 3.5594, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208719026863204e-05, + "loss": 3.5697, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207880432112152e-05, + "loss": 3.5639, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207043475241473e-05, + "loss": 3.5574, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206204880490421e-05, + "loss": 3.5523, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205366285739369e-05, + "loss": 3.5593, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204527690988317e-05, + "loss": 3.545, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203690734117638e-05, + "loss": 3.5723, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028521393665865e-05, + "loss": 3.5441, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2020135446155344e-05, + "loss": 3.5766, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011749498644824e-05, + "loss": 3.5631, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2003379929938034e-05, + "loss": 3.5429, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994993982427513e-05, + "loss": 3.5602, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986608034916993e-05, + "loss": 3.5603, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197822208740647e-05, + "loss": 3.5451, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196985251869968e-05, + "loss": 3.5503, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196146657118916e-05, + "loss": 3.5661, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195308062367864e-05, + "loss": 3.556, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194471105497185e-05, + "loss": 3.5543, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193632510746133e-05, + "loss": 3.538, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192793915995082e-05, + "loss": 3.5538, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.19195532124403e-05, + "loss": 3.5497, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191118364373351e-05, + "loss": 3.5614, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190279769622299e-05, + "loss": 3.5486, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189441174871247e-05, + "loss": 3.5596, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188602580120195e-05, + "loss": 3.563, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1877656232495156e-05, + "loss": 3.5584, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1869270284984636e-05, + "loss": 3.5572, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860884337474116e-05, + "loss": 3.5559, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185249838996359e-05, + "loss": 3.5544, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1844128821256805e-05, + "loss": 3.5609, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835742873746285e-05, + "loss": 3.5542, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182735692623577e-05, + "loss": 3.5547, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818970978725245e-05, + "loss": 3.5574, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181060141001846e-05, + "loss": 3.5548, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180221546250794e-05, + "loss": 3.5365, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179382951499742e-05, + "loss": 3.5538, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785443567486894e-05, + "loss": 3.5503, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177707399878011e-05, + "loss": 3.554, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176868805126959e-05, + "loss": 3.5522, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176030210375906e-05, + "loss": 3.5565, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175191615624854e-05, + "loss": 3.5473, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174354658754176e-05, + "loss": 3.5434, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173516064003124e-05, + "loss": 3.5498, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172677469252072e-05, + "loss": 3.5645, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.17183887450102e-05, + "loss": 3.5548, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1710019176303415e-05, + "loss": 3.5631, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1701633228792895e-05, + "loss": 3.5465, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169324728128237e-05, + "loss": 3.5501, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168486133377185e-05, + "loss": 3.5473, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676491765065064e-05, + "loss": 3.5643, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166810581755454e-05, + "loss": 3.5519, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165971987004402e-05, + "loss": 3.5599, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.16513339225335e-05, + "loss": 3.5488, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164296435382671e-05, + "loss": 3.5495, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163457840631619e-05, + "loss": 3.5637, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162619245880567e-05, + "loss": 3.5455, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161780651129515e-05, + "loss": 3.5493, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160943694258837e-05, + "loss": 3.5532, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160105099507784e-05, + "loss": 3.5504, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159266504756732e-05, + "loss": 3.5516, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.15842791000568e-05, + "loss": 3.5542, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157590953135001e-05, + "loss": 3.5403, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156752358383949e-05, + "loss": 3.5567, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155913763632897e-05, + "loss": 3.5559, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155075168881845e-05, + "loss": 3.55, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1542382120111666e-05, + "loss": 3.5609, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1533996172601146e-05, + "loss": 3.5667, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525610225090626e-05, + "loss": 3.5533, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1517224277580106e-05, + "loss": 3.5519, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508854708873315e-05, + "loss": 3.5473, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500468761362795e-05, + "loss": 3.5552, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1492082813852275e-05, + "loss": 3.5433, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483696866341755e-05, + "loss": 3.5528, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1475327297634964e-05, + "loss": 3.5461, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466941350124444e-05, + "loss": 3.5591, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458555402613924e-05, + "loss": 3.5491, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1450169455103404e-05, + "loss": 3.5515, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144179988639662e-05, + "loss": 3.5526, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.14334139388861e-05, + "loss": 3.5524, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142502799137558e-05, + "loss": 3.5443, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141664204386506e-05, + "loss": 3.5609, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140827247515827e-05, + "loss": 3.564, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139988652764775e-05, + "loss": 3.5574, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139150058013723e-05, + "loss": 3.5444, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138311463262671e-05, + "loss": 3.5524, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137474506391992e-05, + "loss": 3.5527, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.13663591164094e-05, + "loss": 3.5567, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135797316889888e-05, + "loss": 3.5539, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134958722138836e-05, + "loss": 3.5667, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1341217652681573e-05, + "loss": 3.5549, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332831705171053e-05, + "loss": 3.5624, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324445757660533e-05, + "loss": 3.5513, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131605981015001e-05, + "loss": 3.559, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130769024144322e-05, + "loss": 3.5472, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.12993042939327e-05, + "loss": 3.5474, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129091834642218e-05, + "loss": 3.5578, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128253239891166e-05, + "loss": 3.5405, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127416283020487e-05, + "loss": 3.5563, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126577688269435e-05, + "loss": 3.5454, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8476827144622803, + "eval_runtime": 305.5713, + "eval_samples_per_second": 1248.779, + "eval_steps_per_second": 39.025, + "step": 1144792 + }, + { + "epoch": 0.0, + "learning_rate": 3.125739093518383e-05, + "loss": 3.5418, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124900498767331e-05, + "loss": 3.5499, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.124061904016279e-05, + "loss": 3.5493, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123223309265227e-05, + "loss": 3.5597, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122386352394549e-05, + "loss": 3.5564, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121547757643497e-05, + "loss": 3.5625, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120709162892445e-05, + "loss": 3.5507, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119870568141393e-05, + "loss": 3.5489, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.1190336112707136e-05, + "loss": 3.5363, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.1181950165196616e-05, + "loss": 3.5531, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.1173564217686096e-05, + "loss": 3.5499, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.1165178270175576e-05, + "loss": 3.5485, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.1156808701468785e-05, + "loss": 3.5545, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.1148422753958265e-05, + "loss": 3.5384, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.1140036806447745e-05, + "loss": 3.541, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.1131650858937225e-05, + "loss": 3.5393, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112328129023044e-05, + "loss": 3.5387, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111489534271992e-05, + "loss": 3.5441, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.11065093952094e-05, + "loss": 3.5495, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109812344769888e-05, + "loss": 3.543, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108975387899209e-05, + "loss": 3.5622, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108136793148157e-05, + "loss": 3.5511, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107298198397105e-05, + "loss": 3.5477, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106459603646053e-05, + "loss": 3.5466, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105622646775374e-05, + "loss": 3.5603, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104784052024322e-05, + "loss": 3.5439, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.10394545727327e-05, + "loss": 3.5508, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.103106862522218e-05, + "loss": 3.5397, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.1022699056515394e-05, + "loss": 3.5462, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.1014329487808604e-05, + "loss": 3.5442, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.1005943540298083e-05, + "loss": 3.5445, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.0997557592787563e-05, + "loss": 3.5509, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098917164527704e-05, + "loss": 3.5526, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098078569776652e-05, + "loss": 3.5539, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0972399750256e-05, + "loss": 3.5484, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096401380274548e-05, + "loss": 3.5523, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095562785523496e-05, + "loss": 3.5511, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094725828652817e-05, + "loss": 3.5387, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093887233901765e-05, + "loss": 3.5445, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.093048639150713e-05, + "loss": 3.529, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092210044399662e-05, + "loss": 3.5425, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091373087528983e-05, + "loss": 3.5334, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090534492777931e-05, + "loss": 3.556, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089695898026879e-05, + "loss": 3.5427, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088857303275827e-05, + "loss": 3.5374, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.088020346405148e-05, + "loss": 3.546, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087181751654096e-05, + "loss": 3.5468, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086343156903044e-05, + "loss": 3.5406, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085504562151991e-05, + "loss": 3.5218, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.0846676052813126e-05, + "loss": 3.5429, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.0838290105302606e-05, + "loss": 3.5556, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.0829904157792086e-05, + "loss": 3.5492, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.0821518210281566e-05, + "loss": 3.5435, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081314864157478e-05, + "loss": 3.5339, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080476269406426e-05, + "loss": 3.5446, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079637674655374e-05, + "loss": 3.5296, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0787990799043215e-05, + "loss": 3.5548, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077962123033643e-05, + "loss": 3.5278, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077123528282591e-05, + "loss": 3.5598, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.0762849335315384e-05, + "loss": 3.5473, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0754463387804864e-05, + "loss": 3.5311, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074609381909808e-05, + "loss": 3.5441, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073770787158756e-05, + "loss": 3.5479, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072932192407704e-05, + "loss": 3.5249, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072093597656652e-05, + "loss": 3.534, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.0712566407859735e-05, + "loss": 3.554, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.0704180460349215e-05, + "loss": 3.541, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069579451283869e-05, + "loss": 3.5384, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068740856532817e-05, + "loss": 3.526, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.0679038996621384e-05, + "loss": 3.5392, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067065304911086e-05, + "loss": 3.5299, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066226710160034e-05, + "loss": 3.547, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065388115408982e-05, + "loss": 3.5317, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064551158538303e-05, + "loss": 3.5452, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063712563787251e-05, + "loss": 3.5454, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062873969036199e-05, + "loss": 3.5464, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.062035374285147e-05, + "loss": 3.54, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061198417414469e-05, + "loss": 3.5414, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060359822663416e-05, + "loss": 3.5419, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059521227912364e-05, + "loss": 3.5434, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058684271041686e-05, + "loss": 3.5409, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057845676290633e-05, + "loss": 3.5372, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.057007081539581e-05, + "loss": 3.5411, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056168486788529e-05, + "loss": 3.5419, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055331529917851e-05, + "loss": 3.5222, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054492935166798e-05, + "loss": 3.5377, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053654340415747e-05, + "loss": 3.539, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052815745664695e-05, + "loss": 3.5407, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051978788794016e-05, + "loss": 3.5385, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511401940429636e-05, + "loss": 3.5386, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0503015992919116e-05, + "loss": 3.5351, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494630045408596e-05, + "loss": 3.5287, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0486260476701805e-05, + "loss": 3.5332, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477874529191285e-05, + "loss": 3.5458, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469488581680765e-05, + "loss": 3.5414, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0461102634170248e-05, + "loss": 3.5473, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452733065463457e-05, + "loss": 3.5348, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0444347117952937e-05, + "loss": 3.5376, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435961170442417e-05, + "loss": 3.5336, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427575222931897e-05, + "loss": 3.5475, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.041920565422511e-05, + "loss": 3.5372, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.041081970671459e-05, + "loss": 3.5452, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.040243375920407e-05, + "loss": 3.5327, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.039404781169355e-05, + "loss": 3.5316, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.038567824298676e-05, + "loss": 3.5531, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037729229547624e-05, + "loss": 3.5294, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036890634796572e-05, + "loss": 3.532, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360520400455202e-05, + "loss": 3.5392, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.035215083174841e-05, + "loss": 3.5394, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.034376488423789e-05, + "loss": 3.5298, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.033537893672737e-05, + "loss": 3.5401, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.032699298921685e-05, + "loss": 3.5274, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318623420510063e-05, + "loss": 3.5393, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0310237472999543e-05, + "loss": 3.539, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0301851525489023e-05, + "loss": 3.5377, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0293465577978503e-05, + "loss": 3.5419, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0285096009271712e-05, + "loss": 3.5553, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276710061761192e-05, + "loss": 3.5379, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0268324114250672e-05, + "loss": 3.5362, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259938166740152e-05, + "loss": 3.5358, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251568598033365e-05, + "loss": 3.5348, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0243182650522845e-05, + "loss": 3.5345, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234796703012325e-05, + "loss": 3.5369, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0226410755501804e-05, + "loss": 3.5331, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0218041186795017e-05, + "loss": 3.5421, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209655239284497e-05, + "loss": 3.5361, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0201269291773977e-05, + "loss": 3.5392, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192883344263457e-05, + "loss": 3.5349, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184513775556666e-05, + "loss": 3.5336, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0176127828046146e-05, + "loss": 3.5301, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167741880535626e-05, + "loss": 3.5453, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0159355933025106e-05, + "loss": 3.5513, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150986364318318e-05, + "loss": 3.545, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142600416807798e-05, + "loss": 3.5272, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0134214469297278e-05, + "loss": 3.5366, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125828521786758e-05, + "loss": 3.5423, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0117458953079967e-05, + "loss": 3.5405, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.010907300556945e-05, + "loss": 3.5387, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.010068705805893e-05, + "loss": 3.5507, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.009230111054841e-05, + "loss": 3.5386, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.008393154184162e-05, + "loss": 3.5504, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.00755455943311e-05, + "loss": 3.5349, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.006715964682058e-05, + "loss": 3.5454, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058790078113792e-05, + "loss": 3.5365, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0050404130603272e-05, + "loss": 3.5299, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0042018183092752e-05, + "loss": 3.545, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033632235582232e-05, + "loss": 3.5298, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.002526266687544e-05, + "loss": 3.5387, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.001687671936492e-05, + "loss": 3.5313, + "step": 1220608 + }, + { + "epoch": 0.03, + "eval_loss": 3.8497231006622314, + "eval_runtime": 301.7491, + "eval_samples_per_second": 1264.597, + "eval_steps_per_second": 39.52, + "step": 1221112 + }, + { + "epoch": 1.0, + "learning_rate": 3.0008490771854404e-05, + "loss": 3.5339, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 3.0000104824343884e-05, + "loss": 3.5344, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991735255637093e-05, + "loss": 3.533, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9983349308126573e-05, + "loss": 3.5453, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974963360616053e-05, + "loss": 3.5422, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966577413105533e-05, + "loss": 3.5499, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9958207844398746e-05, + "loss": 3.5346, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949821896888226e-05, + "loss": 3.5324, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9941435949377706e-05, + "loss": 3.5268, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9933050001867186e-05, + "loss": 3.5381, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9924680433160395e-05, + "loss": 3.534, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9916294485649875e-05, + "loss": 3.5352, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9907908538139358e-05, + "loss": 3.5355, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899522590628838e-05, + "loss": 3.5242, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9891153021922047e-05, + "loss": 3.5291, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882767074411527e-05, + "loss": 3.5269, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9874381126901007e-05, + "loss": 3.5191, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9865995179390487e-05, + "loss": 3.5354, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.98576256106837e-05, + "loss": 3.5319, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984923966317318e-05, + "loss": 3.5311, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.984085371566266e-05, + "loss": 3.5502, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.983246776815214e-05, + "loss": 3.5312, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9824098199445348e-05, + "loss": 3.539, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815712251934828e-05, + "loss": 3.5303, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.980732630442431e-05, + "loss": 3.544, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.979894035691379e-05, + "loss": 3.5311, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790570788207e-05, + "loss": 3.5346, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.978218484069648e-05, + "loss": 3.5257, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.977379889318596e-05, + "loss": 3.5363, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.976541294567544e-05, + "loss": 3.5268, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9757043376968653e-05, + "loss": 3.5318, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748657429458133e-05, + "loss": 3.5386, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9740271481947613e-05, + "loss": 3.5336, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731885534437093e-05, + "loss": 3.5386, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723515965730302e-05, + "loss": 3.5345, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9715130018219782e-05, + "loss": 3.5305, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706744070709265e-05, + "loss": 3.5428, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698358123198745e-05, + "loss": 3.5207, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689988554491954e-05, + "loss": 3.5306, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681602606981434e-05, + "loss": 3.5172, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9673216659470914e-05, + "loss": 3.5243, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664830711960394e-05, + "loss": 3.5201, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9656461143253607e-05, + "loss": 3.5398, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9648075195743087e-05, + "loss": 3.5301, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639689248232567e-05, + "loss": 3.5221, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9631303300722047e-05, + "loss": 3.5315, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.9622933732015256e-05, + "loss": 3.529, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.9614547784504736e-05, + "loss": 3.5259, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960616183699422e-05, + "loss": 3.5128, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.95977758894837e-05, + "loss": 3.5242, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9589406320776908e-05, + "loss": 3.54, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9581020373266388e-05, + "loss": 3.5369, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572634425755868e-05, + "loss": 3.524, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9564248478245348e-05, + "loss": 3.523, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.955587890953856e-05, + "loss": 3.5339, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.954749296202804e-05, + "loss": 3.516, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.953910701451752e-05, + "loss": 3.5352, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530721067007e-05, + "loss": 3.5164, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.952235149830021e-05, + "loss": 3.5432, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.951396555078969e-05, + "loss": 3.5361, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505579603279173e-05, + "loss": 3.5199, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9497193655768653e-05, + "loss": 3.5259, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.948882408706186e-05, + "loss": 3.5361, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.948043813955134e-05, + "loss": 3.5108, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.947205219204082e-05, + "loss": 3.5178, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.94636662445303e-05, + "loss": 3.5394, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9455296675823514e-05, + "loss": 3.5275, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446910728312994e-05, + "loss": 3.5229, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438524780802474e-05, + "loss": 3.5131, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9430138833291954e-05, + "loss": 3.5209, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421769264585163e-05, + "loss": 3.5167, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9413399695878375e-05, + "loss": 3.5363, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9405013748367855e-05, + "loss": 3.5175, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396627800857335e-05, + "loss": 3.533, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9388241853346815e-05, + "loss": 3.529, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379855905836295e-05, + "loss": 3.5345, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9371469958325775e-05, + "loss": 3.5229, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9363084010815252e-05, + "loss": 3.5284, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354698063304732e-05, + "loss": 3.5273, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9346328494597948e-05, + "loss": 3.5281, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337942547087428e-05, + "loss": 3.5275, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.93295565995769e-05, + "loss": 3.5218, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.932117065206638e-05, + "loss": 3.5266, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312801083359597e-05, + "loss": 3.5282, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9304415135849073e-05, + "loss": 3.5134, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9296029188338553e-05, + "loss": 3.5186, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287643240828033e-05, + "loss": 3.5262, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.927927367212125e-05, + "loss": 3.5277, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270887724610725e-05, + "loss": 3.5208, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262501777100205e-05, + "loss": 3.5271, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9254115829589685e-05, + "loss": 3.5183, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.92457462608829e-05, + "loss": 3.5135, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9237360313372374e-05, + "loss": 3.5193, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9228974365861854e-05, + "loss": 3.5286, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220588418351334e-05, + "loss": 3.529, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9212218849644547e-05, + "loss": 3.5319, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203832902134027e-05, + "loss": 3.527, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195446954623507e-05, + "loss": 3.5154, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9187061007112987e-05, + "loss": 3.5216, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178691438406196e-05, + "loss": 3.5288, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9170305490895676e-05, + "loss": 3.5267, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916191954338516e-05, + "loss": 3.53, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915353359587464e-05, + "loss": 3.5193, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9145164027167848e-05, + "loss": 3.5164, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9136778079657328e-05, + "loss": 3.5402, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9128392132146808e-05, + "loss": 3.5152, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9120006184636288e-05, + "loss": 3.5211, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.91116366159295e-05, + "loss": 3.524, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.910325066841898e-05, + "loss": 3.5276, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.909486472090846e-05, + "loss": 3.5153, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.908647877339794e-05, + "loss": 3.5196, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.907810920469115e-05, + "loss": 3.5182, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.906972325718063e-05, + "loss": 3.5254, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9061337309670113e-05, + "loss": 3.5241, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052951362159593e-05, + "loss": 3.5223, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044581793452802e-05, + "loss": 3.5302, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9036195845942282e-05, + "loss": 3.5387, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027809898431762e-05, + "loss": 3.5275, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9019423950921242e-05, + "loss": 3.5223, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9011054382214454e-05, + "loss": 3.5185, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002668434703934e-05, + "loss": 3.5176, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8994282487193414e-05, + "loss": 3.522, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985896539682894e-05, + "loss": 3.5232, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977526970976103e-05, + "loss": 3.5188, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8969141023465583e-05, + "loss": 3.524, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960755075955066e-05, + "loss": 3.524, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8952369128444546e-05, + "loss": 3.5239, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943999559737756e-05, + "loss": 3.5231, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935613612227235e-05, + "loss": 3.5202, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8927227664716715e-05, + "loss": 3.5192, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8918841717206195e-05, + "loss": 3.5312, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8910472148499408e-05, + "loss": 3.5336, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8902086200988888e-05, + "loss": 3.534, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893700253478368e-05, + "loss": 3.5107, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8885330684771577e-05, + "loss": 3.5242, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876944737261057e-05, + "loss": 3.5239, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8868558789750537e-05, + "loss": 3.5289, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.886017284224002e-05, + "loss": 3.5186, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885180327353323e-05, + "loss": 3.5346, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.884341732602271e-05, + "loss": 3.5249, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.883503137851219e-05, + "loss": 3.5394, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.882664543100167e-05, + "loss": 3.5196, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.881827586229488e-05, + "loss": 3.5333, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.880988991478436e-05, + "loss": 3.5224, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.880150396727384e-05, + "loss": 3.5173, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.879311801976332e-05, + "loss": 3.5302, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.878474845105653e-05, + "loss": 3.5153, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.877636250354601e-05, + "loss": 3.5224, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.876797655603549e-05, + "loss": 3.5198, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759590608524974e-05, + "loss": 3.521, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8510491847991943, + "eval_runtime": 304.3121, + "eval_samples_per_second": 1253.946, + "eval_steps_per_second": 39.187, + "step": 1297432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8751204661014454e-05, + "loss": 3.5195, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742818713503934e-05, + "loss": 3.5216, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734432765993414e-05, + "loss": 3.5301, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8726046818482894e-05, + "loss": 3.5248, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717677249776103e-05, + "loss": 3.5394, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8709291302265583e-05, + "loss": 3.5179, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700905354755066e-05, + "loss": 3.5199, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692535786048275e-05, + "loss": 3.5128, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8684149838537755e-05, + "loss": 3.5247, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675763891027235e-05, + "loss": 3.5213, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8667377943516715e-05, + "loss": 3.5191, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8659008374809927e-05, + "loss": 3.5245, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650622427299407e-05, + "loss": 3.5067, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8642236479788887e-05, + "loss": 3.5185, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633850532278367e-05, + "loss": 3.5132, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8625480963571576e-05, + "loss": 3.5096, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8617095016061056e-05, + "loss": 3.5147, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608709068550536e-05, + "loss": 3.5165, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.860032312104002e-05, + "loss": 3.5179, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859195355233323e-05, + "loss": 3.5385, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.858356760482271e-05, + "loss": 3.5172, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.857518165731219e-05, + "loss": 3.52, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.856679570980167e-05, + "loss": 3.5194, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.855842614109488e-05, + "loss": 3.5266, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.855004019358436e-05, + "loss": 3.5201, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.854165424607384e-05, + "loss": 3.5244, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.853326829856332e-05, + "loss": 3.5116, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.852489872985653e-05, + "loss": 3.5219, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.851651278234601e-05, + "loss": 3.5087, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8508143213639223e-05, + "loss": 3.5203, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499757266128702e-05, + "loss": 3.5232, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491371318618182e-05, + "loss": 3.5201, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482985371107662e-05, + "loss": 3.5255, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474599423597142e-05, + "loss": 3.521, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8466213476086622e-05, + "loss": 3.5188, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.84578275285761e-05, + "loss": 3.5234, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449457959869315e-05, + "loss": 3.5136, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8441072012358795e-05, + "loss": 3.5134, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432686064848275e-05, + "loss": 3.5022, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424300117337748e-05, + "loss": 3.5098, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415930548630964e-05, + "loss": 3.5097, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407544601120444e-05, + "loss": 3.525, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8399158653609924e-05, + "loss": 3.5166, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.83907727060994e-05, + "loss": 3.51, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382403137392616e-05, + "loss": 3.5201, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8374017189882096e-05, + "loss": 3.5149, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.836563124237157e-05, + "loss": 3.513, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8357245294861053e-05, + "loss": 3.4999, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834887572615427e-05, + "loss": 3.5084, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.834048977864375e-05, + "loss": 3.5273, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.833210383113322e-05, + "loss": 3.5234, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.83237178836227e-05, + "loss": 3.5085, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8315348314915917e-05, + "loss": 3.5159, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306962367405394e-05, + "loss": 3.5187, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298576419894874e-05, + "loss": 3.5001, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8290190472384354e-05, + "loss": 3.5236, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.828182090367757e-05, + "loss": 3.5045, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273434956167043e-05, + "loss": 3.5269, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8265049008656523e-05, + "loss": 3.5215, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256663061146006e-05, + "loss": 3.5099, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8248293492439222e-05, + "loss": 3.5094, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239907544928695e-05, + "loss": 3.5231, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231521597418175e-05, + "loss": 3.494, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8223135649907655e-05, + "loss": 3.5071, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214766081200868e-05, + "loss": 3.5265, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206380133690348e-05, + "loss": 3.5159, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197994186179828e-05, + "loss": 3.5121, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189608238669308e-05, + "loss": 3.4965, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8181238669962517e-05, + "loss": 3.5096, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172852722451997e-05, + "loss": 3.505, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8164466774941477e-05, + "loss": 3.5153, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815608082743096e-05, + "loss": 3.5073, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.814771125872417e-05, + "loss": 3.5196, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.813932531121365e-05, + "loss": 3.5163, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.813093936370313e-05, + "loss": 3.5221, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.812255341619261e-05, + "loss": 3.5079, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811418384748582e-05, + "loss": 3.515, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.81057978999753e-05, + "loss": 3.5124, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809741195246478e-05, + "loss": 3.5147, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808902600495426e-05, + "loss": 3.5163, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.808065643624747e-05, + "loss": 3.507, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807227048873695e-05, + "loss": 3.5157, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806388454122643e-05, + "loss": 3.5113, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055498593715914e-05, + "loss": 3.4989, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8047129025009123e-05, + "loss": 3.5034, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038743077498603e-05, + "loss": 3.511, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8030357129988083e-05, + "loss": 3.5148, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021971182477563e-05, + "loss": 3.5084, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013601613770775e-05, + "loss": 3.5106, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8005215666260255e-05, + "loss": 3.5049, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996829718749735e-05, + "loss": 3.5018, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988460150042944e-05, + "loss": 3.5051, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7980074202532424e-05, + "loss": 3.5131, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971688255021904e-05, + "loss": 3.516, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7963302307511384e-05, + "loss": 3.5191, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954932738804596e-05, + "loss": 3.516, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946546791294076e-05, + "loss": 3.5028, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7938160843783556e-05, + "loss": 3.5096, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929774896273036e-05, + "loss": 3.5104, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7921405327566245e-05, + "loss": 3.5174, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791301938005573e-05, + "loss": 3.5159, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790463343254521e-05, + "loss": 3.5089, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789624748503469e-05, + "loss": 3.5038, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887877916327898e-05, + "loss": 3.5268, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7879491968817378e-05, + "loss": 3.4992, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7871106021306858e-05, + "loss": 3.5102, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862720073796338e-05, + "loss": 3.5097, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785435050508955e-05, + "loss": 3.5134, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784596455757903e-05, + "loss": 3.4999, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783757861006851e-05, + "loss": 3.5129, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.782919266255799e-05, + "loss": 3.5011, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.78208230938512e-05, + "loss": 3.5113, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7812437146340682e-05, + "loss": 3.5115, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7804051198830162e-05, + "loss": 3.5051, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795665251319642e-05, + "loss": 3.52, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.778729568261285e-05, + "loss": 3.5247, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777890973510233e-05, + "loss": 3.5147, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.777052378759181e-05, + "loss": 3.5085, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.776213784008129e-05, + "loss": 3.5065, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753768271374504e-05, + "loss": 3.5074, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745382323863984e-05, + "loss": 3.5055, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736996376353464e-05, + "loss": 3.5165, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728610428842944e-05, + "loss": 3.5043, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7720240860136153e-05, + "loss": 3.5092, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711854912625636e-05, + "loss": 3.5121, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703468965115116e-05, + "loss": 3.5143, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7695083017604596e-05, + "loss": 3.5041, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686713448897805e-05, + "loss": 3.507, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7678327501387285e-05, + "loss": 3.5118, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669941553876765e-05, + "loss": 3.5097, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7661555606366245e-05, + "loss": 3.5196, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7653186037659457e-05, + "loss": 3.5223, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644800090148937e-05, + "loss": 3.5004, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7636414142638417e-05, + "loss": 3.5122, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7628028195127897e-05, + "loss": 3.5106, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619658626421106e-05, + "loss": 3.5108, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761127267891059e-05, + "loss": 3.5099, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760288673140007e-05, + "loss": 3.5187, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759450078388955e-05, + "loss": 3.511, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758613121518276e-05, + "loss": 3.5272, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757774526767224e-05, + "loss": 3.509, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756935932016172e-05, + "loss": 3.5182, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.75609733726512e-05, + "loss": 3.5113, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.755260380394441e-05, + "loss": 3.5043, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.754421785643389e-05, + "loss": 3.5161, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.753583190892337e-05, + "loss": 3.5066, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.752744596141285e-05, + "loss": 3.5076, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.751907639270606e-05, + "loss": 3.5054, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.751069044519554e-05, + "loss": 3.5044, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.852248430252075, + "eval_runtime": 308.6151, + "eval_samples_per_second": 1236.462, + "eval_steps_per_second": 38.64, + "step": 1373752 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502304497685023e-05, + "loss": 3.5088, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493918550174503e-05, + "loss": 3.5063, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485548981467712e-05, + "loss": 3.5183, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7477163033957192e-05, + "loss": 3.5095, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468777086446672e-05, + "loss": 3.5281, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7460391138936152e-05, + "loss": 3.5052, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7452021570229365e-05, + "loss": 3.5084, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443635622718845e-05, + "loss": 3.4975, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7435249675208325e-05, + "loss": 3.5116, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.7426863727697805e-05, + "loss": 3.5072, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7418494158991014e-05, + "loss": 3.5017, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7410108211480494e-05, + "loss": 3.5175, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401722263969977e-05, + "loss": 3.4912, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7393336316459457e-05, + "loss": 3.5102, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384966747752666e-05, + "loss": 3.4936, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376580800242146e-05, + "loss": 3.5001, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7368194852731626e-05, + "loss": 3.4981, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359808905221106e-05, + "loss": 3.5065, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.735143933651432e-05, + "loss": 3.5016, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.73430533890038e-05, + "loss": 3.525, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334667441493278e-05, + "loss": 3.506, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7326281493982758e-05, + "loss": 3.5081, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317911925275967e-05, + "loss": 3.5057, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309525977765447e-05, + "loss": 3.5144, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.730114003025493e-05, + "loss": 3.5059, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.729275408274441e-05, + "loss": 3.5156, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.728438451403762e-05, + "loss": 3.4974, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.72759985665271e-05, + "loss": 3.5062, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.726761261901658e-05, + "loss": 3.4959, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.725922667150606e-05, + "loss": 3.51, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250857102799272e-05, + "loss": 3.5095, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242471155288752e-05, + "loss": 3.5075, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7234085207778232e-05, + "loss": 3.5164, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225699260267712e-05, + "loss": 3.5067, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.721732969156092e-05, + "loss": 3.506, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.72089437440504e-05, + "loss": 3.51, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200557796539884e-05, + "loss": 3.5028, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7192188227833093e-05, + "loss": 3.4981, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7183802280322573e-05, + "loss": 3.492, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7175416332812053e-05, + "loss": 3.4952, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7167030385301533e-05, + "loss": 3.4956, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158660816594746e-05, + "loss": 3.5107, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7150274869084226e-05, + "loss": 3.5076, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141888921573706e-05, + "loss": 3.4947, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7133502974063186e-05, + "loss": 3.51, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7125133405356395e-05, + "loss": 3.5007, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116747457845875e-05, + "loss": 3.496, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7108361510335355e-05, + "loss": 3.4923, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7099975562824838e-05, + "loss": 3.4893, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7091605994118047e-05, + "loss": 3.5164, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7083220046607527e-05, + "loss": 3.5112, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074834099097007e-05, + "loss": 3.4984, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7066448151586487e-05, + "loss": 3.5008, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.70580785828797e-05, + "loss": 3.5073, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.704969263536918e-05, + "loss": 3.4858, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.704130668785866e-05, + "loss": 3.5088, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.703292074034814e-05, + "loss": 3.4902, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.702455117164135e-05, + "loss": 3.5135, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701616522413083e-05, + "loss": 3.5115, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007779276620308e-05, + "loss": 3.4985, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6999393329109785e-05, + "loss": 3.4953, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6991023760403e-05, + "loss": 3.5109, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.698263781289248e-05, + "loss": 3.4837, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.697425186538196e-05, + "loss": 3.4981, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965865917871437e-05, + "loss": 3.5087, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6957496349164653e-05, + "loss": 3.5048, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6949110401654133e-05, + "loss": 3.4971, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940724454143606e-05, + "loss": 3.4862, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6932338506633086e-05, + "loss": 3.4918, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6923968937926302e-05, + "loss": 3.4936, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915582990415782e-05, + "loss": 3.5043, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.690719704290526e-05, + "loss": 3.4913, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.689881109539474e-05, + "loss": 3.5086, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6890441526687954e-05, + "loss": 3.5044, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6882055579177434e-05, + "loss": 3.509, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873669631666908e-05, + "loss": 3.4923, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686528368415639e-05, + "loss": 3.5017, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856914115449607e-05, + "loss": 3.5024, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.684852816793908e-05, + "loss": 3.4984, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.684014222042856e-05, + "loss": 3.5051, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.683175627291804e-05, + "loss": 3.4976, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6823386704211256e-05, + "loss": 3.4996, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6815000756700732e-05, + "loss": 3.4995, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806614809190212e-05, + "loss": 3.4855, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6798228861679692e-05, + "loss": 3.497, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789859292972908e-05, + "loss": 3.4964, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.678147334546238e-05, + "loss": 3.5048, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.677308739795186e-05, + "loss": 3.4948, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764701450441345e-05, + "loss": 3.5, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6756331881734554e-05, + "loss": 3.4928, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747945934224034e-05, + "loss": 3.4879, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739559986713514e-05, + "loss": 3.4885, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6731174039202993e-05, + "loss": 3.497, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722804470496206e-05, + "loss": 3.5079, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6714418522985686e-05, + "loss": 3.5061, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6706032575475166e-05, + "loss": 3.5006, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697646627964646e-05, + "loss": 3.4926, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6689277059257855e-05, + "loss": 3.4959, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680891111747335e-05, + "loss": 3.4976, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6672505164236815e-05, + "loss": 3.5054, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6664119216726298e-05, + "loss": 3.5025, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6655749648019507e-05, + "loss": 3.4961, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6647363700508987e-05, + "loss": 3.4882, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638977752998467e-05, + "loss": 3.5129, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630591805487947e-05, + "loss": 3.4877, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.662222223678116e-05, + "loss": 3.4983, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.661383628927064e-05, + "loss": 3.4938, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.660545034176012e-05, + "loss": 3.4977, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.65970643942496e-05, + "loss": 3.4905, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.658869482554281e-05, + "loss": 3.5004, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.658030887803229e-05, + "loss": 3.4878, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.657192293052177e-05, + "loss": 3.495, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.656353698301125e-05, + "loss": 3.5041, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.655516741430446e-05, + "loss": 3.4885, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.654678146679394e-05, + "loss": 3.5104, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.653839551928342e-05, + "loss": 3.5098, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.653002595057663e-05, + "loss": 3.5026, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521640003066113e-05, + "loss": 3.492, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6513254055555593e-05, + "loss": 3.4951, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504868108045073e-05, + "loss": 3.4946, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6496498539338282e-05, + "loss": 3.4904, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6488112591827762e-05, + "loss": 3.5025, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479726644317242e-05, + "loss": 3.4909, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6471340696806722e-05, + "loss": 3.4974, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462971128099935e-05, + "loss": 3.5018, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454585180589415e-05, + "loss": 3.4984, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6446199233078895e-05, + "loss": 3.4911, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6437813285568375e-05, + "loss": 3.4955, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6429443716861584e-05, + "loss": 3.5004, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6421057769351064e-05, + "loss": 3.4972, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412671821840547e-05, + "loss": 3.5047, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6404285874330027e-05, + "loss": 3.5087, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395916305623236e-05, + "loss": 3.4853, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387530358112716e-05, + "loss": 3.4982, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6379144410602196e-05, + "loss": 3.5003, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370758463091676e-05, + "loss": 3.4964, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636238889438489e-05, + "loss": 3.4966, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6354002946874368e-05, + "loss": 3.5075, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6345616999363848e-05, + "loss": 3.5006, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6337231051853328e-05, + "loss": 3.5139, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328861483146537e-05, + "loss": 3.4965, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6320475535636017e-05, + "loss": 3.5008, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.63120895881255e-05, + "loss": 3.4991, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.630370364061498e-05, + "loss": 3.4945, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629533407190819e-05, + "loss": 3.4983, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.628694812439767e-05, + "loss": 3.4969, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627856217688715e-05, + "loss": 3.4923, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.627017622937663e-05, + "loss": 3.4933, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6261806660669842e-05, + "loss": 3.4925, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.853142738342285, + "eval_runtime": 308.5781, + "eval_samples_per_second": 1236.611, + "eval_steps_per_second": 38.645, + "step": 1450072 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253420713159322e-05, + "loss": 3.4944, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6245034765648802e-05, + "loss": 3.494, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236648818138282e-05, + "loss": 3.5079, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6228262870627762e-05, + "loss": 3.4958, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.621989330192097e-05, + "loss": 3.5183, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211507354410454e-05, + "loss": 3.4921, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6203121406899934e-05, + "loss": 3.4966, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194735459389414e-05, + "loss": 3.4845, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6186365890682623e-05, + "loss": 3.4978, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177979943172103e-05, + "loss": 3.4966, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169593995661583e-05, + "loss": 3.4883, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6161224426954796e-05, + "loss": 3.5012, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152838479444276e-05, + "loss": 3.4816, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144452531933756e-05, + "loss": 3.495, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6136066584423236e-05, + "loss": 3.4869, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127697015716445e-05, + "loss": 3.485, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6119311068205925e-05, + "loss": 3.4853, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110925120695408e-05, + "loss": 3.4917, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102539173184888e-05, + "loss": 3.4906, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6094169604478097e-05, + "loss": 3.5102, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085783656967577e-05, + "loss": 3.4919, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6077397709457057e-05, + "loss": 3.5002, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6069011761946537e-05, + "loss": 3.4914, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.606064219323975e-05, + "loss": 3.4997, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.605225624572923e-05, + "loss": 3.4907, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.604387029821871e-05, + "loss": 3.5019, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603548435070819e-05, + "loss": 3.4909, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6027114782001398e-05, + "loss": 3.4887, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018728834490878e-05, + "loss": 3.4841, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.601034288698036e-05, + "loss": 3.4948, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.600195693946984e-05, + "loss": 3.5012, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599358737076305e-05, + "loss": 3.4933, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598520142325253e-05, + "loss": 3.5038, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597681547574201e-05, + "loss": 3.4954, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596842952823149e-05, + "loss": 3.4899, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5960059959524703e-05, + "loss": 3.4977, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951674012014183e-05, + "loss": 3.4936, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5943288064503663e-05, + "loss": 3.4837, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934902116993143e-05, + "loss": 3.4799, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926532548286352e-05, + "loss": 3.4816, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5918146600775832e-05, + "loss": 3.4905, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909760653265315e-05, + "loss": 3.4949, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5901374705754795e-05, + "loss": 3.4949, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5893005137048004e-05, + "loss": 3.4801, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884619189537484e-05, + "loss": 3.499, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5876233242026964e-05, + "loss": 3.4876, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867847294516444e-05, + "loss": 3.4855, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859477725809657e-05, + "loss": 3.477, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5851091778299137e-05, + "loss": 3.4748, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842705830788617e-05, + "loss": 3.5063, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5834319883278097e-05, + "loss": 3.4984, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825950314571306e-05, + "loss": 3.4848, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817564367060786e-05, + "loss": 3.4894, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580917841955027e-05, + "loss": 3.4897, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.580079247203975e-05, + "loss": 3.474, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5792422903332958e-05, + "loss": 3.4948, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5784036955822438e-05, + "loss": 3.4825, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775651008311918e-05, + "loss": 3.4945, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5767265060801398e-05, + "loss": 3.503, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.575889549209461e-05, + "loss": 3.4854, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.575050954458409e-05, + "loss": 3.4798, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.574212359707357e-05, + "loss": 3.5022, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.573373764956305e-05, + "loss": 3.4711, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.572536808085626e-05, + "loss": 3.4802, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.571698213334574e-05, + "loss": 3.4985, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570859618583522e-05, + "loss": 3.4934, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5700210238324703e-05, + "loss": 3.4867, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.569184066961791e-05, + "loss": 3.478, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568345472210739e-05, + "loss": 3.476, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567506877459687e-05, + "loss": 3.4794, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666682827086348e-05, + "loss": 3.4956, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5658313258379564e-05, + "loss": 3.4754, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649927310869044e-05, + "loss": 3.4953, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641541363358524e-05, + "loss": 3.4896, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5633155415847997e-05, + "loss": 3.4985, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624785847141213e-05, + "loss": 3.4842, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5616399899630693e-05, + "loss": 3.4854, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5608013952120173e-05, + "loss": 3.4897, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559962800460965e-05, + "loss": 3.4861, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5591258435902865e-05, + "loss": 3.4951, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582872488392345e-05, + "loss": 3.4839, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574486540881822e-05, + "loss": 3.4842, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5566100593371302e-05, + "loss": 3.4893, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557731024664518e-05, + "loss": 3.4706, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5549345077153998e-05, + "loss": 3.4833, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.554095912964347e-05, + "loss": 3.4861, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.553257318213295e-05, + "loss": 3.4913, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5524203613426167e-05, + "loss": 3.4797, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515817665915647e-05, + "loss": 3.4866, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507431718405123e-05, + "loss": 3.4792, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.549906214969834e-05, + "loss": 3.4785, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.549067620218782e-05, + "loss": 3.4772, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5482290254677292e-05, + "loss": 3.483, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473904307166772e-05, + "loss": 3.5003, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465534738459988e-05, + "loss": 3.4957, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.545714879094947e-05, + "loss": 3.4867, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448762843438945e-05, + "loss": 3.4772, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5440376895928424e-05, + "loss": 3.4833, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.543200732722164e-05, + "loss": 3.4884, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542362137971112e-05, + "loss": 3.4856, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5415235432200597e-05, + "loss": 3.4911, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406849484690077e-05, + "loss": 3.4871, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5398479915983293e-05, + "loss": 3.4778, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5390093968472766e-05, + "loss": 3.5041, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381708020962246e-05, + "loss": 3.4759, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5373322073451726e-05, + "loss": 3.4877, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536495250474494e-05, + "loss": 3.4786, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5356566557234418e-05, + "loss": 3.4888, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5348180609723898e-05, + "loss": 3.4768, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339794662213378e-05, + "loss": 3.4874, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5331425093506594e-05, + "loss": 3.4826, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.532303914599607e-05, + "loss": 3.4802, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.531465319848555e-05, + "loss": 3.4872, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.530626725097503e-05, + "loss": 3.4798, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.529789768226824e-05, + "loss": 3.493, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.528951173475772e-05, + "loss": 3.5001, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.52811257872472e-05, + "loss": 3.4913, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.527273983973668e-05, + "loss": 3.48, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5264370271029892e-05, + "loss": 3.4858, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255984323519372e-05, + "loss": 3.4799, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247598376008852e-05, + "loss": 3.4801, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5239212428498332e-05, + "loss": 3.4908, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.523084285979154e-05, + "loss": 3.4742, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5222456912281024e-05, + "loss": 3.4887, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5214070964770504e-05, + "loss": 3.4847, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205685017259984e-05, + "loss": 3.4894, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5197315448553193e-05, + "loss": 3.4814, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188929501042673e-05, + "loss": 3.485, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180543553532153e-05, + "loss": 3.4851, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5172157606021633e-05, + "loss": 3.4887, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163788037314846e-05, + "loss": 3.4892, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5155402089804326e-05, + "loss": 3.4986, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5147016142293806e-05, + "loss": 3.4746, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138630194783285e-05, + "loss": 3.4891, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5130260626076495e-05, + "loss": 3.4884, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121874678565978e-05, + "loss": 3.4829, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5113488731055458e-05, + "loss": 3.4829, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5105102783544938e-05, + "loss": 3.4982, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096733214838147e-05, + "loss": 3.4861, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5088347267327627e-05, + "loss": 3.5041, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079961319817107e-05, + "loss": 3.4817, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071575372306587e-05, + "loss": 3.4906, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.50632058035998e-05, + "loss": 3.4849, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.505481985608928e-05, + "loss": 3.4861, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.504643390857876e-05, + "loss": 3.4822, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.503804796106824e-05, + "loss": 3.485, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029678392361448e-05, + "loss": 3.482, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.502129244485093e-05, + "loss": 3.4758, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.501290649734041e-05, + "loss": 3.4831, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8550570011138916, + "eval_runtime": 304.5981, + "eval_samples_per_second": 1252.769, + "eval_steps_per_second": 39.15, + "step": 1526392 + }, + { + "epoch": 1.0, + "learning_rate": 2.500452054982989e-05, + "loss": 3.4846, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.49961509811231e-05, + "loss": 3.4799, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.498776503361258e-05, + "loss": 3.4924, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.497937908610206e-05, + "loss": 3.4859, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.497099313859154e-05, + "loss": 3.5032, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4962623569884753e-05, + "loss": 3.4839, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4954237622374233e-05, + "loss": 3.4841, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4945851674863713e-05, + "loss": 3.4716, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4937465727353193e-05, + "loss": 3.4834, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4929096158646402e-05, + "loss": 3.4829, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4920710211135885e-05, + "loss": 3.479, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4912324263625365e-05, + "loss": 3.4861, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4903938316114845e-05, + "loss": 3.4716, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4895568747408054e-05, + "loss": 3.4834, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4887182799897534e-05, + "loss": 3.4742, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4878796852387014e-05, + "loss": 3.4732, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4870410904876494e-05, + "loss": 3.4725, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4862041336169707e-05, + "loss": 3.4818, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4853655388659187e-05, + "loss": 3.4771, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4845269441148667e-05, + "loss": 3.4973, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836899872441876e-05, + "loss": 3.48, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4828513924931356e-05, + "loss": 3.4897, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.482012797742084e-05, + "loss": 3.4806, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.481174202991032e-05, + "loss": 3.4849, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4803372461203528e-05, + "loss": 3.4786, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794986513693008e-05, + "loss": 3.4927, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786600566182488e-05, + "loss": 3.4748, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4778214618671968e-05, + "loss": 3.4813, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.476984504996518e-05, + "loss": 3.4726, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.476145910245466e-05, + "loss": 3.4809, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.475307315494414e-05, + "loss": 3.489, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.474468720743362e-05, + "loss": 3.4822, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.473631763872683e-05, + "loss": 3.4912, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.472793169121631e-05, + "loss": 3.4807, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719545743705793e-05, + "loss": 3.479, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4711159796195273e-05, + "loss": 3.4858, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470279022748848e-05, + "loss": 3.4829, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.469440427997796e-05, + "loss": 3.4685, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.468601833246744e-05, + "loss": 3.4737, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.467763238495692e-05, + "loss": 3.4683, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4669262816250134e-05, + "loss": 3.4768, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4660876868739614e-05, + "loss": 3.4821, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.4652490921229094e-05, + "loss": 3.481, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.4644104973718574e-05, + "loss": 3.4718, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.4635735405011783e-05, + "loss": 3.4815, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4627349457501263e-05, + "loss": 3.4749, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4618963509990743e-05, + "loss": 3.4748, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4610577562480226e-05, + "loss": 3.4689, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4602207993773435e-05, + "loss": 3.4578, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4593822046262915e-05, + "loss": 3.4967, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4585436098752395e-05, + "loss": 3.4838, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4577050151241875e-05, + "loss": 3.4799, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.4568680582535088e-05, + "loss": 3.4787, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4560294635024568e-05, + "loss": 3.4765, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551908687514048e-05, + "loss": 3.4645, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4543522740003528e-05, + "loss": 3.4781, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4535153171296737e-05, + "loss": 3.4727, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4526767223786217e-05, + "loss": 3.4825, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4518381276275697e-05, + "loss": 3.4921, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4509995328765176e-05, + "loss": 3.4718, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.450162576005839e-05, + "loss": 3.469, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.449323981254787e-05, + "loss": 3.4902, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.448485386503735e-05, + "loss": 3.4623, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4476467917526825e-05, + "loss": 3.4691, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.446809834882004e-05, + "loss": 3.4851, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.445971240130952e-05, + "loss": 3.4795, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4451326453799e-05, + "loss": 3.4736, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442940506288478e-05, + "loss": 3.4667, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.443457093758169e-05, + "loss": 3.4591, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.442618499007117e-05, + "loss": 3.4694, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.441779904256065e-05, + "loss": 3.4819, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.440941309505013e-05, + "loss": 3.4677, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4401043526343343e-05, + "loss": 3.4785, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4392657578832823e-05, + "loss": 3.4813, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.43842716313223e-05, + "loss": 3.4905, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.437588568381178e-05, + "loss": 3.4721, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367516115104995e-05, + "loss": 3.472, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.435913016759447e-05, + "loss": 3.4794, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.435074422008395e-05, + "loss": 3.4705, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.434235827257343e-05, + "loss": 3.4869, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333988703866644e-05, + "loss": 3.4712, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4325602756356124e-05, + "loss": 3.4735, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4317216808845604e-05, + "loss": 3.4784, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4308830861335084e-05, + "loss": 3.4617, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4300461292628296e-05, + "loss": 3.4696, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4292075345117773e-05, + "loss": 3.4723, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4283689397607253e-05, + "loss": 3.4794, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4275303450096733e-05, + "loss": 3.4665, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4266933881389945e-05, + "loss": 3.4762, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4258547933879425e-05, + "loss": 3.4653, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4250161986368905e-05, + "loss": 3.4712, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4241776038858385e-05, + "loss": 3.4621, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4233406470151594e-05, + "loss": 3.4751, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4225020522641078e-05, + "loss": 3.4847, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4216634575130558e-05, + "loss": 3.482, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4208248627620037e-05, + "loss": 3.4783, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4199879058913247e-05, + "loss": 3.4666, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4191493111402727e-05, + "loss": 3.4724, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4183107163892206e-05, + "loss": 3.4724, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.4174721216381686e-05, + "loss": 3.4791, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.41663516476749e-05, + "loss": 3.4786, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.415796570016438e-05, + "loss": 3.474, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.414957975265386e-05, + "loss": 3.4666, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.414119380514334e-05, + "loss": 3.4886, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132824236436548e-05, + "loss": 3.464, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4124438288926028e-05, + "loss": 3.478, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411605234141551e-05, + "loss": 3.4671, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.410768277270872e-05, + "loss": 3.476, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.40992968251982e-05, + "loss": 3.4624, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.409091087768768e-05, + "loss": 3.4791, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.408252493017716e-05, + "loss": 3.4674, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4074155361470373e-05, + "loss": 3.4709, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4065769413959853e-05, + "loss": 3.4767, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4057383466449333e-05, + "loss": 3.4717, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4048997518938813e-05, + "loss": 3.4803, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.404062795023202e-05, + "loss": 3.488, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.40322420027215e-05, + "loss": 3.4781, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.402385605521098e-05, + "loss": 3.4691, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4015470107700465e-05, + "loss": 3.4738, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4007100538993674e-05, + "loss": 3.4705, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3998714591483154e-05, + "loss": 3.4674, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3990328643972634e-05, + "loss": 3.4802, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3981942696462114e-05, + "loss": 3.4575, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3973573127755326e-05, + "loss": 3.4762, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3965187180244806e-05, + "loss": 3.4717, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3956801232734286e-05, + "loss": 3.4762, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3948415285223766e-05, + "loss": 3.4702, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3940045716516975e-05, + "loss": 3.4744, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3931659769006455e-05, + "loss": 3.4697, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3923273821495935e-05, + "loss": 3.4797, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.391488787398542e-05, + "loss": 3.4775, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3906518305278628e-05, + "loss": 3.4861, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3898132357768108e-05, + "loss": 3.4631, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3889746410257588e-05, + "loss": 3.4775, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3881360462747067e-05, + "loss": 3.4773, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.387299089404028e-05, + "loss": 3.4706, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386460494652976e-05, + "loss": 3.471, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385621899901924e-05, + "loss": 3.481, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384783305150872e-05, + "loss": 3.4756, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.383946348280193e-05, + "loss": 3.4941, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.383107753529141e-05, + "loss": 3.4693, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.382269158778089e-05, + "loss": 3.4785, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3814305640270372e-05, + "loss": 3.4712, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.380593607156358e-05, + "loss": 3.4735, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.379755012405306e-05, + "loss": 3.4779, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.378916417654254e-05, + "loss": 3.4721, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780778229032018e-05, + "loss": 3.4713, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3772408660325234e-05, + "loss": 3.4596, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3764022712814714e-05, + "loss": 3.4716, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.8569018840789795, + "eval_runtime": 303.7697, + "eval_samples_per_second": 1256.185, + "eval_steps_per_second": 39.257, + "step": 1602712 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755636765304194e-05, + "loss": 3.4729, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374725081779367e-05, + "loss": 3.4701, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373886487028315e-05, + "loss": 3.4803, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.373047892277263e-05, + "loss": 3.4771, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3722109354065843e-05, + "loss": 3.4875, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713723406555322e-05, + "loss": 3.472, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3705337459044802e-05, + "loss": 3.472, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696951511534282e-05, + "loss": 3.463, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368858194282749e-05, + "loss": 3.4694, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.368019599531697e-05, + "loss": 3.4714, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.367181004780645e-05, + "loss": 3.4731, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663424100295935e-05, + "loss": 3.4668, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3655054531589144e-05, + "loss": 3.4649, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646668584078624e-05, + "loss": 3.4686, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3638282636568104e-05, + "loss": 3.4652, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629896689057584e-05, + "loss": 3.4584, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621527120350796e-05, + "loss": 3.4626, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3613141172840276e-05, + "loss": 3.4712, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604755225329756e-05, + "loss": 3.4633, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596369277819236e-05, + "loss": 3.4858, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587999709112445e-05, + "loss": 3.4718, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579613761601925e-05, + "loss": 3.4776, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3571227814091405e-05, + "loss": 3.4663, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356284186658089e-05, + "loss": 3.4732, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554472297874098e-05, + "loss": 3.4663, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3546086350363577e-05, + "loss": 3.4809, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537700402853057e-05, + "loss": 3.4652, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3529314455342537e-05, + "loss": 3.4664, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.352094488663575e-05, + "loss": 3.4622, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351255893912523e-05, + "loss": 3.471, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350417299161471e-05, + "loss": 3.4743, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.349578704410419e-05, + "loss": 3.4737, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.34874174753974e-05, + "loss": 3.4764, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.347903152788688e-05, + "loss": 3.4723, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.347064558037636e-05, + "loss": 3.4667, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3462259632865842e-05, + "loss": 3.4763, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345389006415905e-05, + "loss": 3.4733, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.344550411664853e-05, + "loss": 3.458, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343711816913801e-05, + "loss": 3.4624, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.342873222162749e-05, + "loss": 3.4562, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420362652920704e-05, + "loss": 3.4604, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411976705410183e-05, + "loss": 3.4733, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403590757899663e-05, + "loss": 3.4697, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3395204810389143e-05, + "loss": 3.462, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386835241682352e-05, + "loss": 3.47, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378449294171832e-05, + "loss": 3.4637, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3370063346661312e-05, + "loss": 3.4655, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361677399150796e-05, + "loss": 3.4553, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3353307830444005e-05, + "loss": 3.4438, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344921882933485e-05, + "loss": 3.4858, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3336535935422965e-05, + "loss": 3.4723, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.332814998791244e-05, + "loss": 3.4712, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319780419205657e-05, + "loss": 3.4612, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3311394471695137e-05, + "loss": 3.4693, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3303008524184617e-05, + "loss": 3.4525, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294622576674094e-05, + "loss": 3.4649, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3286253007967306e-05, + "loss": 3.4646, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277867060456786e-05, + "loss": 3.466, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269481112946266e-05, + "loss": 3.4824, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.326111154423948e-05, + "loss": 3.4625, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.325272559672896e-05, + "loss": 3.4587, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.324433964921844e-05, + "loss": 3.4807, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235953701707915e-05, + "loss": 3.4501, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3227584133001128e-05, + "loss": 3.4558, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321919818549061e-05, + "loss": 3.4719, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321081223798009e-05, + "loss": 3.4722, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3202426290469567e-05, + "loss": 3.4583, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319405672176278e-05, + "loss": 3.4615, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318567077425226e-05, + "loss": 3.4472, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317728482674174e-05, + "loss": 3.4594, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316889887923122e-05, + "loss": 3.4701, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3160529310524432e-05, + "loss": 3.4568, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3152143363013912e-05, + "loss": 3.468, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314375741550339e-05, + "loss": 3.4675, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.313537146799287e-05, + "loss": 3.4791, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.312700189928608e-05, + "loss": 3.4605, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118615951775565e-05, + "loss": 3.4632, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.311023000426504e-05, + "loss": 3.4662, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.310184405675452e-05, + "loss": 3.4591, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3093474488047734e-05, + "loss": 3.4707, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3085088540537213e-05, + "loss": 3.4633, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.307670259302669e-05, + "loss": 3.4641, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3068316645516173e-05, + "loss": 3.4687, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059947076809386e-05, + "loss": 3.4524, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051561129298862e-05, + "loss": 3.4544, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3043175181788342e-05, + "loss": 3.4633, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034789234277822e-05, + "loss": 3.467, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3026419665571035e-05, + "loss": 3.4564, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3018033718060515e-05, + "loss": 3.4677, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009647770549995e-05, + "loss": 3.453, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3001261823039475e-05, + "loss": 3.4601, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992892254332684e-05, + "loss": 3.4509, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984506306822164e-05, + "loss": 3.464, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2976120359311644e-05, + "loss": 3.4722, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967734411801127e-05, + "loss": 3.4685, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2959364843094336e-05, + "loss": 3.4673, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950978895583816e-05, + "loss": 3.4543, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942592948073296e-05, + "loss": 3.4625, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2934207000562776e-05, + "loss": 3.4593, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292583743185599e-05, + "loss": 3.469, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291745148434547e-05, + "loss": 3.4611, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.290906553683495e-05, + "loss": 3.4666, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.290067958932443e-05, + "loss": 3.4586, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2892310020617637e-05, + "loss": 3.4745, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288394045191085e-05, + "loss": 3.453, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875554504400333e-05, + "loss": 3.4656, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286716855688981e-05, + "loss": 3.4518, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285878260937929e-05, + "loss": 3.4686, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.285039666186877e-05, + "loss": 3.4535, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.284201071435825e-05, + "loss": 3.4644, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.283362476684773e-05, + "loss": 3.4542, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282523881933721e-05, + "loss": 3.4605, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816869250630422e-05, + "loss": 3.4631, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2808483303119902e-05, + "loss": 3.4598, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2800097355609382e-05, + "loss": 3.4651, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2791711408098862e-05, + "loss": 3.4771, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278334183939207e-05, + "loss": 3.4662, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277495589188155e-05, + "loss": 3.466, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766569944371034e-05, + "loss": 3.4579, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2758183996860514e-05, + "loss": 3.4565, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749814428153723e-05, + "loss": 3.4617, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2741428480643203e-05, + "loss": 3.4659, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2733042533132683e-05, + "loss": 3.4494, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724656585622163e-05, + "loss": 3.4627, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2716287016915376e-05, + "loss": 3.4647, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707901069404856e-05, + "loss": 3.4622, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699515121894336e-05, + "loss": 3.4613, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2691129174383812e-05, + "loss": 3.4621, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682759605677025e-05, + "loss": 3.46, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2674373658166505e-05, + "loss": 3.4651, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665987710655988e-05, + "loss": 3.4674, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657601763145465e-05, + "loss": 3.4769, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2649232194438677e-05, + "loss": 3.4504, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640846246928157e-05, + "loss": 3.4649, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632460299417637e-05, + "loss": 3.4683, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2624074351907114e-05, + "loss": 3.4572, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261570478320033e-05, + "loss": 3.4642, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260731883568981e-05, + "loss": 3.4695, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598932888179286e-05, + "loss": 3.4634, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590546940668766e-05, + "loss": 3.4816, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.258217737196198e-05, + "loss": 3.4611, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257379142445146e-05, + "loss": 3.4656, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256540547694094e-05, + "loss": 3.4576, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2557019529430418e-05, + "loss": 3.4665, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.254864996072363e-05, + "loss": 3.458, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.254026401321311e-05, + "loss": 3.4637, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531878065702587e-05, + "loss": 3.4615, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523492118192067e-05, + "loss": 3.4454, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2515122549485283e-05, + "loss": 3.4625, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.857164144515991, + "eval_runtime": 304.0172, + "eval_samples_per_second": 1255.163, + "eval_steps_per_second": 39.225, + "step": 1679032 + }, + { + "epoch": 1.0, + "learning_rate": 2.250673660197476e-05, + "loss": 3.4676, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.249835065446424e-05, + "loss": 3.4589, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.248996470695372e-05, + "loss": 3.4657, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481595138246932e-05, + "loss": 3.4641, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2473209190736412e-05, + "loss": 3.4783, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464823243225892e-05, + "loss": 3.4602, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2456437295715372e-05, + "loss": 3.4628, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2448067727008584e-05, + "loss": 3.45, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243968177949806e-05, + "loss": 3.4575, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.243129583198754e-05, + "loss": 3.461, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.242290988447702e-05, + "loss": 3.4592, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2414540315770233e-05, + "loss": 3.4589, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2406154368259713e-05, + "loss": 3.4532, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397768420749193e-05, + "loss": 3.456, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2389382473238673e-05, + "loss": 3.4568, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2381012904531882e-05, + "loss": 3.447, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2372626957021366e-05, + "loss": 3.4509, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2364241009510846e-05, + "loss": 3.4558, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355855062000326e-05, + "loss": 3.4553, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2347485493293535e-05, + "loss": 3.472, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2339099545783015e-05, + "loss": 3.4638, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330713598272495e-05, + "loss": 3.4706, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2322327650761975e-05, + "loss": 3.4536, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313958082055187e-05, + "loss": 3.4617, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305572134544667e-05, + "loss": 3.457, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2297186187034147e-05, + "loss": 3.4686, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288800239523627e-05, + "loss": 3.454, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2280430670816836e-05, + "loss": 3.4572, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.227204472330632e-05, + "loss": 3.4545, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.22636587757958e-05, + "loss": 3.4555, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.225527282828528e-05, + "loss": 3.4606, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.224690325957849e-05, + "loss": 3.4662, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.223851731206797e-05, + "loss": 3.4638, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.223013136455745e-05, + "loss": 3.4649, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221745417046928e-05, + "loss": 3.4591, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221337584834014e-05, + "loss": 3.4612, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220498990082962e-05, + "loss": 3.461, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.21966039533191e-05, + "loss": 3.4509, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.218821800580858e-05, + "loss": 3.4502, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.217984843710179e-05, + "loss": 3.4425, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171462489591273e-05, + "loss": 3.4525, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2163076542080753e-05, + "loss": 3.4596, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2154690594570233e-05, + "loss": 3.4588, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2146321025863442e-05, + "loss": 3.4506, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2137935078352922e-05, + "loss": 3.458, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2129549130842402e-05, + "loss": 3.4541, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2121163183331882e-05, + "loss": 3.4537, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112793614625094e-05, + "loss": 3.4449, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2104407667114574e-05, + "loss": 3.4306, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2096021719604054e-05, + "loss": 3.4733, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2087652150897263e-05, + "loss": 3.457, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2079266203386743e-05, + "loss": 3.4645, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070880255876227e-05, + "loss": 3.4527, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2062494308365707e-05, + "loss": 3.4529, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2054124739658916e-05, + "loss": 3.444, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045738792148396e-05, + "loss": 3.452, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2037352844637876e-05, + "loss": 3.4578, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028966897127356e-05, + "loss": 3.4517, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2020597328420568e-05, + "loss": 3.4735, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2012211380910048e-05, + "loss": 3.4501, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003825433399528e-05, + "loss": 3.4488, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1995439485889008e-05, + "loss": 3.4693, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1987069917182217e-05, + "loss": 3.4383, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1978683969671697e-05, + "loss": 3.4419, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.197029802216118e-05, + "loss": 3.4666, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961912074650657e-05, + "loss": 3.4596, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.195354250594387e-05, + "loss": 3.4441, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.194515655843335e-05, + "loss": 3.4518, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193677061092283e-05, + "loss": 3.4342, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928384663412306e-05, + "loss": 3.4523, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1920015094705522e-05, + "loss": 3.4558, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911629147195002e-05, + "loss": 3.4448, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1903243199684482e-05, + "loss": 3.4557, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894857252173958e-05, + "loss": 3.4573, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.188648768346717e-05, + "loss": 3.4655, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.187810173595665e-05, + "loss": 3.4499, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.186971578844613e-05, + "loss": 3.4503, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.186132984093561e-05, + "loss": 3.4583, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852960272228823e-05, + "loss": 3.4485, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844574324718303e-05, + "loss": 3.4567, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.183618837720778e-05, + "loss": 3.4545, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.182780242969726e-05, + "loss": 3.45, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1819432860990475e-05, + "loss": 3.462, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1811046913479955e-05, + "loss": 3.4389, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1802660965969432e-05, + "loss": 3.442, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1794275018458912e-05, + "loss": 3.4549, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1785905449752124e-05, + "loss": 3.4564, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1777519502241604e-05, + "loss": 3.4475, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1769133554731084e-05, + "loss": 3.4528, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760747607220564e-05, + "loss": 3.4385, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1752378038513777e-05, + "loss": 3.4507, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1743992091003253e-05, + "loss": 3.4371, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1735606143492733e-05, + "loss": 3.4557, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1727220195982213e-05, + "loss": 3.4654, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1718850627275426e-05, + "loss": 3.4547, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1710464679764906e-05, + "loss": 3.4555, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1702078732254386e-05, + "loss": 3.4443, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1693692784743866e-05, + "loss": 3.4482, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1685323216037075e-05, + "loss": 3.4447, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1676937268526558e-05, + "loss": 3.4609, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1668551321016038e-05, + "loss": 3.4523, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1660165373505518e-05, + "loss": 3.4567, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651795804798727e-05, + "loss": 3.4443, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1643409857288207e-05, + "loss": 3.4616, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163504028858142e-05, + "loss": 3.448, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.16266543410709e-05, + "loss": 3.4551, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161826839356038e-05, + "loss": 3.4388, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160988244604986e-05, + "loss": 3.4581, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.160149649853934e-05, + "loss": 3.4426, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.159311055102882e-05, + "loss": 3.4529, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.15847246035183e-05, + "loss": 3.4433, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.157633865600778e-05, + "loss": 3.4543, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.156796908730099e-05, + "loss": 3.4491, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155958313979047e-05, + "loss": 3.4471, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.155119719227995e-05, + "loss": 3.4575, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.154281124476943e-05, + "loss": 3.4627, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.153444167606264e-05, + "loss": 3.4577, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152605572855212e-05, + "loss": 3.4515, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517669781041604e-05, + "loss": 3.4481, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.150928383353108e-05, + "loss": 3.4467, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1500914264824293e-05, + "loss": 3.4488, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1492528317313773e-05, + "loss": 3.4529, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1484142369803253e-05, + "loss": 3.4409, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.147575642229273e-05, + "loss": 3.4523, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1467386853585945e-05, + "loss": 3.4536, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1459000906075425e-05, + "loss": 3.4524, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1450614958564905e-05, + "loss": 3.4504, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1442229011054382e-05, + "loss": 3.4526, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1433859442347594e-05, + "loss": 3.4448, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1425473494837074e-05, + "loss": 3.4577, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1417087547326554e-05, + "loss": 3.4578, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408701599816034e-05, + "loss": 3.4579, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1400332031109247e-05, + "loss": 3.4423, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391946083598727e-05, + "loss": 3.4553, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1383560136088203e-05, + "loss": 3.4561, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1375174188577683e-05, + "loss": 3.4454, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.13668046198709e-05, + "loss": 3.4552, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.135841867236038e-05, + "loss": 3.4548, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1350032724849856e-05, + "loss": 3.4543, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1341646777339335e-05, + "loss": 3.4705, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1333277208632548e-05, + "loss": 3.4484, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324891261122028e-05, + "loss": 3.4571, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1316505313611508e-05, + "loss": 3.4532, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1308119366100988e-05, + "loss": 3.4539, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.12997497973942e-05, + "loss": 3.4469, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1291363849883677e-05, + "loss": 3.4471, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282977902373157e-05, + "loss": 3.4519, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1274591954862637e-05, + "loss": 3.4375, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1266222386155853e-05, + "loss": 3.456, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.85917592048645, + "eval_runtime": 304.0686, + "eval_samples_per_second": 1254.95, + "eval_steps_per_second": 39.218, + "step": 1755352 + }, + { + "epoch": 0.0, + "learning_rate": 2.125783643864533e-05, + "loss": 3.4562, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124945049113481e-05, + "loss": 3.4452, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.124106454362429e-05, + "loss": 3.4558, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.123267859611377e-05, + "loss": 3.4527, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.122430902740698e-05, + "loss": 3.4636, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.121592307989646e-05, + "loss": 3.4509, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120753713238594e-05, + "loss": 3.4554, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119915118487542e-05, + "loss": 3.4409, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.119078161616863e-05, + "loss": 3.4448, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.118239566865811e-05, + "loss": 3.4522, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.117400972114759e-05, + "loss": 3.4489, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165623773637074e-05, + "loss": 3.4437, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1157254204930283e-05, + "loss": 3.4494, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148868257419763e-05, + "loss": 3.4407, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1140482309909243e-05, + "loss": 3.4424, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1132096362398723e-05, + "loss": 3.4367, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123726793691935e-05, + "loss": 3.4369, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1115340846181415e-05, + "loss": 3.4506, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106954898670895e-05, + "loss": 3.4383, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098568951160375e-05, + "loss": 3.4635, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1090199382453584e-05, + "loss": 3.4542, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081813434943064e-05, + "loss": 3.4582, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1073427487432544e-05, + "loss": 3.4448, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1065041539922024e-05, + "loss": 3.4457, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056671971215237e-05, + "loss": 3.4499, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1048286023704717e-05, + "loss": 3.4583, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039900076194196e-05, + "loss": 3.4438, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031514128683676e-05, + "loss": 3.4482, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102314455997689e-05, + "loss": 3.4403, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101475861246637e-05, + "loss": 3.4453, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100637266495585e-05, + "loss": 3.448, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099798671744533e-05, + "loss": 3.4553, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989617148738538e-05, + "loss": 3.4524, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0981231201228018e-05, + "loss": 3.4529, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972845253717498e-05, + "loss": 3.4493, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0964459306206978e-05, + "loss": 3.4483, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095608973750019e-05, + "loss": 3.4521, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094770378998967e-05, + "loss": 3.4407, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093931784247915e-05, + "loss": 3.4396, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930931894968627e-05, + "loss": 3.4306, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.092256232626184e-05, + "loss": 3.4417, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0914176378751323e-05, + "loss": 3.4412, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905790431240803e-05, + "loss": 3.4508, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089740448373028e-05, + "loss": 3.4465, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.088903491502349e-05, + "loss": 3.443, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.088064896751297e-05, + "loss": 3.4447, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.087226302000245e-05, + "loss": 3.4456, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.086387707249193e-05, + "loss": 3.4328, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0855507503785144e-05, + "loss": 3.4224, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0847121556274624e-05, + "loss": 3.4574, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.08387356087641e-05, + "loss": 3.4478, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0830366040057313e-05, + "loss": 3.4543, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821980092546793e-05, + "loss": 3.4411, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813594145036276e-05, + "loss": 3.4436, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0805208197525753e-05, + "loss": 3.4324, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796838628818965e-05, + "loss": 3.4411, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0788452681308445e-05, + "loss": 3.4475, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0780066733797922e-05, + "loss": 3.4382, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771680786287405e-05, + "loss": 3.4633, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0763311217580618e-05, + "loss": 3.4438, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754925270070098e-05, + "loss": 3.4332, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746539322559574e-05, + "loss": 3.4583, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0738153375049054e-05, + "loss": 3.4288, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729783806342267e-05, + "loss": 3.4314, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0721397858831747e-05, + "loss": 3.4548, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0713011911321226e-05, + "loss": 3.448, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704625963810706e-05, + "loss": 3.4365, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.069625639510392e-05, + "loss": 3.4396, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687870447593396e-05, + "loss": 3.4247, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679484500082875e-05, + "loss": 3.4381, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.067109855257236e-05, + "loss": 3.4445, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.066272898386557e-05, + "loss": 3.437, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0654343036355048e-05, + "loss": 3.4455, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645957088844528e-05, + "loss": 3.4423, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637571141334008e-05, + "loss": 3.4547, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062920157262722e-05, + "loss": 3.4386, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.06208156251167e-05, + "loss": 3.4427, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.061242967760618e-05, + "loss": 3.4437, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060404373009566e-05, + "loss": 3.4391, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.059567416138887e-05, + "loss": 3.4468, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.058728821387835e-05, + "loss": 3.4452, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057890226636783e-05, + "loss": 3.4385, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570516318857312e-05, + "loss": 3.4487, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.056214675015052e-05, + "loss": 3.4273, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.055376080264e-05, + "loss": 3.4302, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.054537485512948e-05, + "loss": 3.4448, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.053698890761896e-05, + "loss": 3.4473, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528619338912174e-05, + "loss": 3.4324, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0520233391401654e-05, + "loss": 3.4446, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511847443891134e-05, + "loss": 3.4267, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0503461496380614e-05, + "loss": 3.4385, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0495091927673823e-05, + "loss": 3.4312, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0486705980163303e-05, + "loss": 3.4412, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0478320032652783e-05, + "loss": 3.4526, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469934085142263e-05, + "loss": 3.442, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461564516435475e-05, + "loss": 3.448, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0453178568924955e-05, + "loss": 3.433, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444792621414435e-05, + "loss": 3.4398, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0436406673903915e-05, + "loss": 3.4369, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0428037105197124e-05, + "loss": 3.448, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419651157686608e-05, + "loss": 3.4407, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0411265210176087e-05, + "loss": 3.449, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402879262665567e-05, + "loss": 3.4345, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0394509693958777e-05, + "loss": 3.445, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0386123746448257e-05, + "loss": 3.4425, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037775417774147e-05, + "loss": 3.4412, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036936823023095e-05, + "loss": 3.4297, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.036098228272043e-05, + "loss": 3.4472, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.035259633520991e-05, + "loss": 3.4294, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034421038769939e-05, + "loss": 3.4428, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033582444018887e-05, + "loss": 3.4316, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0327438492678345e-05, + "loss": 3.443, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031906892397156e-05, + "loss": 3.4395, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.031068297646104e-05, + "loss": 3.4367, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030229702895052e-05, + "loss": 3.4461, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293911081439998e-05, + "loss": 3.4521, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028554151273321e-05, + "loss": 3.4484, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027715556522269e-05, + "loss": 3.4394, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026876961771217e-05, + "loss": 3.4369, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.026038367020165e-05, + "loss": 3.4334, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0252014101494863e-05, + "loss": 3.44, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0243628153984342e-05, + "loss": 3.4395, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023524220647382e-05, + "loss": 3.4303, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.02268562589633e-05, + "loss": 3.4433, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0218486690256515e-05, + "loss": 3.4466, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0210100742745995e-05, + "loss": 3.4374, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.020171479523547e-05, + "loss": 3.4372, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.019332884772495e-05, + "loss": 3.4428, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184959279018164e-05, + "loss": 3.4341, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176573331507644e-05, + "loss": 3.4465, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0168187383997124e-05, + "loss": 3.4458, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159801436486604e-05, + "loss": 3.4487, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0151431867779816e-05, + "loss": 3.4302, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0143045920269293e-05, + "loss": 3.4465, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134659972758773e-05, + "loss": 3.4432, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0126274025248253e-05, + "loss": 3.4373, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.011790445654147e-05, + "loss": 3.4454, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0109518509030945e-05, + "loss": 3.4369, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0101132561520425e-05, + "loss": 3.4475, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092746614009905e-05, + "loss": 3.4622, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0084377045303118e-05, + "loss": 3.4345, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075991097792597e-05, + "loss": 3.4448, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067605150282077e-05, + "loss": 3.4458, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0059219202771557e-05, + "loss": 3.4426, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050849634064766e-05, + "loss": 3.436, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0042463686554246e-05, + "loss": 3.4343, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0034077739043726e-05, + "loss": 3.4431, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025691791533206e-05, + "loss": 3.4264, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.001732222282642e-05, + "loss": 3.4435, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.861421585083008, + "eval_runtime": 304.0853, + "eval_samples_per_second": 1254.881, + "eval_steps_per_second": 39.216, + "step": 1831672 + }, + { + "epoch": 1.0, + "learning_rate": 2.00089362753159e-05, + "loss": 3.4407, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.000055032780538e-05, + "loss": 3.4349, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.999216438029486e-05, + "loss": 3.4437, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983794811588068e-05, + "loss": 3.4435, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9975408864077548e-05, + "loss": 3.4517, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996702291656703e-05, + "loss": 3.4405, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995863696905651e-05, + "loss": 3.4453, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.995026740034972e-05, + "loss": 3.4325, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.99418814528392e-05, + "loss": 3.4314, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993349550532868e-05, + "loss": 3.4427, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992510955781816e-05, + "loss": 3.4391, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916739989111372e-05, + "loss": 3.4314, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.9908354041600852e-05, + "loss": 3.4427, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9899968094090332e-05, + "loss": 3.4277, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9891582146579812e-05, + "loss": 3.4316, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988321257787302e-05, + "loss": 3.4234, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.98748266303625e-05, + "loss": 3.4307, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9866440682851985e-05, + "loss": 3.4383, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9858054735341465e-05, + "loss": 3.4309, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9849685166634674e-05, + "loss": 3.4489, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9841299219124154e-05, + "loss": 3.4461, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832913271613634e-05, + "loss": 3.4446, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9824527324103114e-05, + "loss": 3.4361, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9816157755396326e-05, + "loss": 3.4379, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807771807885806e-05, + "loss": 3.436, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9799385860375286e-05, + "loss": 3.4478, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9790999912864766e-05, + "loss": 3.431, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9782630344157975e-05, + "loss": 3.4413, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9774244396647455e-05, + "loss": 3.4268, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.976585844913694e-05, + "loss": 3.4362, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.975747250162642e-05, + "loss": 3.4354, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9749102932919627e-05, + "loss": 3.4444, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740716985409107e-05, + "loss": 3.4445, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9732331037898587e-05, + "loss": 3.4453, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723945090388067e-05, + "loss": 3.4317, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.971557552168128e-05, + "loss": 3.4373, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.970718957417076e-05, + "loss": 3.443, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.969880362666024e-05, + "loss": 3.4275, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9690417679149716e-05, + "loss": 3.4319, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.968204811044293e-05, + "loss": 3.4204, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.967366216293241e-05, + "loss": 3.4273, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9665276215421892e-05, + "loss": 3.4318, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.965689026791137e-05, + "loss": 3.4412, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.964852069920458e-05, + "loss": 3.4393, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.964013475169406e-05, + "loss": 3.4278, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.963174880418354e-05, + "loss": 3.4343, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.962336285667302e-05, + "loss": 3.4381, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614993287966233e-05, + "loss": 3.4209, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9606607340455713e-05, + "loss": 3.4142, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959822139294519e-05, + "loss": 3.444, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9589851824238402e-05, + "loss": 3.4393, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9581465876727882e-05, + "loss": 3.4425, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9573079929217362e-05, + "loss": 3.4306, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564693981706842e-05, + "loss": 3.4342, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9556324413000055e-05, + "loss": 3.4246, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9547938465489535e-05, + "loss": 3.4283, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9539552517979015e-05, + "loss": 3.4407, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953116657046849e-05, + "loss": 3.4239, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522797001761707e-05, + "loss": 3.4539, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9514411054251187e-05, + "loss": 3.4349, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9506025106740664e-05, + "loss": 3.4201, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9497639159230144e-05, + "loss": 3.4471, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9489269590523356e-05, + "loss": 3.4273, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480883643012836e-05, + "loss": 3.4179, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9472497695502316e-05, + "loss": 3.4441, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9464111747991796e-05, + "loss": 3.4368, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.945574217928501e-05, + "loss": 3.4263, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.944735623177449e-05, + "loss": 3.4263, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438970284263965e-05, + "loss": 3.4159, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9430584336753445e-05, + "loss": 3.4276, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.942221476804666e-05, + "loss": 3.4375, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413828820536137e-05, + "loss": 3.4242, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9405442873025617e-05, + "loss": 3.4337, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9397056925515097e-05, + "loss": 3.4289, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.938868735680831e-05, + "loss": 3.4435, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9380301409297786e-05, + "loss": 3.431, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.937191546178727e-05, + "loss": 3.4347, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936352951427675e-05, + "loss": 3.4303, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9355159945569962e-05, + "loss": 3.4264, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934677399805944e-05, + "loss": 3.4392, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933838805054892e-05, + "loss": 3.4329, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.93300021030384e-05, + "loss": 3.4269, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.932163253433161e-05, + "loss": 3.4404, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.931324658682109e-05, + "loss": 3.4143, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.930486063931057e-05, + "loss": 3.4226, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.929647469180005e-05, + "loss": 3.4339, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.928810512309326e-05, + "loss": 3.4344, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.927971917558274e-05, + "loss": 3.4212, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9271333228072223e-05, + "loss": 3.4362, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262947280561703e-05, + "loss": 3.4201, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9254577711854912e-05, + "loss": 3.428, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9246191764344392e-05, + "loss": 3.4184, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9237805816833872e-05, + "loss": 3.4275, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9229419869323352e-05, + "loss": 3.4421, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9221050300616565e-05, + "loss": 3.4317, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212664353106045e-05, + "loss": 3.4367, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9204278405595525e-05, + "loss": 3.4267, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9195892458085005e-05, + "loss": 3.4282, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9187522889378214e-05, + "loss": 3.4277, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9179136941867694e-05, + "loss": 3.4328, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170750994357177e-05, + "loss": 3.4306, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9162365046846657e-05, + "loss": 3.435, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153995478139866e-05, + "loss": 3.4302, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145609530629346e-05, + "loss": 3.4301, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9137223583118826e-05, + "loss": 3.4334, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912885401441204e-05, + "loss": 3.4296, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.912046806690152e-05, + "loss": 3.4173, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9112082119391e-05, + "loss": 3.4385, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.910369617188048e-05, + "loss": 3.4217, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.909531022436996e-05, + "loss": 3.43, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086924276859438e-05, + "loss": 3.4243, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9078538329348915e-05, + "loss": 3.4262, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.907016876064213e-05, + "loss": 3.4303, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.906178281313161e-05, + "loss": 3.4257, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9053396865621087e-05, + "loss": 3.4356, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9045010918110567e-05, + "loss": 3.4431, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036624970600047e-05, + "loss": 3.4396, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.902825540189326e-05, + "loss": 3.4303, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.901986945438274e-05, + "loss": 3.4287, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.901148350687222e-05, + "loss": 3.4251, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.90030975593617e-05, + "loss": 3.4299, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994727990654912e-05, + "loss": 3.4306, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898634204314439e-05, + "loss": 3.4205, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.897795609563387e-05, + "loss": 3.4291, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896957014812335e-05, + "loss": 3.4325, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.896120057941656e-05, + "loss": 3.429, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895281463190604e-05, + "loss": 3.4269, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894442868439552e-05, + "loss": 3.4302, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8936042736885e-05, + "loss": 3.426, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.892767316817821e-05, + "loss": 3.4365, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8919287220667693e-05, + "loss": 3.4334, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910901273157173e-05, + "loss": 3.4433, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8902531704450386e-05, + "loss": 3.4203, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8894145756939862e-05, + "loss": 3.4335, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8885759809429342e-05, + "loss": 3.4338, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8877373861918822e-05, + "loss": 3.4281, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8869004293212035e-05, + "loss": 3.4322, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8860618345701515e-05, + "loss": 3.4312, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8852232398190995e-05, + "loss": 3.434, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843846450680475e-05, + "loss": 3.4499, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8835476881973684e-05, + "loss": 3.4238, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8827090934463164e-05, + "loss": 3.4348, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818704986952647e-05, + "loss": 3.4387, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8810319039442127e-05, + "loss": 3.4273, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801949470735336e-05, + "loss": 3.4271, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793563523224816e-05, + "loss": 3.4246, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8785177575714296e-05, + "loss": 3.429, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776791628203776e-05, + "loss": 3.4219, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.876842205949699e-05, + "loss": 3.43, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.861804246902466, + "eval_runtime": 306.7324, + "eval_samples_per_second": 1244.052, + "eval_steps_per_second": 38.878, + "step": 1907992 + }, + { + "epoch": 0.0, + "learning_rate": 1.876003611198647e-05, + "loss": 3.4343, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751650164475948e-05, + "loss": 3.4249, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8743264216965428e-05, + "loss": 3.4324, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734878269454908e-05, + "loss": 3.4349, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726508700748117e-05, + "loss": 3.4444, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.87181227532376e-05, + "loss": 3.4314, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.870973680572708e-05, + "loss": 3.4332, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.870135085821656e-05, + "loss": 3.4219, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.869298128950977e-05, + "loss": 3.4236, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.868459534199925e-05, + "loss": 3.4318, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.867620939448873e-05, + "loss": 3.4264, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.866782344697821e-05, + "loss": 3.4246, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8659453878271422e-05, + "loss": 3.4299, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8651067930760902e-05, + "loss": 3.4167, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8642681983250382e-05, + "loss": 3.4217, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8634296035739862e-05, + "loss": 3.412, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.862592646703307e-05, + "loss": 3.4229, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617540519522554e-05, + "loss": 3.4299, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8609154572012034e-05, + "loss": 3.4169, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600768624501514e-05, + "loss": 3.4377, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8592399055794723e-05, + "loss": 3.4345, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8584013108284203e-05, + "loss": 3.4341, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8575627160773683e-05, + "loss": 3.426, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8567241213263163e-05, + "loss": 3.4271, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558871644556376e-05, + "loss": 3.4294, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8550485697045856e-05, + "loss": 3.4368, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8542099749535336e-05, + "loss": 3.4187, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533713802024812e-05, + "loss": 3.4299, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8525344233318025e-05, + "loss": 3.4191, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516958285807508e-05, + "loss": 3.4256, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508572338296988e-05, + "loss": 3.4287, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8500186390786464e-05, + "loss": 3.4294, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491816822079677e-05, + "loss": 3.4305, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483430874569157e-05, + "loss": 3.4373, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8475044927058633e-05, + "loss": 3.4258, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466658979548117e-05, + "loss": 3.4258, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.845828941084133e-05, + "loss": 3.4324, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.844990346333081e-05, + "loss": 3.4173, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441517515820286e-05, + "loss": 3.4193, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8433131568309766e-05, + "loss": 3.4152, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424761999602978e-05, + "loss": 3.4162, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8416376052092458e-05, + "loss": 3.4192, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407990104581938e-05, + "loss": 3.4354, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.839962053587515e-05, + "loss": 3.4236, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.839123458836463e-05, + "loss": 3.422, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382848640854107e-05, + "loss": 3.4201, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8374462693343587e-05, + "loss": 3.4275, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8366093124636803e-05, + "loss": 3.4117, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357707177126283e-05, + "loss": 3.4055, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834932122961576e-05, + "loss": 3.4338, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.834093528210524e-05, + "loss": 3.4282, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332565713398452e-05, + "loss": 3.4351, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8324179765887932e-05, + "loss": 3.4173, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315793818377412e-05, + "loss": 3.4221, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8307407870866892e-05, + "loss": 3.4162, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8299038302160104e-05, + "loss": 3.4169, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8290668733453313e-05, + "loss": 3.4331, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8282282785942793e-05, + "loss": 3.4115, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273896838432277e-05, + "loss": 3.4442, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265510890921757e-05, + "loss": 3.427, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8257124943411233e-05, + "loss": 3.4059, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8248738995900713e-05, + "loss": 3.4361, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8240353048390193e-05, + "loss": 3.4194, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231967100879673e-05, + "loss": 3.4069, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223597532172886e-05, + "loss": 3.4282, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8215211584662366e-05, + "loss": 3.4306, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206825637151846e-05, + "loss": 3.4147, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8198439689641325e-05, + "loss": 3.4205, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8190070120934535e-05, + "loss": 3.4021, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181684173424015e-05, + "loss": 3.4178, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8173298225913494e-05, + "loss": 3.4264, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164912278402978e-05, + "loss": 3.4135, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156542709696187e-05, + "loss": 3.4248, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8148156762185667e-05, + "loss": 3.4164, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139770814675147e-05, + "loss": 3.4389, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8131384867164627e-05, + "loss": 3.4239, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.812301529845784e-05, + "loss": 3.4235, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.811462935094732e-05, + "loss": 3.4176, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.81062434034368e-05, + "loss": 3.4179, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.809785745592628e-05, + "loss": 3.4268, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089487887219488e-05, + "loss": 3.4212, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8081101939708968e-05, + "loss": 3.4228, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072715992198448e-05, + "loss": 3.4245, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.806433004468793e-05, + "loss": 3.4127, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.805596047598114e-05, + "loss": 3.4073, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.804757452847062e-05, + "loss": 3.4217, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.80391885809601e-05, + "loss": 3.4281, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.803080263344958e-05, + "loss": 3.4124, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8022433064742793e-05, + "loss": 3.4222, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8014047117232273e-05, + "loss": 3.4129, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005661169721753e-05, + "loss": 3.4144, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7997291601014962e-05, + "loss": 3.4102, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988905653504442e-05, + "loss": 3.4163, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7980519705993922e-05, + "loss": 3.4322, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7972133758483402e-05, + "loss": 3.4216, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963764189776614e-05, + "loss": 3.4247, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7955378242266094e-05, + "loss": 3.4149, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946992294755574e-05, + "loss": 3.4159, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7938606347245054e-05, + "loss": 3.4163, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7930236778538263e-05, + "loss": 3.428, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921850831027747e-05, + "loss": 3.419, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7913464883517227e-05, + "loss": 3.4253, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7905078936006707e-05, + "loss": 3.4199, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896709367299916e-05, + "loss": 3.4173, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7888323419789396e-05, + "loss": 3.4248, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879937472278876e-05, + "loss": 3.4187, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7871551524768355e-05, + "loss": 3.4095, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7863181956061568e-05, + "loss": 3.4215, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854796008551048e-05, + "loss": 3.4118, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7846410061040528e-05, + "loss": 3.418, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7838024113530004e-05, + "loss": 3.4172, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829654544823217e-05, + "loss": 3.4108, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.78212685973127e-05, + "loss": 3.423, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.781288264980218e-05, + "loss": 3.4174, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804496702291657e-05, + "loss": 3.4229, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779612713358487e-05, + "loss": 3.4314, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.778774118607435e-05, + "loss": 3.4294, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7779355238563826e-05, + "loss": 3.4189, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.777096929105331e-05, + "loss": 3.4186, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.776259972234652e-05, + "loss": 3.4147, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7754213774836e-05, + "loss": 3.4227, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745827827325478e-05, + "loss": 3.4215, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7737441879814958e-05, + "loss": 3.4079, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.772907231110817e-05, + "loss": 3.4187, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.772068636359765e-05, + "loss": 3.4211, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.771230041608713e-05, + "loss": 3.4216, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770391446857661e-05, + "loss": 3.414, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7695544899869823e-05, + "loss": 3.4149, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.76871589523593e-05, + "loss": 3.4128, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767877300484878e-05, + "loss": 3.426, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7670387057338263e-05, + "loss": 3.4235, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7662017488631475e-05, + "loss": 3.434, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7653631541120952e-05, + "loss": 3.4104, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7645245593610432e-05, + "loss": 3.4207, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636859646099912e-05, + "loss": 3.4277, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7628490077393124e-05, + "loss": 3.4129, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7620104129882604e-05, + "loss": 3.4228, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611718182372084e-05, + "loss": 3.4171, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7603332234861564e-05, + "loss": 3.4262, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7594962666154773e-05, + "loss": 3.4366, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7586576718644253e-05, + "loss": 3.4187, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7578190771133733e-05, + "loss": 3.4229, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569804823623216e-05, + "loss": 3.4252, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7561435254916426e-05, + "loss": 3.4209, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7553049307405906e-05, + "loss": 3.4165, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544663359895385e-05, + "loss": 3.4169, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7536277412384865e-05, + "loss": 3.4193, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527907843678078e-05, + "loss": 3.4125, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7519521896167558e-05, + "loss": 3.4152, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8624870777130127, + "eval_runtime": 302.5615, + "eval_samples_per_second": 1261.202, + "eval_steps_per_second": 39.413, + "step": 1984312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7511135948657038e-05, + "loss": 3.4195, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502750001146518e-05, + "loss": 3.4156, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7494380432439727e-05, + "loss": 3.4202, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485994484929207e-05, + "loss": 3.4227, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477608537418687e-05, + "loss": 3.4335, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.746922258990817e-05, + "loss": 3.4197, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.746085302120138e-05, + "loss": 3.4257, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.745246707369086e-05, + "loss": 3.4131, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.744408112618034e-05, + "loss": 3.4116, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.743569517866982e-05, + "loss": 3.4166, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.742732560996303e-05, + "loss": 3.421, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741893966245251e-05, + "loss": 3.4151, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.741055371494199e-05, + "loss": 3.4197, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.740216776743147e-05, + "loss": 3.4066, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.739379819872468e-05, + "loss": 3.4111, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.738541225121416e-05, + "loss": 3.3955, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.737702630370364e-05, + "loss": 3.416, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368640356193124e-05, + "loss": 3.4196, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7360270787486333e-05, + "loss": 3.4072, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351884839975813e-05, + "loss": 3.4255, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7343498892465293e-05, + "loss": 3.4256, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7335112944954773e-05, + "loss": 3.4223, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326743376247985e-05, + "loss": 3.416, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7318357428737465e-05, + "loss": 3.4145, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309971481226945e-05, + "loss": 3.4208, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7301585533716425e-05, + "loss": 3.4262, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7293215965009634e-05, + "loss": 3.4061, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7284830017499114e-05, + "loss": 3.4206, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7276444069988594e-05, + "loss": 3.4103, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7268058122478074e-05, + "loss": 3.4123, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259688553771287e-05, + "loss": 3.4173, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7251318985064496e-05, + "loss": 3.4202, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242933037553976e-05, + "loss": 3.417, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7234547090043456e-05, + "loss": 3.4294, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7226161142532936e-05, + "loss": 3.4127, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.721777519502242e-05, + "loss": 3.4182, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.72093892475119e-05, + "loss": 3.4245, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7201003300001375e-05, + "loss": 3.4033, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192617352490855e-05, + "loss": 3.4092, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7184247783784068e-05, + "loss": 3.4081, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7175861836273548e-05, + "loss": 3.4029, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7167475888763028e-05, + "loss": 3.412, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7159089941252508e-05, + "loss": 3.4236, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.715072037254572e-05, + "loss": 3.4148, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7142334425035197e-05, + "loss": 3.4107, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133948477524677e-05, + "loss": 3.4125, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125562530014157e-05, + "loss": 3.4164, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7117192961307373e-05, + "loss": 3.3989, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.710880701379685e-05, + "loss": 3.3918, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.710042106628633e-05, + "loss": 3.4221, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709203511877581e-05, + "loss": 3.4198, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.708366555006902e-05, + "loss": 3.4228, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.70752796025585e-05, + "loss": 3.4088, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.706689365504798e-05, + "loss": 3.409, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705850770753746e-05, + "loss": 3.4072, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.705013813883067e-05, + "loss": 3.4064, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.704175219132015e-05, + "loss": 3.4226, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703336624380963e-05, + "loss": 3.3962, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702498029629911e-05, + "loss": 3.4384, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016610727592323e-05, + "loss": 3.4148, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7008224780081803e-05, + "loss": 3.4004, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999838832571283e-05, + "loss": 3.4204, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6991452885060763e-05, + "loss": 3.408, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6983083316353972e-05, + "loss": 3.3999, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974697368843455e-05, + "loss": 3.4188, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6966311421332935e-05, + "loss": 3.4214, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957941852626144e-05, + "loss": 3.4021, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6949555905115624e-05, + "loss": 3.4146, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6941169957605104e-05, + "loss": 3.3927, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932784010094584e-05, + "loss": 3.4059, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6924414441387797e-05, + "loss": 3.4109, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6916028493877277e-05, + "loss": 3.4069, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907642546366756e-05, + "loss": 3.4128, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6899256598856236e-05, + "loss": 3.4081, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890887030149446e-05, + "loss": 3.426, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6882501082638925e-05, + "loss": 3.4124, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687411513512841e-05, + "loss": 3.4197, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686572918761789e-05, + "loss": 3.4052, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6857359618911098e-05, + "loss": 3.4073, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848973671400578e-05, + "loss": 3.4159, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840587723890058e-05, + "loss": 3.4087, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6832201776379538e-05, + "loss": 3.4108, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.682383220767275e-05, + "loss": 3.4175, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.681544626016223e-05, + "loss": 3.4052, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.680706031265171e-05, + "loss": 3.3933, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.679867436514119e-05, + "loss": 3.4114, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.67903047964344e-05, + "loss": 3.4158, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.678191884892388e-05, + "loss": 3.4022, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.677353290141336e-05, + "loss": 3.4116, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6765146953902842e-05, + "loss": 3.4073, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.675677738519605e-05, + "loss": 3.4015, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.674839143768553e-05, + "loss": 3.4002, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.674000549017501e-05, + "loss": 3.4095, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.673161954266449e-05, + "loss": 3.4231, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6723249973957704e-05, + "loss": 3.4125, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714864026447184e-05, + "loss": 3.4132, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6706478078936664e-05, + "loss": 3.4047, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6698092131426144e-05, + "loss": 3.4061, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6689722562719353e-05, + "loss": 3.4055, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6681336615208833e-05, + "loss": 3.4147, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672950667698313e-05, + "loss": 3.4121, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664564720187796e-05, + "loss": 3.4162, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6656195151481005e-05, + "loss": 3.4103, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647809203970485e-05, + "loss": 3.4045, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6639423256459965e-05, + "loss": 3.4144, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6631037308949445e-05, + "loss": 3.4119, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6622667740242658e-05, + "loss": 3.3992, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6614281792732138e-05, + "loss": 3.4097, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605895845221617e-05, + "loss": 3.4068, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6597509897711097e-05, + "loss": 3.4103, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6589140329004307e-05, + "loss": 3.4023, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580754381493786e-05, + "loss": 3.4007, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6572368433983266e-05, + "loss": 3.4125, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563982486472746e-05, + "loss": 3.4149, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.655561291776596e-05, + "loss": 3.4096, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654722697025544e-05, + "loss": 3.4167, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653884102274492e-05, + "loss": 3.4216, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6530455075234395e-05, + "loss": 3.4083, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.652208550652761e-05, + "loss": 3.4115, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.651369955901709e-05, + "loss": 3.3997, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650531361150657e-05, + "loss": 3.4124, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496927663996048e-05, + "loss": 3.4087, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.648855809528926e-05, + "loss": 3.4001, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.648017214777874e-05, + "loss": 3.4052, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.647178620026822e-05, + "loss": 3.4118, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.64634002527577e-05, + "loss": 3.4124, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6455030684050913e-05, + "loss": 3.4036, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6446644736540392e-05, + "loss": 3.4081, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.643825878902987e-05, + "loss": 3.4083, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.642987284151935e-05, + "loss": 3.4113, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6421503272812565e-05, + "loss": 3.4164, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641311732530204e-05, + "loss": 3.4203, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640473137779152e-05, + "loss": 3.4048, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6396361809084734e-05, + "loss": 3.409, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6387975861574214e-05, + "loss": 3.4145, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6379589914063694e-05, + "loss": 3.4025, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6371203966553174e-05, + "loss": 3.4113, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362834397846386e-05, + "loss": 3.4115, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6354448450335866e-05, + "loss": 3.416, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6346062502825343e-05, + "loss": 3.4257, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6337676555314823e-05, + "loss": 3.4099, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6329306986608035e-05, + "loss": 3.4114, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320921039097515e-05, + "loss": 3.4153, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6312535091586995e-05, + "loss": 3.4096, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6304149144076475e-05, + "loss": 3.4061, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295779575369688e-05, + "loss": 3.41, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6287393627859164e-05, + "loss": 3.4059, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6279007680348644e-05, + "loss": 3.4068, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6270621732838127e-05, + "loss": 3.4052, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.8640949726104736, + "eval_runtime": 304.958, + "eval_samples_per_second": 1251.29, + "eval_steps_per_second": 39.104, + "step": 2060632 + }, + { + "epoch": 0.0, + "learning_rate": 1.6262235785327607e-05, + "loss": 3.4028, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253849837817087e-05, + "loss": 3.4062, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6245463890306567e-05, + "loss": 3.4124, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6237077942796047e-05, + "loss": 3.4155, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228708374089256e-05, + "loss": 3.4205, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6220322426578736e-05, + "loss": 3.4091, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.621193647906822e-05, + "loss": 3.4162, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.620356691036143e-05, + "loss": 3.4057, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.619518096285091e-05, + "loss": 3.3976, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618679501534039e-05, + "loss": 3.4027, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617840906782987e-05, + "loss": 3.416, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.617002312031935e-05, + "loss": 3.4012, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.616163717280883e-05, + "loss": 3.4121, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615325122529831e-05, + "loss": 3.3937, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614488165659152e-05, + "loss": 3.4001, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6136495709080998e-05, + "loss": 3.3905, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6128109761570477e-05, + "loss": 3.4077, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119723814059957e-05, + "loss": 3.4066, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.611135424535317e-05, + "loss": 3.4036, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.610296829784265e-05, + "loss": 3.4071, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609458235033213e-05, + "loss": 3.4196, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608619640282161e-05, + "loss": 3.4126, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.607782683411482e-05, + "loss": 3.4077, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6069440886604302e-05, + "loss": 3.4028, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6061054939093782e-05, + "loss": 3.4175, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052668991583262e-05, + "loss": 3.4119, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604429942287647e-05, + "loss": 3.3997, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603591347536595e-05, + "loss": 3.4078, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602752752785543e-05, + "loss": 3.4022, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601914158034491e-05, + "loss": 3.3964, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010772011638124e-05, + "loss": 3.4107, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6002386064127604e-05, + "loss": 3.4094, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5994016495420816e-05, + "loss": 3.4114, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5985630547910293e-05, + "loss": 3.4173, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5977244600399773e-05, + "loss": 3.4025, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968858652889253e-05, + "loss": 3.41, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5960472705378736e-05, + "loss": 3.4111, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5952086757868216e-05, + "loss": 3.3968, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5943700810357696e-05, + "loss": 3.403, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5935314862847176e-05, + "loss": 3.3928, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5926945294140385e-05, + "loss": 3.392, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5918559346629865e-05, + "loss": 3.3996, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5910173399119345e-05, + "loss": 3.4147, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901787451608825e-05, + "loss": 3.4038, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5893417882902037e-05, + "loss": 3.3962, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5885031935391517e-05, + "loss": 3.4072, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876645987880997e-05, + "loss": 3.4046, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5868260040370474e-05, + "loss": 3.393, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585989047166369e-05, + "loss": 3.3829, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.585150452415317e-05, + "loss": 3.4103, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5843118576642646e-05, + "loss": 3.4118, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834732629132126e-05, + "loss": 3.4116, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.582636306042534e-05, + "loss": 3.4, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581797711291482e-05, + "loss": 3.3984, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.58095911654043e-05, + "loss": 3.3959, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.580120521789378e-05, + "loss": 3.3965, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.579283564918699e-05, + "loss": 3.4123, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.578444970167647e-05, + "loss": 3.3899, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5776063754165947e-05, + "loss": 3.4265, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767677806655427e-05, + "loss": 3.4053, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5759308237948643e-05, + "loss": 3.3929, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575092229043812e-05, + "loss": 3.4086, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.57425363429276e-05, + "loss": 3.3962, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.573415039541708e-05, + "loss": 3.393, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725780826710292e-05, + "loss": 3.4059, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5717394879199772e-05, + "loss": 3.4117, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5709008931689252e-05, + "loss": 3.3959, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700639362982465e-05, + "loss": 3.403, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5692253415471945e-05, + "loss": 3.3807, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568386746796142e-05, + "loss": 3.3976, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.56754815204509e-05, + "loss": 3.3994, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5667111951744114e-05, + "loss": 3.4002, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5658726004233593e-05, + "loss": 3.3977, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5650340056723073e-05, + "loss": 3.3993, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641954109212553e-05, + "loss": 3.4189, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5633584540505766e-05, + "loss": 3.402, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5625198592995242e-05, + "loss": 3.4055, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616812645484726e-05, + "loss": 3.3961, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5608426697974206e-05, + "loss": 3.4001, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5600057129267418e-05, + "loss": 3.4058, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591671181756895e-05, + "loss": 3.3999, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5583285234246375e-05, + "loss": 3.3983, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574899286735855e-05, + "loss": 3.4075, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5566529718029067e-05, + "loss": 3.3981, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5558143770518547e-05, + "loss": 3.3827, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549757823008027e-05, + "loss": 3.3974, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5541371875497507e-05, + "loss": 3.4059, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5533002306790716e-05, + "loss": 3.3935, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524616359280196e-05, + "loss": 3.4001, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5516230411769676e-05, + "loss": 3.3993, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550784446425916e-05, + "loss": 3.3907, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.549947489555237e-05, + "loss": 3.3938, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.549108894804185e-05, + "loss": 3.3957, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548270300053133e-05, + "loss": 3.4099, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547431705302081e-05, + "loss": 3.407, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.546594748431402e-05, + "loss": 3.4063, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.54575615368035e-05, + "loss": 3.3917, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544917558929298e-05, + "loss": 3.3976, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.544078964178246e-05, + "loss": 3.3996, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.543242007307567e-05, + "loss": 3.4042, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.542403412556515e-05, + "loss": 3.4011, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541564817805463e-05, + "loss": 3.4049, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5407262230544113e-05, + "loss": 3.4011, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398892661837322e-05, + "loss": 3.3942, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5390506714326802e-05, + "loss": 3.4073, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5382120766816282e-05, + "loss": 3.3974, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373734819305762e-05, + "loss": 3.3963, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5365365250598975e-05, + "loss": 3.398, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356979303088454e-05, + "loss": 3.3977, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5348593355577934e-05, + "loss": 3.3971, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5340207408067414e-05, + "loss": 3.3922, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5331837839360623e-05, + "loss": 3.3916, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5323451891850103e-05, + "loss": 3.4033, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5315065944339583e-05, + "loss": 3.4028, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306679996829067e-05, + "loss": 3.3989, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5298310428122276e-05, + "loss": 3.4054, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289924480611756e-05, + "loss": 3.4161, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5281538533101236e-05, + "loss": 3.3967, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5273152585590716e-05, + "loss": 3.4004, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5264783016883928e-05, + "loss": 3.3966, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5256397069373406e-05, + "loss": 3.3976, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5248011121862888e-05, + "loss": 3.3977, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239625174352368e-05, + "loss": 3.3938, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5231255605645577e-05, + "loss": 3.3967, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222869658135059e-05, + "loss": 3.4027, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5214500089428268e-05, + "loss": 3.4004, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.520611414191775e-05, + "loss": 3.3952, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.519772819440723e-05, + "loss": 3.3983, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.518934224689671e-05, + "loss": 3.3989, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.518095629938619e-05, + "loss": 3.3987, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172570351875668e-05, + "loss": 3.4038, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5164184404365148e-05, + "loss": 3.4109, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.515581483565836e-05, + "loss": 3.3948, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5147428888147842e-05, + "loss": 3.4023, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5139042940637318e-05, + "loss": 3.4025, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130656993126798e-05, + "loss": 3.3931, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5122287424420012e-05, + "loss": 3.3982, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113901476909489e-05, + "loss": 3.3977, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105515529398969e-05, + "loss": 3.4124, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.509712958188845e-05, + "loss": 3.4124, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088760013181663e-05, + "loss": 3.4002, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5080374065671141e-05, + "loss": 3.402, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071988118160621e-05, + "loss": 3.4058, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063602170650101e-05, + "loss": 3.4005, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5055232601943314e-05, + "loss": 3.3958, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046846654432792e-05, + "loss": 3.4, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5038460706922272e-05, + "loss": 3.3912, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5030074759411752e-05, + "loss": 3.399, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021705190704963e-05, + "loss": 3.3947, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.86489200592041, + "eval_runtime": 305.1998, + "eval_samples_per_second": 1250.299, + "eval_steps_per_second": 39.073, + "step": 2136952 + }, + { + "epoch": 1.0, + "learning_rate": 1.5013319243194443e-05, + "loss": 3.4012, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004933295683923e-05, + "loss": 3.3917, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4996547348173404e-05, + "loss": 3.4008, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4988177779466613e-05, + "loss": 3.4055, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979791831956095e-05, + "loss": 3.4089, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4971405884445575e-05, + "loss": 3.4018, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4963019936935055e-05, + "loss": 3.4087, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954650368228266e-05, + "loss": 3.3934, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4946264420717746e-05, + "loss": 3.3886, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937878473207226e-05, + "loss": 3.3983, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4929492525696706e-05, + "loss": 3.3972, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4921106578186186e-05, + "loss": 3.3944, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912720630675667e-05, + "loss": 3.4038, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4904334683165144e-05, + "loss": 3.383, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895965114458358e-05, + "loss": 3.3917, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887579166947838e-05, + "loss": 3.3779, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4879193219437318e-05, + "loss": 3.4001, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870807271926796e-05, + "loss": 3.3941, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4862437703220009e-05, + "loss": 3.3942, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4854051755709489e-05, + "loss": 3.3966, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845665808198969e-05, + "loss": 3.4082, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4837279860688447e-05, + "loss": 3.4019, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.482891029198166e-05, + "loss": 3.3981, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.482052434447114e-05, + "loss": 3.3942, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4812138396960617e-05, + "loss": 3.4079, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803752449450097e-05, + "loss": 3.3995, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4795382880743312e-05, + "loss": 3.391, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786996933232792e-05, + "loss": 3.3996, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778610985722268e-05, + "loss": 3.3873, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.477022503821175e-05, + "loss": 3.3938, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761855469504962e-05, + "loss": 3.3995, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4753469521994442e-05, + "loss": 3.3944, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4745099953287653e-05, + "loss": 3.4023, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736714005777133e-05, + "loss": 3.4069, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4728328058266613e-05, + "loss": 3.3929, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719942110756091e-05, + "loss": 3.4005, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711556163245571e-05, + "loss": 3.4031, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4703170215735051e-05, + "loss": 3.3861, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694784268224531e-05, + "loss": 3.394, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4686398320714013e-05, + "loss": 3.3819, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4678028752007222e-05, + "loss": 3.3822, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669642804496703e-05, + "loss": 3.3922, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4661256856986183e-05, + "loss": 3.406, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652870909475663e-05, + "loss": 3.391, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644501340768874e-05, + "loss": 3.3913, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4636115393258354e-05, + "loss": 3.3925, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627729445747834e-05, + "loss": 3.3976, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4619343498237314e-05, + "loss": 3.3823, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610973929530525e-05, + "loss": 3.3761, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4602587982020005e-05, + "loss": 3.3963, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4594202034509485e-05, + "loss": 3.408, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585816086998966e-05, + "loss": 3.4021, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4577446518292175e-05, + "loss": 3.3858, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4569060570781657e-05, + "loss": 3.393, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560674623271137e-05, + "loss": 3.3869, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4552288675760617e-05, + "loss": 3.3799, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543919107053828e-05, + "loss": 3.4074, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535533159543308e-05, + "loss": 3.3777, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4527147212032788e-05, + "loss": 3.412, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518761264522268e-05, + "loss": 3.3943, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4510391695815478e-05, + "loss": 3.3846, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4502005748304958e-05, + "loss": 3.399, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493619800794438e-05, + "loss": 3.3902, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.448523385328392e-05, + "loss": 3.3809, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.447686428457713e-05, + "loss": 3.3933, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4468478337066609e-05, + "loss": 3.4017, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.446009238955609e-05, + "loss": 3.3869, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.44517228208493e-05, + "loss": 3.3933, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4443336873338782e-05, + "loss": 3.3708, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434950925828261e-05, + "loss": 3.3884, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4426564978317741e-05, + "loss": 3.3907, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4418195409610952e-05, + "loss": 3.3919, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409809462100432e-05, + "loss": 3.3862, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4401423514589912e-05, + "loss": 3.39, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4393037567079392e-05, + "loss": 3.4055, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384667998372603e-05, + "loss": 3.3948, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4376282050862083e-05, + "loss": 3.3953, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367896103351563e-05, + "loss": 3.3884, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359510155841041e-05, + "loss": 3.3909, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4351140587134254e-05, + "loss": 3.3999, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342754639623735e-05, + "loss": 3.3899, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4334368692113215e-05, + "loss": 3.3911, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325982744602692e-05, + "loss": 3.3964, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317613175895906e-05, + "loss": 3.3922, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4309227228385386e-05, + "loss": 3.3713, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300841280874866e-05, + "loss": 3.3916, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4292455333364344e-05, + "loss": 3.3919, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4284085764657557e-05, + "loss": 3.3826, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275699817147036e-05, + "loss": 3.3885, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4267313869636515e-05, + "loss": 3.3874, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258927922125995e-05, + "loss": 3.3823, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250558353419207e-05, + "loss": 3.3824, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4242172405908689e-05, + "loss": 3.3902, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233786458398165e-05, + "loss": 3.3964, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4225400510887645e-05, + "loss": 3.3929, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.421703094218086e-05, + "loss": 3.3996, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.420864499467034e-05, + "loss": 3.3836, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4200259047159816e-05, + "loss": 3.3867, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191873099649298e-05, + "loss": 3.3887, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.418350353094251e-05, + "loss": 3.3947, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4175117583431988e-05, + "loss": 3.3913, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166731635921468e-05, + "loss": 3.3911, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4158345688410948e-05, + "loss": 3.3891, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149976119704161e-05, + "loss": 3.3875, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141590172193639e-05, + "loss": 3.3966, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4133204224683119e-05, + "loss": 3.3872, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124818277172599e-05, + "loss": 3.3857, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4116448708465813e-05, + "loss": 3.3908, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.410806276095529e-05, + "loss": 3.384, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.409967681344477e-05, + "loss": 3.3861, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4091290865934251e-05, + "loss": 3.3853, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.408292129722746e-05, + "loss": 3.3809, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074535349716942e-05, + "loss": 3.3922, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4066149402206422e-05, + "loss": 3.3964, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057763454695902e-05, + "loss": 3.382, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4049393885989113e-05, + "loss": 3.3971, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4041007938478593e-05, + "loss": 3.4059, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4032621990968073e-05, + "loss": 3.3859, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4024236043457553e-05, + "loss": 3.3903, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015866474750763e-05, + "loss": 3.3867, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4007480527240243e-05, + "loss": 3.3883, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3999094579729723e-05, + "loss": 3.3868, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3990708632219205e-05, + "loss": 3.385, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3982339063512414e-05, + "loss": 3.3867, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973953116001894e-05, + "loss": 3.3946, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3965567168491376e-05, + "loss": 3.3881, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3957197599784585e-05, + "loss": 3.3892, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948811652274066e-05, + "loss": 3.3898, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3940425704763546e-05, + "loss": 3.3878, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3932039757253026e-05, + "loss": 3.3826, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923670188546237e-05, + "loss": 3.4015, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3915284241035717e-05, + "loss": 3.396, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906898293525197e-05, + "loss": 3.3884, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898512346014677e-05, + "loss": 3.3863, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3890142777307888e-05, + "loss": 3.3955, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881756829797368e-05, + "loss": 3.3843, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3873370882286848e-05, + "loss": 3.3901, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.386498493477633e-05, + "loss": 3.3901, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856615366069539e-05, + "loss": 3.4027, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.384822941855902e-05, + "loss": 3.3982, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.38398434710485e-05, + "loss": 3.3997, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.383145752353798e-05, + "loss": 3.3867, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3823087954831191e-05, + "loss": 3.3988, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.381470200732067e-05, + "loss": 3.3892, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.380631605981015e-05, + "loss": 3.3848, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.379793011229963e-05, + "loss": 3.3927, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789560543592842e-05, + "loss": 3.3791, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3781174596082321e-05, + "loss": 3.3928, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772788648571801e-05, + "loss": 3.3836, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8653323650360107, + "eval_runtime": 304.245, + "eval_samples_per_second": 1254.223, + "eval_steps_per_second": 39.195, + "step": 2213272 + }, + { + "epoch": 0.0, + "learning_rate": 1.3764402701061283e-05, + "loss": 3.3946, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3756016753550763e-05, + "loss": 3.3827, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.374763080604024e-05, + "loss": 3.3888, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3739244858529721e-05, + "loss": 3.4011, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730875289822934e-05, + "loss": 3.3918, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3722489342312412e-05, + "loss": 3.4009, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3714103394801892e-05, + "loss": 3.3904, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705733826095104e-05, + "loss": 3.3882, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3697347878584584e-05, + "loss": 3.3772, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688961931074063e-05, + "loss": 3.3868, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3680575983563543e-05, + "loss": 3.3883, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3672190036053023e-05, + "loss": 3.3865, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663804088542504e-05, + "loss": 3.3947, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3655418141031984e-05, + "loss": 3.3703, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3647032193521464e-05, + "loss": 3.3801, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638662624814675e-05, + "loss": 3.3758, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3630276677304155e-05, + "loss": 3.3873, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621890729793635e-05, + "loss": 3.3819, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3613521161086846e-05, + "loss": 3.3842, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3605135213576326e-05, + "loss": 3.3895, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596749266065806e-05, + "loss": 3.3933, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3588363318555285e-05, + "loss": 3.3932, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579993749848496e-05, + "loss": 3.3868, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571607802337976e-05, + "loss": 3.3839, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3563221854827456e-05, + "loss": 3.3982, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554835907316938e-05, + "loss": 3.388, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3546466338610147e-05, + "loss": 3.3813, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3538080391099629e-05, + "loss": 3.3895, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529694443589109e-05, + "loss": 3.3776, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3521308496078589e-05, + "loss": 3.3811, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.35129389273718e-05, + "loss": 3.3927, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.350455297986128e-05, + "loss": 3.3856, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.349618341115449e-05, + "loss": 3.3927, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.348779746364397e-05, + "loss": 3.3978, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.347941151613345e-05, + "loss": 3.3817, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.347102556862293e-05, + "loss": 3.3897, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.346263962111241e-05, + "loss": 3.3963, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3454253673601892e-05, + "loss": 3.3731, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445867726091368e-05, + "loss": 3.3831, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437481778580848e-05, + "loss": 3.3692, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3429112209874062e-05, + "loss": 3.3773, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420726262363539e-05, + "loss": 3.3782, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.341234031485302e-05, + "loss": 3.3998, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.34039543673425e-05, + "loss": 3.3785, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395584798635713e-05, + "loss": 3.3829, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3387198851125191e-05, + "loss": 3.3841, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378812903614671e-05, + "loss": 3.3851, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3370426956104151e-05, + "loss": 3.3769, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3362057387397364e-05, + "loss": 3.3647, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353671439886842e-05, + "loss": 3.385, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3345285492376322e-05, + "loss": 3.3971, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336899544865802e-05, + "loss": 3.3886, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328529976159012e-05, + "loss": 3.376, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3320144028648492e-05, + "loss": 3.3804, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311758081137974e-05, + "loss": 3.3807, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3303372133627454e-05, + "loss": 3.3693, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3295002564920663e-05, + "loss": 3.3992, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286616617410145e-05, + "loss": 3.3695, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3278230669899625e-05, + "loss": 3.4019, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269844722389105e-05, + "loss": 3.3868, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3261475153682316e-05, + "loss": 3.3722, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3253089206171795e-05, + "loss": 3.3901, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244703258661275e-05, + "loss": 3.3834, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3236317311150755e-05, + "loss": 3.3709, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227947742443966e-05, + "loss": 3.3739, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219561794933446e-05, + "loss": 3.3975, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3211175847422926e-05, + "loss": 3.3771, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202806278716137e-05, + "loss": 3.3809, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3194420331205617e-05, + "loss": 3.3649, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3186034383695098e-05, + "loss": 3.3768, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177648436184578e-05, + "loss": 3.3806, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.316927886747779e-05, + "loss": 3.383, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.316089291996727e-05, + "loss": 3.3735, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3152506972456749e-05, + "loss": 3.3845, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3144121024946229e-05, + "loss": 3.3936, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.313575145623944e-05, + "loss": 3.3822, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.312736550872892e-05, + "loss": 3.3846, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.31189795612184e-05, + "loss": 3.3829, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.311059361370788e-05, + "loss": 3.3795, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.310222404500109e-05, + "loss": 3.3877, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.309383809749057e-05, + "loss": 3.3779, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3085452149980052e-05, + "loss": 3.3815, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3077066202469532e-05, + "loss": 3.3891, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068696633762741e-05, + "loss": 3.3803, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3060310686252223e-05, + "loss": 3.3615, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051924738741703e-05, + "loss": 3.3822, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043538791231183e-05, + "loss": 3.3795, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3035169222524394e-05, + "loss": 3.3783, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026783275013873e-05, + "loss": 3.3764, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3018397327503353e-05, + "loss": 3.3811, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3010011379992833e-05, + "loss": 3.3683, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001641811286044e-05, + "loss": 3.3736, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2993255863775524e-05, + "loss": 3.378, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984869916265006e-05, + "loss": 3.3873, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2976483968754486e-05, + "loss": 3.3845, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2968114400047695e-05, + "loss": 3.3905, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959728452537177e-05, + "loss": 3.3705, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2951342505026656e-05, + "loss": 3.3795, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942956557516136e-05, + "loss": 3.3789, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934586988809347e-05, + "loss": 3.3876, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2926201041298827e-05, + "loss": 3.3811, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917815093788307e-05, + "loss": 3.3857, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2909429146277787e-05, + "loss": 3.3814, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2901059577570998e-05, + "loss": 3.3775, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892673630060478e-05, + "loss": 3.3873, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.288428768254996e-05, + "loss": 3.3751, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875901735039436e-05, + "loss": 3.377, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867532166332649e-05, + "loss": 3.3816, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.285914621882213e-05, + "loss": 3.3745, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.285076027131161e-05, + "loss": 3.3749, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2842374323801087e-05, + "loss": 3.3774, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2834004755094301e-05, + "loss": 3.3698, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.282561880758378e-05, + "loss": 3.3811, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.281723286007326e-05, + "loss": 3.3863, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808846912562739e-05, + "loss": 3.3723, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800477343855952e-05, + "loss": 3.3887, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2792091396345431e-05, + "loss": 3.3946, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.278370544883491e-05, + "loss": 3.3781, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.277531950132439e-05, + "loss": 3.3811, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766949932617602e-05, + "loss": 3.3792, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2758563985107084e-05, + "loss": 3.3768, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.275017803759656e-05, + "loss": 3.3761, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.274179209008604e-05, + "loss": 3.3765, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2733422521379255e-05, + "loss": 3.3767, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2725036573868734e-05, + "loss": 3.3849, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716650626358213e-05, + "loss": 3.3792, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2708281057651425e-05, + "loss": 3.3778, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699895110140905e-05, + "loss": 3.3787, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691509162630383e-05, + "loss": 3.3784, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2683123215119863e-05, + "loss": 3.3721, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674753646413076e-05, + "loss": 3.3899, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2666367698902556e-05, + "loss": 3.3898, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657981751392034e-05, + "loss": 3.3799, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649595803881514e-05, + "loss": 3.3767, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2641226235174727e-05, + "loss": 3.3838, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632840287664208e-05, + "loss": 3.3755, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2624454340153685e-05, + "loss": 3.3797, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2616068392643165e-05, + "loss": 3.3792, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607698823936379e-05, + "loss": 3.3944, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2599312876425855e-05, + "loss": 3.3851, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590926928915337e-05, + "loss": 3.3868, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582540981404817e-05, + "loss": 3.3798, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.257417141269803e-05, + "loss": 3.3906, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565785465187508e-05, + "loss": 3.3784, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2557399517676988e-05, + "loss": 3.3759, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2549013570166468e-05, + "loss": 3.3833, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540644001459679e-05, + "loss": 3.3691, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2532258053949158e-05, + "loss": 3.3843, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523872106438638e-05, + "loss": 3.3684, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8668365478515625, + "eval_runtime": 305.3161, + "eval_samples_per_second": 1249.823, + "eval_steps_per_second": 39.058, + "step": 2289592 + }, + { + "epoch": 0.0, + "learning_rate": 1.2515486158928118e-05, + "loss": 3.3883, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.25071002114176e-05, + "loss": 3.376, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2498714263907078e-05, + "loss": 3.3759, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2490328316396558e-05, + "loss": 3.3933, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.248195874768977e-05, + "loss": 3.382, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.247357280017925e-05, + "loss": 3.3911, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2465186852668729e-05, + "loss": 3.3798, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2456817283961941e-05, + "loss": 3.3762, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2448431336451421e-05, + "loss": 3.3733, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2440045388940901e-05, + "loss": 3.3779, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2431659441430381e-05, + "loss": 3.3756, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2423273493919861e-05, + "loss": 3.3771, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2414887546409341e-05, + "loss": 3.3856, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2406501598898821e-05, + "loss": 3.3654, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2398115651388301e-05, + "loss": 3.3679, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2389746082681512e-05, + "loss": 3.3667, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2381360135170992e-05, + "loss": 3.3727, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2372974187660472e-05, + "loss": 3.3755, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2364588240149952e-05, + "loss": 3.3759, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2356218671443164e-05, + "loss": 3.3793, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2347832723932643e-05, + "loss": 3.3847, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2339446776422122e-05, + "loss": 3.381, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2331077207715335e-05, + "loss": 3.3784, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2322691260204815e-05, + "loss": 3.3714, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2314305312694293e-05, + "loss": 3.3907, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2305919365183773e-05, + "loss": 3.378, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2297549796476986e-05, + "loss": 3.3752, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2289163848966466e-05, + "loss": 3.3773, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2280777901455946e-05, + "loss": 3.3686, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2272391953945426e-05, + "loss": 3.3744, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2264022385238636e-05, + "loss": 3.3778, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2255636437728116e-05, + "loss": 3.3806, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2247266869021327e-05, + "loss": 3.38, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2238880921510807e-05, + "loss": 3.3871, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2230494974000289e-05, + "loss": 3.3742, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2222109026489767e-05, + "loss": 3.3812, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2213723078979247e-05, + "loss": 3.3845, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2205337131468727e-05, + "loss": 3.365, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2196951183958207e-05, + "loss": 3.3723, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2188565236447687e-05, + "loss": 3.3596, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.21801956677409e-05, + "loss": 3.3724, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.217180972023038e-05, + "loss": 3.3683, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2163423772719857e-05, + "loss": 3.3889, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.2155037825209337e-05, + "loss": 3.368, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.214666825650255e-05, + "loss": 3.371, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.213828230899203e-05, + "loss": 3.3756, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2129896361481508e-05, + "loss": 3.3758, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.212151041397099e-05, + "loss": 3.3696, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.21131408452642e-05, + "loss": 3.3522, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.210475489775368e-05, + "loss": 3.3772, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.209636895024316e-05, + "loss": 3.3859, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.208798300273264e-05, + "loss": 3.3798, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2079613434025853e-05, + "loss": 3.3693, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2071227486515331e-05, + "loss": 3.3658, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2062841539004811e-05, + "loss": 3.3758, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2054455591494291e-05, + "loss": 3.3592, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2046086022787504e-05, + "loss": 3.3864, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2037700075276982e-05, + "loss": 3.3604, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2029314127766462e-05, + "loss": 3.3918, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2020928180255943e-05, + "loss": 3.379, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2012558611549153e-05, + "loss": 3.3606, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2004172664038634e-05, + "loss": 3.3792, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1995786716528114e-05, + "loss": 3.3778, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1987400769017594e-05, + "loss": 3.3607, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1979031200310805e-05, + "loss": 3.3652, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1970645252800285e-05, + "loss": 3.3852, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962259305289765e-05, + "loss": 3.3722, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1953873357779245e-05, + "loss": 3.3698, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1945503789072456e-05, + "loss": 3.3539, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1937117841561935e-05, + "loss": 3.3696, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1928731894051415e-05, + "loss": 3.3657, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1920345946540895e-05, + "loss": 3.3762, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1911976377834106e-05, + "loss": 3.3623, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1903590430323588e-05, + "loss": 3.3752, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1895204482813066e-05, + "loss": 3.3786, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1886834914106277e-05, + "loss": 3.3749, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1878448966595759e-05, + "loss": 3.3726, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1870063019085238e-05, + "loss": 3.3716, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1861677071574717e-05, + "loss": 3.3732, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.185330750286793e-05, + "loss": 3.377, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.184492155535741e-05, + "loss": 3.3687, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1836535607846889e-05, + "loss": 3.3729, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1828149660336369e-05, + "loss": 3.3714, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.181978009162958e-05, + "loss": 3.3714, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.181139414411906e-05, + "loss": 3.3534, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.180300819660854e-05, + "loss": 3.3729, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.179462224909802e-05, + "loss": 3.3693, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.178625268039123e-05, + "loss": 3.3722, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1777866732880712e-05, + "loss": 3.3672, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.176948078537019e-05, + "loss": 3.3718, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.176109483785967e-05, + "loss": 3.363, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1752725269152883e-05, + "loss": 3.3611, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1744339321642363e-05, + "loss": 3.3661, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1735953374131841e-05, + "loss": 3.379, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1727567426621323e-05, + "loss": 3.3693, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1719197857914534e-05, + "loss": 3.3792, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1710811910404012e-05, + "loss": 3.3642, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1702425962893493e-05, + "loss": 3.3678, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1694040015382973e-05, + "loss": 3.3654, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1685670446676184e-05, + "loss": 3.3794, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1677284499165664e-05, + "loss": 3.3691, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1668898551655144e-05, + "loss": 3.3757, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1660512604144624e-05, + "loss": 3.3677, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1652143035437837e-05, + "loss": 3.3668, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1643757087927315e-05, + "loss": 3.3808, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1635371140416795e-05, + "loss": 3.362, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1626985192906276e-05, + "loss": 3.3651, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1618615624199486e-05, + "loss": 3.3706, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1610229676688965e-05, + "loss": 3.3659, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1601843729178447e-05, + "loss": 3.3685, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1593457781667927e-05, + "loss": 3.3715, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1585088212961138e-05, + "loss": 3.357, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1576702265450618e-05, + "loss": 3.3748, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1568316317940098e-05, + "loss": 3.3727, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1559930370429576e-05, + "loss": 3.3681, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1551560801722789e-05, + "loss": 3.3795, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1543174854212268e-05, + "loss": 3.3855, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1534788906701748e-05, + "loss": 3.3695, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1526402959191228e-05, + "loss": 3.3705, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.151803339048444e-05, + "loss": 3.366, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1509647442973919e-05, + "loss": 3.3699, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.15012614954634e-05, + "loss": 3.3627, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1492875547952879e-05, + "loss": 3.368, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1484505979246092e-05, + "loss": 3.3647, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1476120031735572e-05, + "loss": 3.3767, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.146773408422505e-05, + "loss": 3.3686, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.145934813671453e-05, + "loss": 3.3702, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1450978568007742e-05, + "loss": 3.3705, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1442592620497222e-05, + "loss": 3.368, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.14342066729867e-05, + "loss": 3.361, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1425820725476182e-05, + "loss": 3.3802, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1417451156769393e-05, + "loss": 3.3812, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1409065209258873e-05, + "loss": 3.3748, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1400679261748353e-05, + "loss": 3.3654, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1392293314237833e-05, + "loss": 3.3704, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1383923745531044e-05, + "loss": 3.368, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1375537798020523e-05, + "loss": 3.3716, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1367151850510003e-05, + "loss": 3.3716, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1358765902999483e-05, + "loss": 3.3839, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1350396334292696e-05, + "loss": 3.3742, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1342010386782174e-05, + "loss": 3.3805, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1333624439271654e-05, + "loss": 3.3704, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1325238491761136e-05, + "loss": 3.3778, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1316868923054347e-05, + "loss": 3.3663, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1308482975543826e-05, + "loss": 3.3674, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1300097028033306e-05, + "loss": 3.376, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1291711080522786e-05, + "loss": 3.3587, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1283341511815997e-05, + "loss": 3.373, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1274955564305477e-05, + "loss": 3.3616, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.867471694946289, + "eval_runtime": 306.729, + "eval_samples_per_second": 1244.066, + "eval_steps_per_second": 38.878, + "step": 2365912 + }, + { + "epoch": 1.0, + "learning_rate": 1.1266569616794957e-05, + "loss": 3.3681, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.125820004808817e-05, + "loss": 3.3675, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1249814100577648e-05, + "loss": 3.3675, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1241428153067128e-05, + "loss": 3.3806, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1233042205556608e-05, + "loss": 3.3742, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1224672636849819e-05, + "loss": 3.3825, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1216286689339299e-05, + "loss": 3.3686, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1207917120632511e-05, + "loss": 3.3686, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1199531173121991e-05, + "loss": 3.3581, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.119114522561147e-05, + "loss": 3.3717, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1182759278100951e-05, + "loss": 3.3667, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.117437333059043e-05, + "loss": 3.3677, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1165987383079909e-05, + "loss": 3.3747, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1157601435569389e-05, + "loss": 3.3566, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.114921548805887e-05, + "loss": 3.3598, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1140845919352081e-05, + "loss": 3.3582, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1132459971841561e-05, + "loss": 3.3588, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1124074024331041e-05, + "loss": 3.3647, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1115688076820521e-05, + "loss": 3.3689, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.1107318508113732e-05, + "loss": 3.3615, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1098932560603212e-05, + "loss": 3.3813, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1090546613092692e-05, + "loss": 3.3696, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.1082177044385905e-05, + "loss": 3.3693, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1073791096875383e-05, + "loss": 3.3664, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1065405149364863e-05, + "loss": 3.379, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1057019201854343e-05, + "loss": 3.3651, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1048649633147555e-05, + "loss": 3.3706, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1040263685637033e-05, + "loss": 3.3621, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1031877738126515e-05, + "loss": 3.3674, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.1023491790615995e-05, + "loss": 3.364, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1015122221909206e-05, + "loss": 3.3654, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1006736274398686e-05, + "loss": 3.3721, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0998366705691897e-05, + "loss": 3.3716, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0989980758181377e-05, + "loss": 3.3735, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0981594810670856e-05, + "loss": 3.3665, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0973208863160336e-05, + "loss": 3.3716, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0964822915649816e-05, + "loss": 3.3696, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0956436968139296e-05, + "loss": 3.3577, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0948051020628776e-05, + "loss": 3.3646, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0939665073118256e-05, + "loss": 3.3506, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0931295504411467e-05, + "loss": 3.3615, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0922909556900947e-05, + "loss": 3.3549, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0914523609390427e-05, + "loss": 3.3777, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0906137661879907e-05, + "loss": 3.363, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.089776809317312e-05, + "loss": 3.3579, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0889382145662598e-05, + "loss": 3.3671, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0880996198152078e-05, + "loss": 3.3667, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.087261025064156e-05, + "loss": 3.3588, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.086424068193477e-05, + "loss": 3.3407, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.085585473442425e-05, + "loss": 3.3638, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.084746878691373e-05, + "loss": 3.3771, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.083908283940321e-05, + "loss": 3.3702, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.083071327069642e-05, + "loss": 3.362, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.08223273231859e-05, + "loss": 3.3541, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.081394137567538e-05, + "loss": 3.3667, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.080555542816486e-05, + "loss": 3.3511, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0797185859458071e-05, + "loss": 3.3758, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0788816290751282e-05, + "loss": 3.3493, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0780430343240764e-05, + "loss": 3.3828, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0772044395730244e-05, + "loss": 3.3684, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0763658448219722e-05, + "loss": 3.3546, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0755272500709202e-05, + "loss": 3.367, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0746886553198684e-05, + "loss": 3.3695, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0738500605688162e-05, + "loss": 3.3475, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0730131036981374e-05, + "loss": 3.3561, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0721745089470854e-05, + "loss": 3.3774, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0713359141960334e-05, + "loss": 3.3616, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0704973194449813e-05, + "loss": 3.3582, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0696603625743025e-05, + "loss": 3.3502, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0688217678232505e-05, + "loss": 3.3595, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0679831730721985e-05, + "loss": 3.352, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0671445783211465e-05, + "loss": 3.3687, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0663076214504676e-05, + "loss": 3.3533, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0654690266994156e-05, + "loss": 3.3672, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0646304319483636e-05, + "loss": 3.3678, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0637918371973116e-05, + "loss": 3.3679, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0629548803266328e-05, + "loss": 3.3625, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0621162855755806e-05, + "loss": 3.3613, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0612776908245286e-05, + "loss": 3.3643, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.0604390960734766e-05, + "loss": 3.3669, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0596021392027979e-05, + "loss": 3.3608, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0587635444517457e-05, + "loss": 3.3612, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.0579249497006939e-05, + "loss": 3.3622, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0570863549496419e-05, + "loss": 3.3642, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.056249398078963e-05, + "loss": 3.3446, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.055410803327911e-05, + "loss": 3.3593, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.054572208576859e-05, + "loss": 3.3606, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.053733613825807e-05, + "loss": 3.3605, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.052896656955128e-05, + "loss": 3.3593, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.052058062204076e-05, + "loss": 3.3593, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.051219467453024e-05, + "loss": 3.3563, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.050380872701972e-05, + "loss": 3.3508, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.049543915831293e-05, + "loss": 3.3555, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.048705321080241e-05, + "loss": 3.3681, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.047866726329189e-05, + "loss": 3.3625, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.047028131578137e-05, + "loss": 3.3687, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0461911747074581e-05, + "loss": 3.3559, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0453525799564063e-05, + "loss": 3.3604, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0445139852053543e-05, + "loss": 3.3554, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0436753904543021e-05, + "loss": 3.3679, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0428384335836234e-05, + "loss": 3.3597, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0419998388325714e-05, + "loss": 3.3694, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0411612440815194e-05, + "loss": 3.3567, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0403226493304674e-05, + "loss": 3.3555, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0394856924597884e-05, + "loss": 3.3742, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0386470977087364e-05, + "loss": 3.3526, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0378085029576844e-05, + "loss": 3.3556, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0369699082066324e-05, + "loss": 3.3623, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0361329513359535e-05, + "loss": 3.3605, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0352943565849017e-05, + "loss": 3.3527, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0344557618338495e-05, + "loss": 3.3632, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0336171670827975e-05, + "loss": 3.3513, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0327802102121187e-05, + "loss": 3.3603, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0319416154610667e-05, + "loss": 3.3653, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.0311030207100146e-05, + "loss": 3.3599, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0302644259589626e-05, + "loss": 3.3652, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0294274690882838e-05, + "loss": 3.3785, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0285888743372316e-05, + "loss": 3.3621, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0277502795861798e-05, + "loss": 3.3579, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0269116848351278e-05, + "loss": 3.3603, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0260747279644489e-05, + "loss": 3.3558, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0252361332133969e-05, + "loss": 3.359, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0243975384623449e-05, + "loss": 3.3571, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0235589437112929e-05, + "loss": 3.3566, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0227219868406141e-05, + "loss": 3.3666, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.021883392089562e-05, + "loss": 3.359, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.02104479733851e-05, + "loss": 3.3609, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0202078404678312e-05, + "loss": 3.3592, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.019369245716779e-05, + "loss": 3.3578, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.018530650965727e-05, + "loss": 3.3517, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0176920562146752e-05, + "loss": 3.3706, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0168550993439962e-05, + "loss": 3.3725, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.016016504592944e-05, + "loss": 3.3679, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0151779098418922e-05, + "loss": 3.3542, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.0143393150908402e-05, + "loss": 3.3582, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.0135023582201613e-05, + "loss": 3.3616, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0126637634691093e-05, + "loss": 3.3613, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0118251687180573e-05, + "loss": 3.3641, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.0109865739670053e-05, + "loss": 3.3725, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0101496170963264e-05, + "loss": 3.3624, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0093110223452744e-05, + "loss": 3.3718, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0084724275942224e-05, + "loss": 3.358, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0076338328431705e-05, + "loss": 3.3698, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0067968759724914e-05, + "loss": 3.3599, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0059582812214394e-05, + "loss": 3.3534, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0051196864703876e-05, + "loss": 3.3671, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0042810917193354e-05, + "loss": 3.3521, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0034441348486567e-05, + "loss": 3.3613, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0026055400976047e-05, + "loss": 3.3559, + "step": 2441728 + }, + { + "epoch": 1.03, + "eval_loss": 3.868337392807007, + "eval_runtime": 306.0542, + "eval_samples_per_second": 1246.809, + "eval_steps_per_second": 38.964, + "step": 2442232 + }, + { + "epoch": 0.0, + "learning_rate": 1.0017669453465527e-05, + "loss": 3.3331, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0009283505955005e-05, + "loss": 3.3583, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 1.0000897558444487e-05, + "loss": 3.357, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.992511610933966e-06, + "loss": 3.3706, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.984142042227176e-06, + "loss": 3.3638, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.975756094716657e-06, + "loss": 3.373, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.967370147206137e-06, + "loss": 3.3602, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.959000578499348e-06, + "loss": 3.3555, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.950614630988828e-06, + "loss": 3.3531, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.942228683478308e-06, + "loss": 3.3623, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.933842735967788e-06, + "loss": 3.3561, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.925456788457268e-06, + "loss": 3.3594, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.917070840946748e-06, + "loss": 3.3603, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.908684893436228e-06, + "loss": 3.3468, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.90031532472944e-06, + "loss": 3.3539, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.891929377218918e-06, + "loss": 3.352, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.883543429708398e-06, + "loss": 3.3461, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.875157482197878e-06, + "loss": 3.3575, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.866787913491091e-06, + "loss": 3.3558, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.858401965980569e-06, + "loss": 3.3547, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.850016018470049e-06, + "loss": 3.375, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.84163007095953e-06, + "loss": 3.3575, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.83326050225274e-06, + "loss": 3.3639, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.824874554742221e-06, + "loss": 3.3554, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.816488607231701e-06, + "loss": 3.3684, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.808102659721181e-06, + "loss": 3.3564, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.799733091014392e-06, + "loss": 3.3607, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.791347143503872e-06, + "loss": 3.3529, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.782961195993352e-06, + "loss": 3.3611, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.774575248482832e-06, + "loss": 3.3542, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.766205679776043e-06, + "loss": 3.3571, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.757819732265523e-06, + "loss": 3.3642, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.749450163558735e-06, + "loss": 3.3565, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.741064216048214e-06, + "loss": 3.3639, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.732678268537693e-06, + "loss": 3.3581, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.724292321027175e-06, + "loss": 3.3555, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.715906373516655e-06, + "loss": 3.3668, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.707520426006133e-06, + "loss": 3.3458, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.699134478495613e-06, + "loss": 3.3562, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.690748530985095e-06, + "loss": 3.3423, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.682378962278304e-06, + "loss": 3.3497, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.673993014767784e-06, + "loss": 3.3465, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.665607067257266e-06, + "loss": 3.3667, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.657221119746746e-06, + "loss": 3.3553, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.648851551039956e-06, + "loss": 3.3497, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.640465603529436e-06, + "loss": 3.3576, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.632079656018916e-06, + "loss": 3.3561, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.623693708508395e-06, + "loss": 3.3516, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.615324139801607e-06, + "loss": 3.3394, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.606938192291087e-06, + "loss": 3.3499, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.598552244780567e-06, + "loss": 3.3659, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.590166297270047e-06, + "loss": 3.3659, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.581796728563258e-06, + "loss": 3.3504, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.573410781052738e-06, + "loss": 3.3475, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.56502483354222e-06, + "loss": 3.3591, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.556638886031698e-06, + "loss": 3.3417, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.54826931732491e-06, + "loss": 3.3623, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.539899748618121e-06, + "loss": 3.3413, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.5315138011076e-06, + "loss": 3.37, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.52312785359708e-06, + "loss": 3.3641, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.51474190608656e-06, + "loss": 3.3473, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.50635595857604e-06, + "loss": 3.3546, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.49797001106552e-06, + "loss": 3.3646, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.489584063555e-06, + "loss": 3.338, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.481214494848211e-06, + "loss": 3.3441, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.472828547337691e-06, + "loss": 3.3672, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.464442599827171e-06, + "loss": 3.3546, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.456056652316651e-06, + "loss": 3.3514, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.447687083609864e-06, + "loss": 3.3409, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.439301136099342e-06, + "loss": 3.3462, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.430915188588822e-06, + "loss": 3.3439, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.422529241078302e-06, + "loss": 3.3597, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.414159672371514e-06, + "loss": 3.3434, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.405773724860993e-06, + "loss": 3.3606, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.397387777350473e-06, + "loss": 3.3564, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.389001829839954e-06, + "loss": 3.3626, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.380632261133165e-06, + "loss": 3.3515, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.372246313622645e-06, + "loss": 3.3521, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.363860366112125e-06, + "loss": 3.3565, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.355474418601605e-06, + "loss": 3.3569, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.347104849894816e-06, + "loss": 3.3537, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.338718902384296e-06, + "loss": 3.3498, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.330332954873776e-06, + "loss": 3.3536, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.321947007363256e-06, + "loss": 3.3527, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.313577438656466e-06, + "loss": 3.341, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.305191491145946e-06, + "loss": 3.3459, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.296805543635426e-06, + "loss": 3.3513, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.288419596124906e-06, + "loss": 3.3552, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.280050027418117e-06, + "loss": 3.3452, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.271664079907599e-06, + "loss": 3.3525, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.263278132397079e-06, + "loss": 3.3464, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.254892184886557e-06, + "loss": 3.3417, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.24652261617977e-06, + "loss": 3.3456, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.23813666866925e-06, + "loss": 3.3559, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.229750721158728e-06, + "loss": 3.3541, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.221364773648208e-06, + "loss": 3.3596, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.21299520494142e-06, + "loss": 3.3555, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.2046092574309e-06, + "loss": 3.3455, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.19622330992038e-06, + "loss": 3.3486, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.18783736240986e-06, + "loss": 3.355, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.17946779370307e-06, + "loss": 3.3537, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.171081846192552e-06, + "loss": 3.3618, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.16269589868203e-06, + "loss": 3.3475, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.15430995117151e-06, + "loss": 3.3426, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.145940382464723e-06, + "loss": 3.3665, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.137554434954201e-06, + "loss": 3.342, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.129168487443681e-06, + "loss": 3.3488, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.120782539933161e-06, + "loss": 3.3512, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.112412971226374e-06, + "loss": 3.3529, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.104027023715852e-06, + "loss": 3.3431, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.095641076205334e-06, + "loss": 3.3494, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.087255128694814e-06, + "loss": 3.3446, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.078885559988024e-06, + "loss": 3.3551, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.070499612477504e-06, + "loss": 3.3515, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.062113664966984e-06, + "loss": 3.3476, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.053727717456464e-06, + "loss": 3.3586, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.045358148749675e-06, + "loss": 3.3665, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.036972201239155e-06, + "loss": 3.3563, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.028586253728635e-06, + "loss": 3.35, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.020200306218115e-06, + "loss": 3.3499, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.011830737511326e-06, + "loss": 3.3433, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 9.003444790000806e-06, + "loss": 3.3508, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.995058842490287e-06, + "loss": 3.3496, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.986672894979766e-06, + "loss": 3.3472, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.978303326272976e-06, + "loss": 3.3519, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.969917378762458e-06, + "loss": 3.3518, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.961531431251938e-06, + "loss": 3.3512, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.953161862545149e-06, + "loss": 3.348, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.944775915034629e-06, + "loss": 3.3476, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.936389967524109e-06, + "loss": 3.3446, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.928004020013589e-06, + "loss": 3.3614, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.9196344513068e-06, + "loss": 3.3615, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.91124850379628e-06, + "loss": 3.3602, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.90286255628576e-06, + "loss": 3.3413, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.89447660877524e-06, + "loss": 3.3525, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.88610704006845e-06, + "loss": 3.3506, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.87772109255793e-06, + "loss": 3.3552, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.869335145047412e-06, + "loss": 3.3482, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.86094919753689e-06, + "loss": 3.3645, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.852579628830102e-06, + "loss": 3.3524, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.844193681319582e-06, + "loss": 3.3657, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.835807733809062e-06, + "loss": 3.3462, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.82742178629854e-06, + "loss": 3.362, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.819052217591753e-06, + "loss": 3.3496, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.810666270081233e-06, + "loss": 3.346, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.802280322570711e-06, + "loss": 3.3566, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.793894375060193e-06, + "loss": 3.3449, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.785524806353404e-06, + "loss": 3.3512, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.777138858842884e-06, + "loss": 3.3488, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.768752911332364e-06, + "loss": 3.3476, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.868732452392578, + "eval_runtime": 304.4372, + "eval_samples_per_second": 1253.431, + "eval_steps_per_second": 39.171, + "step": 2518552 + }, + { + "epoch": 1.0, + "learning_rate": 8.760366963821844e-06, + "loss": 3.3494, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.751997395115056e-06, + "loss": 3.352, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.743611447604536e-06, + "loss": 3.3604, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.735225500094014e-06, + "loss": 3.352, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.726839552583494e-06, + "loss": 3.3686, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.718469983876707e-06, + "loss": 3.3481, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.710100415169918e-06, + "loss": 3.347, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.701714467659397e-06, + "loss": 3.3431, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.693328520148877e-06, + "loss": 3.3536, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.684942572638357e-06, + "loss": 3.348, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.676556625127837e-06, + "loss": 3.3474, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.668170677617317e-06, + "loss": 3.3551, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.659784730106797e-06, + "loss": 3.3366, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.651398782596276e-06, + "loss": 3.3491, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.643029213889488e-06, + "loss": 3.3414, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.634643266378968e-06, + "loss": 3.3416, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.626257318868448e-06, + "loss": 3.3456, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.617871371357928e-06, + "loss": 3.3449, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.609501802651139e-06, + "loss": 3.3476, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.601115855140619e-06, + "loss": 3.3676, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.592729907630099e-06, + "loss": 3.3465, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.584343960119579e-06, + "loss": 3.3501, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.575974391412791e-06, + "loss": 3.3479, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.567588443902271e-06, + "loss": 3.3546, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.55920249639175e-06, + "loss": 3.3482, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.55081654888123e-06, + "loss": 3.3546, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.542446980174442e-06, + "loss": 3.3436, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.534061032663922e-06, + "loss": 3.3516, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.5256750851534e-06, + "loss": 3.3396, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.517289137642882e-06, + "loss": 3.3489, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.508919568936092e-06, + "loss": 3.3537, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.500550000229305e-06, + "loss": 3.3503, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.492164052718783e-06, + "loss": 3.3568, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.483778105208263e-06, + "loss": 3.3482, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.475392157697743e-06, + "loss": 3.348, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.467006210187223e-06, + "loss": 3.3557, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.458620262676703e-06, + "loss": 3.3414, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.450234315166183e-06, + "loss": 3.3465, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.441848367655663e-06, + "loss": 3.3342, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.433478798948874e-06, + "loss": 3.341, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.425092851438354e-06, + "loss": 3.3424, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.416706903927835e-06, + "loss": 3.3564, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.408320956417313e-06, + "loss": 3.3472, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.399951387710526e-06, + "loss": 3.3397, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.391565440200006e-06, + "loss": 3.3517, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.383179492689486e-06, + "loss": 3.3462, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.374793545178964e-06, + "loss": 3.3423, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.366423976472177e-06, + "loss": 3.3303, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.358038028961657e-06, + "loss": 3.3404, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.349652081451135e-06, + "loss": 3.3573, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.341266133940616e-06, + "loss": 3.3561, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.332896565233827e-06, + "loss": 3.3368, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.324510617723307e-06, + "loss": 3.3433, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.316124670212787e-06, + "loss": 3.3485, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.307738722702267e-06, + "loss": 3.3314, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.299369153995478e-06, + "loss": 3.3541, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.29099958528869e-06, + "loss": 3.3347, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.282613637778169e-06, + "loss": 3.3595, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.27422769026765e-06, + "loss": 3.351, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.26584174275713e-06, + "loss": 3.3415, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.257455795246609e-06, + "loss": 3.3413, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.249069847736088e-06, + "loss": 3.3561, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.24068390022557e-06, + "loss": 3.3261, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.23229795271505e-06, + "loss": 3.3378, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.223928384008261e-06, + "loss": 3.3583, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.21554243649774e-06, + "loss": 3.3455, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.20715648898722e-06, + "loss": 3.3419, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.198786920280432e-06, + "loss": 3.3296, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.190400972769912e-06, + "loss": 3.3389, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.182015025259392e-06, + "loss": 3.3379, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.173629077748871e-06, + "loss": 3.3456, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.165259509042082e-06, + "loss": 3.3376, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.156873561531562e-06, + "loss": 3.351, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.148487614021042e-06, + "loss": 3.3473, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.140101666510524e-06, + "loss": 3.3527, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.131732097803733e-06, + "loss": 3.3394, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.123346150293215e-06, + "loss": 3.344, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.114960202782695e-06, + "loss": 3.3472, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.106574255272173e-06, + "loss": 3.349, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.098204686565385e-06, + "loss": 3.3466, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.089818739054865e-06, + "loss": 3.3396, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.081432791544345e-06, + "loss": 3.3465, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.073046844033823e-06, + "loss": 3.3414, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.064677275327036e-06, + "loss": 3.3301, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.056291327816516e-06, + "loss": 3.3361, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.047905380305996e-06, + "loss": 3.3432, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.039519432795476e-06, + "loss": 3.3496, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.031149864088687e-06, + "loss": 3.3391, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.022763916578167e-06, + "loss": 3.3422, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.014377969067646e-06, + "loss": 3.3354, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.005992021557126e-06, + "loss": 3.3323, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.997622452850339e-06, + "loss": 3.3341, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.989236505339819e-06, + "loss": 3.3456, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.980850557829297e-06, + "loss": 3.346, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.972464610318777e-06, + "loss": 3.3484, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.96409504161199e-06, + "loss": 3.3477, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.955709094101468e-06, + "loss": 3.3366, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.94732314659095e-06, + "loss": 3.3403, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.93893719908043e-06, + "loss": 3.3426, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.93056763037364e-06, + "loss": 3.347, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.92218168286312e-06, + "loss": 3.3476, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.9137957353526e-06, + "loss": 3.3408, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.90540978784208e-06, + "loss": 3.3368, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.897040219135293e-06, + "loss": 3.3587, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.888654271624771e-06, + "loss": 3.3316, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.88026832411425e-06, + "loss": 3.3427, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.87188237660373e-06, + "loss": 3.3408, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.863512807896942e-06, + "loss": 3.3444, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.855126860386422e-06, + "loss": 3.3321, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.846740912875901e-06, + "loss": 3.3432, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.838354965365383e-06, + "loss": 3.3334, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.829985396658592e-06, + "loss": 3.3431, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.821599449148074e-06, + "loss": 3.3435, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.813213501637554e-06, + "loss": 3.3361, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.804827554127032e-06, + "loss": 3.351, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.796457985420245e-06, + "loss": 3.3582, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.788072037909725e-06, + "loss": 3.345, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.779686090399204e-06, + "loss": 3.3401, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.771316521692415e-06, + "loss": 3.3424, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.762930574181895e-06, + "loss": 3.3365, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.754544626671375e-06, + "loss": 3.3383, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.746158679160855e-06, + "loss": 3.3455, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.737789110454066e-06, + "loss": 3.335, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.729403162943546e-06, + "loss": 3.3412, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.721033594236758e-06, + "loss": 3.3451, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.712647646726238e-06, + "loss": 3.3439, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.704261699215717e-06, + "loss": 3.3346, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.695875751705198e-06, + "loss": 3.3392, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.687489804194678e-06, + "loss": 3.3423, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.679103856684156e-06, + "loss": 3.3438, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.670717909173636e-06, + "loss": 3.3526, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.662331961663118e-06, + "loss": 3.3502, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.653962392956329e-06, + "loss": 3.3346, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.645576445445809e-06, + "loss": 3.3439, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.637190497935289e-06, + "loss": 3.3442, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.628804550424769e-06, + "loss": 3.3432, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.620434981717979e-06, + "loss": 3.3415, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.6120490342074595e-06, + "loss": 3.3529, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.603663086696939e-06, + "loss": 3.3423, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.59527713918642e-06, + "loss": 3.3583, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.58690757047963e-06, + "loss": 3.3393, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.578521622969111e-06, + "loss": 3.3505, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.570135675458591e-06, + "loss": 3.3432, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.56174972794807e-06, + "loss": 3.3373, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.553380159241282e-06, + "loss": 3.3466, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.544994211730762e-06, + "loss": 3.34, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.5366082642202424e-06, + "loss": 3.3377, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.528222316709721e-06, + "loss": 3.3372, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.519852748002932e-06, + "loss": 3.3375, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.869279623031616, + "eval_runtime": 305.0926, + "eval_samples_per_second": 1250.738, + "eval_steps_per_second": 39.086, + "step": 2594872 + }, + { + "epoch": 0.0, + "learning_rate": 7.511466800492413e-06, + "loss": 3.3412, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.503080852981893e-06, + "loss": 3.3408, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.494694905471372e-06, + "loss": 3.3523, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.486308957960852e-06, + "loss": 3.3421, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.477939389254064e-06, + "loss": 3.3589, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.469553441743543e-06, + "loss": 3.341, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.4611838730367545e-06, + "loss": 3.3412, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.452797925526235e-06, + "loss": 3.3312, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.444411978015715e-06, + "loss": 3.3479, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.436026030505194e-06, + "loss": 3.3402, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.427640082994674e-06, + "loss": 3.3355, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.419254135484155e-06, + "loss": 3.3509, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.410868187973634e-06, + "loss": 3.3241, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.402482240463114e-06, + "loss": 3.3421, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.394112671756326e-06, + "loss": 3.3279, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.385726724245806e-06, + "loss": 3.3342, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.377340776735285e-06, + "loss": 3.3325, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.3689712080284966e-06, + "loss": 3.3389, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.360585260517977e-06, + "loss": 3.3343, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.352199313007456e-06, + "loss": 3.3575, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.3438133654969364e-06, + "loss": 3.3399, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.335443796790148e-06, + "loss": 3.3413, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.327057849279628e-06, + "loss": 3.3378, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.318671901769107e-06, + "loss": 3.3489, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.310285954258587e-06, + "loss": 3.3377, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.301916385551799e-06, + "loss": 3.3485, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.2935304380412795e-06, + "loss": 3.3318, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.285144490530759e-06, + "loss": 3.3394, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.276758543020239e-06, + "loss": 3.3291, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.26838897431345e-06, + "loss": 3.3449, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.260003026802929e-06, + "loss": 3.3428, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.251633458096141e-06, + "loss": 3.3405, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.243247510585621e-06, + "loss": 3.3503, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.234861563075102e-06, + "loss": 3.3398, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.226475615564581e-06, + "loss": 3.3368, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.218089668054061e-06, + "loss": 3.3432, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.209703720543541e-06, + "loss": 3.3358, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.20131777303302e-06, + "loss": 3.3326, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.192931825522501e-06, + "loss": 3.3266, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.184562256815712e-06, + "loss": 3.3292, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.176176309305192e-06, + "loss": 3.3316, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.167790361794671e-06, + "loss": 3.3453, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.159404414284151e-06, + "loss": 3.3406, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.151034845577363e-06, + "loss": 3.3296, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.142648898066844e-06, + "loss": 3.3453, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.134262950556322e-06, + "loss": 3.3338, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.125877003045803e-06, + "loss": 3.3307, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.1175074343390145e-06, + "loss": 3.3265, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.1091214868284936e-06, + "loss": 3.3253, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.1007355393179735e-06, + "loss": 3.3515, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.092349591807454e-06, + "loss": 3.3478, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.083980023100666e-06, + "loss": 3.3306, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.075594075590144e-06, + "loss": 3.332, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.067208128079625e-06, + "loss": 3.3393, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.058822180569105e-06, + "loss": 3.3214, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.050452611862317e-06, + "loss": 3.3442, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.042083043155527e-06, + "loss": 3.3253, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.033697095645007e-06, + "loss": 3.3475, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.025311148134487e-06, + "loss": 3.3466, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.0169252006239664e-06, + "loss": 3.3335, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.008539253113447e-06, + "loss": 3.3309, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 7.000153305602927e-06, + "loss": 3.347, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.991767358092407e-06, + "loss": 3.3188, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.983381410581886e-06, + "loss": 3.3338, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.975011841875098e-06, + "loss": 3.3436, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.966625894364579e-06, + "loss": 3.3391, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.958239946854058e-06, + "loss": 3.332, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.949853999343538e-06, + "loss": 3.3238, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.941484430636749e-06, + "loss": 3.3274, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.933098483126229e-06, + "loss": 3.329, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.9247125356157085e-06, + "loss": 3.336, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.916326588105189e-06, + "loss": 3.3256, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.907957019398401e-06, + "loss": 3.3432, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.899571071887881e-06, + "loss": 3.3387, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.89118512437736e-06, + "loss": 3.345, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.88279917686684e-06, + "loss": 3.3275, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.8744296081600516e-06, + "loss": 3.3346, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.866043660649531e-06, + "loss": 3.3393, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.857657713139011e-06, + "loss": 3.3371, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.849288144432222e-06, + "loss": 3.3403, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.840902196921703e-06, + "loss": 3.3342, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.832516249411182e-06, + "loss": 3.3321, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.824130301900662e-06, + "loss": 3.3334, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.815760733193874e-06, + "loss": 3.3218, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.8073747856833546e-06, + "loss": 3.3301, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.798988838172833e-06, + "loss": 3.3315, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.790602890662314e-06, + "loss": 3.3404, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.782233321955525e-06, + "loss": 3.3287, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.773847374445004e-06, + "loss": 3.3336, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.765461426934484e-06, + "loss": 3.3264, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.757075479423964e-06, + "loss": 3.3247, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.748705910717176e-06, + "loss": 3.3239, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.740319963206655e-06, + "loss": 3.3332, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.731934015696136e-06, + "loss": 3.3431, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.723548068185616e-06, + "loss": 3.34, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.715178499478826e-06, + "loss": 3.3354, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.7067925519683065e-06, + "loss": 3.3286, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.6984066044577865e-06, + "loss": 3.3318, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.690020656947267e-06, + "loss": 3.3313, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.681651088240477e-06, + "loss": 3.3416, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.673265140729957e-06, + "loss": 3.3373, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.664879193219438e-06, + "loss": 3.3337, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.656493245708917e-06, + "loss": 3.3243, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.648123677002129e-06, + "loss": 3.3472, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.639737729491609e-06, + "loss": 3.3249, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.6313517819810895e-06, + "loss": 3.3359, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.622965834470568e-06, + "loss": 3.33, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.614596265763779e-06, + "loss": 3.3319, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.60621031825326e-06, + "loss": 3.3277, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.59782437074274e-06, + "loss": 3.336, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.589438423232219e-06, + "loss": 3.3255, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.581068854525431e-06, + "loss": 3.3291, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.572682907014911e-06, + "loss": 3.3401, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.56429695950439e-06, + "loss": 3.3233, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.555911011993871e-06, + "loss": 3.3462, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.547541443287082e-06, + "loss": 3.3477, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.539155495776562e-06, + "loss": 3.3378, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.5307695482660415e-06, + "loss": 3.3283, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.5223836007555214e-06, + "loss": 3.3332, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.514014032048733e-06, + "loss": 3.3294, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.505628084538214e-06, + "loss": 3.3278, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.497242137027693e-06, + "loss": 3.3358, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.488856189517173e-06, + "loss": 3.3264, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.480486620810385e-06, + "loss": 3.3345, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.472117052103596e-06, + "loss": 3.3377, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.463731104593075e-06, + "loss": 3.3327, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.455345157082555e-06, + "loss": 3.3275, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.446959209572036e-06, + "loss": 3.3309, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.438573262061514e-06, + "loss": 3.3347, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.430187314550995e-06, + "loss": 3.3328, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.421801367040475e-06, + "loss": 3.341, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.413431798333687e-06, + "loss": 3.3453, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.405045850823166e-06, + "loss": 3.3247, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.396659903312646e-06, + "loss": 3.3352, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.388273955802127e-06, + "loss": 3.3359, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.379888008291606e-06, + "loss": 3.3318, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.371502060781086e-06, + "loss": 3.3326, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.3631161132705665e-06, + "loss": 3.3437, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.354730165760045e-06, + "loss": 3.3366, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.346360597053256e-06, + "loss": 3.3481, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.337974649542737e-06, + "loss": 3.3323, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.329588702032217e-06, + "loss": 3.3372, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.321219133325428e-06, + "loss": 3.3358, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.312833185814908e-06, + "loss": 3.3316, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.304447238304388e-06, + "loss": 3.3338, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.296061290793869e-06, + "loss": 3.333, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.287675343283348e-06, + "loss": 3.3291, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.279305774576559e-06, + "loss": 3.3292, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.270919827066039e-06, + "loss": 3.3274, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.8690664768218994, + "eval_runtime": 312.7811, + "eval_samples_per_second": 1219.994, + "eval_steps_per_second": 38.126, + "step": 2671192 + }, + { + "epoch": 1.0, + "learning_rate": 6.2625338795555184e-06, + "loss": 3.3314, + "step": 2671616 + }, + { + "epoch": 1.0, + "learning_rate": 6.25416431084873e-06, + "loss": 3.3307, + "step": 2672128 + }, + { + "epoch": 1.0, + "learning_rate": 6.24577836333821e-06, + "loss": 3.3447, + "step": 2672640 + }, + { + "epoch": 1.0, + "learning_rate": 6.23739241582769e-06, + "loss": 3.3316, + "step": 2673152 + }, + { + "epoch": 1.0, + "learning_rate": 6.22900646831717e-06, + "loss": 3.3529, + "step": 2673664 + }, + { + "epoch": 1.0, + "learning_rate": 6.220636899610381e-06, + "loss": 3.3305, + "step": 2674176 + }, + { + "epoch": 1.0, + "learning_rate": 6.212267330903593e-06, + "loss": 3.3332, + "step": 2674688 + }, + { + "epoch": 1.0, + "learning_rate": 6.203881383393072e-06, + "loss": 3.3239, + "step": 2675200 + }, + { + "epoch": 1.0, + "learning_rate": 6.195495435882553e-06, + "loss": 3.335, + "step": 2675712 + }, + { + "epoch": 1.0, + "learning_rate": 6.187109488372032e-06, + "loss": 3.3322, + "step": 2676224 + }, + { + "epoch": 1.0, + "learning_rate": 6.178723540861512e-06, + "loss": 3.3245, + "step": 2676736 + }, + { + "epoch": 1.0, + "learning_rate": 6.170337593350992e-06, + "loss": 3.3377, + "step": 2677248 + }, + { + "epoch": 1.0, + "learning_rate": 6.161951645840472e-06, + "loss": 3.3188, + "step": 2677760 + }, + { + "epoch": 1.0, + "learning_rate": 6.153565698329952e-06, + "loss": 3.3307, + "step": 2678272 + }, + { + "epoch": 1.0, + "learning_rate": 6.145196129623163e-06, + "loss": 3.3245, + "step": 2678784 + }, + { + "epoch": 1.0, + "learning_rate": 6.136810182112644e-06, + "loss": 3.3228, + "step": 2679296 + }, + { + "epoch": 1.0, + "learning_rate": 6.128424234602123e-06, + "loss": 3.3206, + "step": 2679808 + }, + { + "epoch": 1.0, + "learning_rate": 6.120038287091603e-06, + "loss": 3.3279, + "step": 2680320 + }, + { + "epoch": 1.0, + "learning_rate": 6.111668718384814e-06, + "loss": 3.3292, + "step": 2680832 + }, + { + "epoch": 1.0, + "learning_rate": 6.103282770874294e-06, + "loss": 3.347, + "step": 2681344 + }, + { + "epoch": 1.0, + "learning_rate": 6.094896823363774e-06, + "loss": 3.3306, + "step": 2681856 + }, + { + "epoch": 1.0, + "learning_rate": 6.086527254656985e-06, + "loss": 3.3369, + "step": 2682368 + }, + { + "epoch": 1.0, + "learning_rate": 6.078141307146466e-06, + "loss": 3.3287, + "step": 2682880 + }, + { + "epoch": 1.0, + "learning_rate": 6.069755359635945e-06, + "loss": 3.3384, + "step": 2683392 + }, + { + "epoch": 1.0, + "learning_rate": 6.061369412125426e-06, + "loss": 3.3283, + "step": 2683904 + }, + { + "epoch": 1.0, + "learning_rate": 6.0529998434186366e-06, + "loss": 3.3397, + "step": 2684416 + }, + { + "epoch": 1.0, + "learning_rate": 6.0446138959081165e-06, + "loss": 3.3275, + "step": 2684928 + }, + { + "epoch": 1.0, + "learning_rate": 6.0362279483975965e-06, + "loss": 3.3273, + "step": 2685440 + }, + { + "epoch": 1.0, + "learning_rate": 6.0278420008870764e-06, + "loss": 3.3196, + "step": 2685952 + }, + { + "epoch": 1.01, + "learning_rate": 6.019472432180288e-06, + "loss": 3.3327, + "step": 2686464 + }, + { + "epoch": 1.01, + "learning_rate": 6.011086484669767e-06, + "loss": 3.3393, + "step": 2686976 + }, + { + "epoch": 1.01, + "learning_rate": 6.002716915962979e-06, + "loss": 3.3284, + "step": 2687488 + }, + { + "epoch": 1.01, + "learning_rate": 5.994330968452459e-06, + "loss": 3.3423, + "step": 2688000 + }, + { + "epoch": 1.01, + "learning_rate": 5.985945020941939e-06, + "loss": 3.3319, + "step": 2688512 + }, + { + "epoch": 1.01, + "learning_rate": 5.977559073431419e-06, + "loss": 3.3243, + "step": 2689024 + }, + { + "epoch": 1.01, + "learning_rate": 5.969173125920899e-06, + "loss": 3.3363, + "step": 2689536 + }, + { + "epoch": 1.01, + "learning_rate": 5.960787178410379e-06, + "loss": 3.3302, + "step": 2690048 + }, + { + "epoch": 1.01, + "learning_rate": 5.952401230899858e-06, + "loss": 3.3222, + "step": 2690560 + }, + { + "epoch": 1.01, + "learning_rate": 5.9440152833893385e-06, + "loss": 3.3185, + "step": 2691072 + }, + { + "epoch": 1.01, + "learning_rate": 5.935645714682549e-06, + "loss": 3.3185, + "step": 2691584 + }, + { + "epoch": 1.01, + "learning_rate": 5.927259767172029e-06, + "loss": 3.3279, + "step": 2692096 + }, + { + "epoch": 1.01, + "learning_rate": 5.918873819661509e-06, + "loss": 3.3331, + "step": 2692608 + }, + { + "epoch": 1.01, + "learning_rate": 5.910487872150989e-06, + "loss": 3.3329, + "step": 2693120 + }, + { + "epoch": 1.01, + "learning_rate": 5.902118303444201e-06, + "loss": 3.32, + "step": 2693632 + }, + { + "epoch": 1.01, + "learning_rate": 5.893732355933681e-06, + "loss": 3.3369, + "step": 2694144 + }, + { + "epoch": 1.01, + "learning_rate": 5.885346408423161e-06, + "loss": 3.3258, + "step": 2694656 + }, + { + "epoch": 1.01, + "learning_rate": 5.87696046091264e-06, + "loss": 3.3232, + "step": 2695168 + }, + { + "epoch": 1.01, + "learning_rate": 5.8685908922058515e-06, + "loss": 3.3136, + "step": 2695680 + }, + { + "epoch": 1.01, + "learning_rate": 5.8602049446953314e-06, + "loss": 3.3118, + "step": 2696192 + }, + { + "epoch": 1.01, + "learning_rate": 5.851818997184811e-06, + "loss": 3.3453, + "step": 2696704 + }, + { + "epoch": 1.01, + "learning_rate": 5.843433049674291e-06, + "loss": 3.3386, + "step": 2697216 + }, + { + "epoch": 1.01, + "learning_rate": 5.835063480967503e-06, + "loss": 3.3238, + "step": 2697728 + }, + { + "epoch": 1.01, + "learning_rate": 5.826677533456983e-06, + "loss": 3.3263, + "step": 2698240 + }, + { + "epoch": 1.01, + "learning_rate": 5.818291585946463e-06, + "loss": 3.3273, + "step": 2698752 + }, + { + "epoch": 1.01, + "learning_rate": 5.809905638435943e-06, + "loss": 3.3141, + "step": 2699264 + }, + { + "epoch": 1.01, + "learning_rate": 5.8015360697291545e-06, + "loss": 3.3325, + "step": 2699776 + }, + { + "epoch": 1.01, + "learning_rate": 5.793166501022365e-06, + "loss": 3.3206, + "step": 2700288 + }, + { + "epoch": 1.01, + "learning_rate": 5.784780553511845e-06, + "loss": 3.3336, + "step": 2700800 + }, + { + "epoch": 1.01, + "learning_rate": 5.776394606001325e-06, + "loss": 3.3432, + "step": 2701312 + }, + { + "epoch": 1.01, + "learning_rate": 5.768008658490804e-06, + "loss": 3.3254, + "step": 2701824 + }, + { + "epoch": 1.01, + "learning_rate": 5.759622710980285e-06, + "loss": 3.3203, + "step": 2702336 + }, + { + "epoch": 1.01, + "learning_rate": 5.751236763469764e-06, + "loss": 3.3417, + "step": 2702848 + }, + { + "epoch": 1.01, + "learning_rate": 5.742850815959244e-06, + "loss": 3.3116, + "step": 2703360 + }, + { + "epoch": 1.01, + "learning_rate": 5.734464868448725e-06, + "loss": 3.3187, + "step": 2703872 + }, + { + "epoch": 1.01, + "learning_rate": 5.726095299741936e-06, + "loss": 3.3382, + "step": 2704384 + }, + { + "epoch": 1.01, + "learning_rate": 5.717709352231416e-06, + "loss": 3.3318, + "step": 2704896 + }, + { + "epoch": 1.01, + "learning_rate": 5.709323404720896e-06, + "loss": 3.323, + "step": 2705408 + }, + { + "epoch": 1.01, + "learning_rate": 5.700937457210376e-06, + "loss": 3.3173, + "step": 2705920 + }, + { + "epoch": 1.01, + "learning_rate": 5.692567888503586e-06, + "loss": 3.3148, + "step": 2706432 + }, + { + "epoch": 1.01, + "learning_rate": 5.684181940993067e-06, + "loss": 3.3172, + "step": 2706944 + }, + { + "epoch": 1.01, + "learning_rate": 5.675795993482546e-06, + "loss": 3.3345, + "step": 2707456 + }, + { + "epoch": 1.01, + "learning_rate": 5.667410045972026e-06, + "loss": 3.3136, + "step": 2707968 + }, + { + "epoch": 1.01, + "learning_rate": 5.659040477265238e-06, + "loss": 3.3337, + "step": 2708480 + }, + { + "epoch": 1.01, + "learning_rate": 5.650654529754718e-06, + "loss": 3.3285, + "step": 2708992 + }, + { + "epoch": 1.01, + "learning_rate": 5.642268582244198e-06, + "loss": 3.3384, + "step": 2709504 + }, + { + "epoch": 1.01, + "learning_rate": 5.633899013537409e-06, + "loss": 3.3237, + "step": 2710016 + }, + { + "epoch": 1.01, + "learning_rate": 5.625513066026889e-06, + "loss": 3.3202, + "step": 2710528 + }, + { + "epoch": 1.01, + "learning_rate": 5.6171271185163685e-06, + "loss": 3.3295, + "step": 2711040 + }, + { + "epoch": 1.01, + "learning_rate": 5.608741171005849e-06, + "loss": 3.325, + "step": 2711552 + }, + { + "epoch": 1.01, + "learning_rate": 5.60037160229906e-06, + "loss": 3.3337, + "step": 2712064 + }, + { + "epoch": 1.01, + "learning_rate": 5.59198565478854e-06, + "loss": 3.3228, + "step": 2712576 + }, + { + "epoch": 1.01, + "learning_rate": 5.58359970727802e-06, + "loss": 3.324, + "step": 2713088 + }, + { + "epoch": 1.01, + "learning_rate": 5.5752137597675e-06, + "loss": 3.3284, + "step": 2713600 + }, + { + "epoch": 1.01, + "learning_rate": 5.566844191060712e-06, + "loss": 3.3113, + "step": 2714112 + }, + { + "epoch": 1.01, + "learning_rate": 5.558458243550191e-06, + "loss": 3.3215, + "step": 2714624 + }, + { + "epoch": 1.01, + "learning_rate": 5.5500722960396715e-06, + "loss": 3.3267, + "step": 2715136 + }, + { + "epoch": 1.01, + "learning_rate": 5.541686348529151e-06, + "loss": 3.3317, + "step": 2715648 + }, + { + "epoch": 1.01, + "learning_rate": 5.533316779822362e-06, + "loss": 3.3199, + "step": 2716160 + }, + { + "epoch": 1.01, + "learning_rate": 5.524930832311842e-06, + "loss": 3.3256, + "step": 2716672 + }, + { + "epoch": 1.02, + "learning_rate": 5.516544884801322e-06, + "loss": 3.3148, + "step": 2717184 + }, + { + "epoch": 1.02, + "learning_rate": 5.508158937290802e-06, + "loss": 3.3174, + "step": 2717696 + }, + { + "epoch": 1.02, + "learning_rate": 5.499789368584014e-06, + "loss": 3.3158, + "step": 2718208 + }, + { + "epoch": 1.02, + "learning_rate": 5.491403421073493e-06, + "loss": 3.3226, + "step": 2718720 + }, + { + "epoch": 1.02, + "learning_rate": 5.483017473562973e-06, + "loss": 3.3362, + "step": 2719232 + }, + { + "epoch": 1.02, + "learning_rate": 5.474631526052453e-06, + "loss": 3.3336, + "step": 2719744 + }, + { + "epoch": 1.02, + "learning_rate": 5.4662619573456644e-06, + "loss": 3.3255, + "step": 2720256 + }, + { + "epoch": 1.02, + "learning_rate": 5.457876009835144e-06, + "loss": 3.319, + "step": 2720768 + }, + { + "epoch": 1.02, + "learning_rate": 5.449490062324624e-06, + "loss": 3.3241, + "step": 2721280 + }, + { + "epoch": 1.02, + "learning_rate": 5.441104114814104e-06, + "loss": 3.3259, + "step": 2721792 + }, + { + "epoch": 1.02, + "learning_rate": 5.432734546107315e-06, + "loss": 3.3266, + "step": 2722304 + }, + { + "epoch": 1.02, + "learning_rate": 5.424348598596796e-06, + "loss": 3.33, + "step": 2722816 + }, + { + "epoch": 1.02, + "learning_rate": 5.415962651086275e-06, + "loss": 3.3248, + "step": 2723328 + }, + { + "epoch": 1.02, + "learning_rate": 5.407576703575755e-06, + "loss": 3.3167, + "step": 2723840 + }, + { + "epoch": 1.02, + "learning_rate": 5.399207134868967e-06, + "loss": 3.3428, + "step": 2724352 + }, + { + "epoch": 1.02, + "learning_rate": 5.3908211873584466e-06, + "loss": 3.3146, + "step": 2724864 + }, + { + "epoch": 1.02, + "learning_rate": 5.3824352398479265e-06, + "loss": 3.3263, + "step": 2725376 + }, + { + "epoch": 1.02, + "learning_rate": 5.3740492923374065e-06, + "loss": 3.3178, + "step": 2725888 + }, + { + "epoch": 1.02, + "learning_rate": 5.365679723630618e-06, + "loss": 3.3278, + "step": 2726400 + }, + { + "epoch": 1.02, + "learning_rate": 5.357293776120097e-06, + "loss": 3.317, + "step": 2726912 + }, + { + "epoch": 1.02, + "learning_rate": 5.348907828609578e-06, + "loss": 3.3264, + "step": 2727424 + }, + { + "epoch": 1.02, + "learning_rate": 5.340521881099057e-06, + "loss": 3.3196, + "step": 2727936 + }, + { + "epoch": 1.02, + "learning_rate": 5.332152312392269e-06, + "loss": 3.3197, + "step": 2728448 + }, + { + "epoch": 1.02, + "learning_rate": 5.323766364881749e-06, + "loss": 3.328, + "step": 2728960 + }, + { + "epoch": 1.02, + "learning_rate": 5.315380417371228e-06, + "loss": 3.3188, + "step": 2729472 + }, + { + "epoch": 1.02, + "learning_rate": 5.306994469860709e-06, + "loss": 3.3319, + "step": 2729984 + }, + { + "epoch": 1.02, + "learning_rate": 5.2986249011539194e-06, + "loss": 3.3418, + "step": 2730496 + }, + { + "epoch": 1.02, + "learning_rate": 5.290238953643399e-06, + "loss": 3.3292, + "step": 2731008 + }, + { + "epoch": 1.02, + "learning_rate": 5.281853006132879e-06, + "loss": 3.3192, + "step": 2731520 + }, + { + "epoch": 1.02, + "learning_rate": 5.27346705862236e-06, + "loss": 3.3264, + "step": 2732032 + }, + { + "epoch": 1.02, + "learning_rate": 5.265097489915571e-06, + "loss": 3.3186, + "step": 2732544 + }, + { + "epoch": 1.02, + "learning_rate": 5.256711542405051e-06, + "loss": 3.3206, + "step": 2733056 + }, + { + "epoch": 1.02, + "learning_rate": 5.248325594894531e-06, + "loss": 3.3263, + "step": 2733568 + }, + { + "epoch": 1.02, + "learning_rate": 5.23993964738401e-06, + "loss": 3.3142, + "step": 2734080 + }, + { + "epoch": 1.02, + "learning_rate": 5.231570078677222e-06, + "loss": 3.3278, + "step": 2734592 + }, + { + "epoch": 1.02, + "learning_rate": 5.2231841311667015e-06, + "loss": 3.3256, + "step": 2735104 + }, + { + "epoch": 1.02, + "learning_rate": 5.2147981836561815e-06, + "loss": 3.3269, + "step": 2735616 + }, + { + "epoch": 1.02, + "learning_rate": 5.2064122361456615e-06, + "loss": 3.3186, + "step": 2736128 + }, + { + "epoch": 1.02, + "learning_rate": 5.198042667438873e-06, + "loss": 3.3227, + "step": 2736640 + }, + { + "epoch": 1.02, + "learning_rate": 5.189656719928353e-06, + "loss": 3.322, + "step": 2737152 + }, + { + "epoch": 1.02, + "learning_rate": 5.181270772417833e-06, + "loss": 3.3291, + "step": 2737664 + }, + { + "epoch": 1.02, + "learning_rate": 5.172884824907313e-06, + "loss": 3.3288, + "step": 2738176 + }, + { + "epoch": 1.02, + "learning_rate": 5.164515256200525e-06, + "loss": 3.3377, + "step": 2738688 + }, + { + "epoch": 1.02, + "learning_rate": 5.156129308690004e-06, + "loss": 3.3157, + "step": 2739200 + }, + { + "epoch": 1.02, + "learning_rate": 5.147743361179484e-06, + "loss": 3.3276, + "step": 2739712 + }, + { + "epoch": 1.02, + "learning_rate": 5.139373792472695e-06, + "loss": 3.3257, + "step": 2740224 + }, + { + "epoch": 1.02, + "learning_rate": 5.130987844962174e-06, + "loss": 3.3193, + "step": 2740736 + }, + { + "epoch": 1.02, + "learning_rate": 5.122601897451655e-06, + "loss": 3.3236, + "step": 2741248 + }, + { + "epoch": 1.02, + "learning_rate": 5.114215949941135e-06, + "loss": 3.3369, + "step": 2741760 + }, + { + "epoch": 1.02, + "learning_rate": 5.105846381234347e-06, + "loss": 3.3261, + "step": 2742272 + }, + { + "epoch": 1.02, + "learning_rate": 5.097460433723826e-06, + "loss": 3.3419, + "step": 2742784 + }, + { + "epoch": 1.02, + "learning_rate": 5.089074486213306e-06, + "loss": 3.3214, + "step": 2743296 + }, + { + "epoch": 1.02, + "learning_rate": 5.080688538702786e-06, + "loss": 3.3305, + "step": 2743808 + }, + { + "epoch": 1.02, + "learning_rate": 5.072318969995997e-06, + "loss": 3.3235, + "step": 2744320 + }, + { + "epoch": 1.02, + "learning_rate": 5.063933022485477e-06, + "loss": 3.3253, + "step": 2744832 + }, + { + "epoch": 1.02, + "learning_rate": 5.0555470749749565e-06, + "loss": 3.3221, + "step": 2745344 + }, + { + "epoch": 1.02, + "learning_rate": 5.047161127464437e-06, + "loss": 3.3251, + "step": 2745856 + }, + { + "epoch": 1.02, + "learning_rate": 5.038791558757648e-06, + "loss": 3.3243, + "step": 2746368 + }, + { + "epoch": 1.02, + "learning_rate": 5.030405611247128e-06, + "loss": 3.3169, + "step": 2746880 + }, + { + "epoch": 1.02, + "learning_rate": 5.022019663736608e-06, + "loss": 3.321, + "step": 2747392 + }, + { + "epoch": 1.03, + "eval_loss": 3.8688833713531494, + "eval_runtime": 310.8279, + "eval_samples_per_second": 1227.66, + "eval_steps_per_second": 38.365, + "step": 2747512 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.8757831628692316e+18, + "trial_name": null, + "trial_params": null +}