diff --git "a/checkpoint-2976480/trainer_state.json" "b/checkpoint-2976480/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2976480/trainer_state.json" @@ -0,0 +1,35215 @@ +{ + "best_metric": 3.849526882171631, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/passive/transformer/0/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2976480, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9439, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.817, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1835, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9785, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8168, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6117, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5357, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4533, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4043, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3518, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3117, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2639, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2131, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.175, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1275, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.112, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0788, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0485, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0198, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 5.0109, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9774, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9542, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9241, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9211, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8846, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.8729, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 4.8443, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8323, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8198, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.8012, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 4.7916, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7801, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7648, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.762, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7413, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.738, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.6962, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7072, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6719, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6816, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6666, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6632, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6384, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.651, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6361, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6303, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6246, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.5932, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5964, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5969, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5867, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.578, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5598, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5563, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5382, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5622, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.517, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5407, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5322, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5108, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5105, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.501, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4952, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4867, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.4952, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4751, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4705, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.464, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4642, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4746, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4659, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4451, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.459, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4597, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4304, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4383, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4285, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4233, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4145, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4187, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4219, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4241, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.401, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.379, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3946, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.3952, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.3936, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 4.3807, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3844, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 4.3799, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 4.3758, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3658, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3683, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3569, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.3698, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 4.358, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.3388, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.3511, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.3506, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 4.3539, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3387, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3396, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3245, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.3338, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3159, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.323, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3208, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3193, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3093, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3132, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3052, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.312, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.3035, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.2982, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3138, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.302, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.3, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.2877, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2917, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.285, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2849, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2925, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2774, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2829, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2636, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2674, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2745, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.265, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2563, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2813, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2625, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2565, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2559, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2587, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.259, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2563, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2501, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2577, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2549, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2501, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2372, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2463, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.238, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2387, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2348, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877612664877228e-05, + "loss": 4.2325, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2384, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2257, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2225, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.200098991394043, + "eval_runtime": 313.6584, + "eval_samples_per_second": 1216.581, + "eval_steps_per_second": 38.019, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874259923753393e-05, + "loss": 4.209, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.2087, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.235, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.2207, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870907182629558e-05, + "loss": 4.2131, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870068587878506e-05, + "loss": 4.2102, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2078, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.1962, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675544415057236e-05, + "loss": 4.2081, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667158467546716e-05, + "loss": 4.2039, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.2068, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.2084, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1921, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.187, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1807, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1793, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1871, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.1775, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1835, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.2002, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857494580253846e-05, + "loss": 4.1802, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856655985502793e-05, + "loss": 4.1835, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855817390751741e-05, + "loss": 4.1725, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854980433881063e-05, + "loss": 4.1866, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854141839130011e-05, + "loss": 4.1696, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853303244378958e-05, + "loss": 4.1687, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852464649627906e-05, + "loss": 4.1618, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851627692757228e-05, + "loss": 4.1681, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850789098006175e-05, + "loss": 4.1589, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849950503255123e-05, + "loss": 4.1568, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849111908504072e-05, + "loss": 4.162, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482749516333934e-05, + "loss": 4.1679, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847436356882341e-05, + "loss": 4.1578, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846597762131289e-05, + "loss": 4.1609, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845759167380237e-05, + "loss": 4.1533, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844922210509558e-05, + "loss": 4.1629, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440836157585056e-05, + "loss": 4.1364, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432450210074536e-05, + "loss": 4.1528, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8424064262564016e-05, + "loss": 4.1299, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415694693857225e-05, + "loss": 4.151, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407308746346705e-05, + "loss": 4.1349, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398922798836185e-05, + "loss": 4.1493, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839053685132567e-05, + "loss": 4.1303, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838216728261888e-05, + "loss": 4.1437, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837378133510836e-05, + "loss": 4.1424, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836539538759784e-05, + "loss": 4.1411, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835700944008732e-05, + "loss": 4.1438, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834863987138053e-05, + "loss": 4.1164, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834025392387001e-05, + "loss": 4.1234, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833186797635949e-05, + "loss": 4.1364, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832348202884897e-05, + "loss": 4.1331, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831511246014218e-05, + "loss": 4.126, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830672651263166e-05, + "loss": 4.1207, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298356943924875e-05, + "loss": 4.1163, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289970996414354e-05, + "loss": 4.1088, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281585048903834e-05, + "loss": 4.1236, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273199101393314e-05, + "loss": 4.1053, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826482953268653e-05, + "loss": 4.1157, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256443585176003e-05, + "loss": 4.124, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248057637665483e-05, + "loss": 4.1044, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823967169015496e-05, + "loss": 4.1056, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823128574264444e-05, + "loss": 4.1045, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822289979513392e-05, + "loss": 4.0978, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.82145138476234e-05, + "loss": 4.0969, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820612790011288e-05, + "loss": 4.1136, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819777471020983e-05, + "loss": 4.0989, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818938876269931e-05, + "loss": 4.0949, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818100281518879e-05, + "loss": 4.0921, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817261686767827e-05, + "loss": 4.094, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816423092016775e-05, + "loss": 4.1086, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815586135146096e-05, + "loss": 4.1011, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814747540395044e-05, + "loss": 4.0936, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813908945643992e-05, + "loss": 4.1025, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81307035089294e-05, + "loss": 4.1062, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812231756141888e-05, + "loss": 4.0848, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811393161390836e-05, + "loss": 4.0934, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810554566639784e-05, + "loss": 4.0911, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097176097691046e-05, + "loss": 4.0885, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808879015018053e-05, + "loss": 4.0815, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808040420267001e-05, + "loss": 4.0848, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807201825515949e-05, + "loss": 4.0954, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806363230764897e-05, + "loss": 4.0916, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805526273894218e-05, + "loss": 4.0839, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804687679143166e-05, + "loss": 4.0595, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803849084392114e-05, + "loss": 4.0756, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803010489641062e-05, + "loss": 4.0818, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.0795, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0757, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800494705387906e-05, + "loss": 4.0721, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799657748517227e-05, + "loss": 4.0787, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988207916465486e-05, + "loss": 4.0693, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979821968954966e-05, + "loss": 4.0639, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971436021444446e-05, + "loss": 4.0782, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963050073933926e-05, + "loss": 4.0613, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954680505227135e-05, + "loss": 4.0817, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946294557716615e-05, + "loss": 4.0709, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937908610206095e-05, + "loss": 4.0516, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929522662695575e-05, + "loss": 4.0687, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921136715185055e-05, + "loss": 4.065, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912750767674535e-05, + "loss": 4.0751, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904381198967744e-05, + "loss": 4.0644, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895995251457224e-05, + "loss": 4.06, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887609303946704e-05, + "loss": 4.0498, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879223356436184e-05, + "loss": 4.066, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708537877294e-05, + "loss": 4.0456, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786246784021888e-05, + "loss": 4.0535, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785408189270836e-05, + "loss": 4.0571, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784569594519783e-05, + "loss": 4.055, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783730999768731e-05, + "loss": 4.0443, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782892405017679e-05, + "loss": 4.0548, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782053810266627e-05, + "loss": 4.0473, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781216853395948e-05, + "loss": 4.0518, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780378258644896e-05, + "loss": 4.0501, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779539663893844e-05, + "loss": 4.0445, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778701069142792e-05, + "loss": 4.069, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777864112272114e-05, + "loss": 4.0548, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777025517521062e-05, + "loss": 4.0507, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.77618692277001e-05, + "loss": 4.0379, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775348328018958e-05, + "loss": 4.0468, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774509733267906e-05, + "loss": 4.0441, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773671138516854e-05, + "loss": 4.037, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772832543765802e-05, + "loss": 4.0542, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77199394901475e-05, + "loss": 4.0412, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711569921440707e-05, + "loss": 4.041, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703183973930186e-05, + "loss": 4.0333, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694814405223396e-05, + "loss": 4.0357, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686428457712876e-05, + "loss": 4.0376, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.7678042510202355e-05, + "loss": 4.0367, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766965656269184e-05, + "loss": 4.024, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766128699398505e-05, + "loss": 4.0535, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765290104647453e-05, + "loss": 4.0416, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764451509896401e-05, + "loss": 4.0328, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763612915145349e-05, + "loss": 4.0308, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762774320394297e-05, + "loss": 4.0287, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761937363523618e-05, + "loss": 4.04, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761098768772566e-05, + "loss": 4.0364, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760260174021514e-05, + "loss": 4.0293, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759421579270462e-05, + "loss": 4.0408, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758584622399783e-05, + "loss": 4.0339, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757746027648731e-05, + "loss": 4.0372, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569074328976796e-05, + "loss": 4.0219, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560688381466276e-05, + "loss": 4.0364, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552318812759485e-05, + "loss": 4.0273, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543932865248965e-05, + "loss": 4.0249, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535546917738445e-05, + "loss": 4.0265, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527160970227925e-05, + "loss": 4.0275, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518775022717405e-05, + "loss": 4.028, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510405454010614e-05, + "loss": 4.0184, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502019506500094e-05, + "loss": 4.0189, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.031566143035889, + "eval_runtime": 313.0538, + "eval_samples_per_second": 1218.931, + "eval_steps_per_second": 38.092, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493633558989574e-05, + "loss": 4.0065, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485247611479054e-05, + "loss": 4.0066, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476861663968534e-05, + "loss": 4.0332, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468475716458014e-05, + "loss": 4.0258, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460089768947494e-05, + "loss": 4.0166, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451703821436974e-05, + "loss": 4.0103, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443317873926453e-05, + "loss": 4.0131, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434931926415933e-05, + "loss": 3.9996, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426545978905413e-05, + "loss": 4.0192, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741817641019862e-05, + "loss": 4.014, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.74097904626881e-05, + "loss": 4.013, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740140451517758e-05, + "loss": 4.0147, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.0025, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.0011, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737626305144975e-05, + "loss": 3.9971, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736787710393923e-05, + "loss": 3.996, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735949115642871e-05, + "loss": 4.0005, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.73511052089182e-05, + "loss": 3.9938, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734273564021141e-05, + "loss": 4.0005, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733434969270089e-05, + "loss": 4.0233, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732596374519037e-05, + "loss": 3.9976, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731757779767985e-05, + "loss": 4.0022, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309208228973056e-05, + "loss": 3.9992, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300822281462536e-05, + "loss": 4.0059, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292436333952016e-05, + "loss": 3.9893, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284050386441496e-05, + "loss": 3.9981, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275664438930976e-05, + "loss": 3.989, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267294870224185e-05, + "loss": 3.9915, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258908922713665e-05, + "loss": 3.9847, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725052297520315e-05, + "loss": 3.9841, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724213702769263e-05, + "loss": 3.9907, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723376745898584e-05, + "loss": 3.9993, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722538151147532e-05, + "loss": 3.9899, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.72169955639648e-05, + "loss": 3.9988, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720860961645428e-05, + "loss": 3.9811, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720022366894376e-05, + "loss": 4.0009, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719185410023697e-05, + "loss": 3.9708, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718346815272645e-05, + "loss": 3.9898, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717508220521593e-05, + "loss": 3.9669, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716669625770541e-05, + "loss": 3.9865, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715832668899862e-05, + "loss": 3.974, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149940741488105e-05, + "loss": 3.9917, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141554793977585e-05, + "loss": 3.9737, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133168846467065e-05, + "loss": 3.9794, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124782898956545e-05, + "loss": 3.9835, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116413330249754e-05, + "loss": 3.9859, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108027382739234e-05, + "loss": 3.9831, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099641435228714e-05, + "loss": 3.9638, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091255487718194e-05, + "loss": 3.9636, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.70828859190114e-05, + "loss": 3.9837, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707449997150088e-05, + "loss": 3.9787, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706611402399036e-05, + "loss": 3.9722, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705772807647984e-05, + "loss": 3.9691, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704935850777306e-05, + "loss": 3.9666, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704097256026254e-05, + "loss": 3.9562, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703258661275202e-05, + "loss": 3.9683, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.70242006652415e-05, + "loss": 3.9558, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701583109653471e-05, + "loss": 3.9685, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700744514902419e-05, + "loss": 3.9758, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699905920151367e-05, + "loss": 3.956, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699067325400315e-05, + "loss": 3.957, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698228730649263e-05, + "loss": 3.962, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.69739013589821e-05, + "loss": 3.9508, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696553179027532e-05, + "loss": 3.9467, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69571458427648e-05, + "loss": 3.9695, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694875989525428e-05, + "loss": 3.9562, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694037394774376e-05, + "loss": 3.9516, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693200437903697e-05, + "loss": 3.9481, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692361843152645e-05, + "loss": 3.9542, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915232484015926e-05, + "loss": 3.9647, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906846536505406e-05, + "loss": 3.9606, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898460588994886e-05, + "loss": 3.9505, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890091020288095e-05, + "loss": 3.9654, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881705072777575e-05, + "loss": 3.9615, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873319125267055e-05, + "loss": 3.9491, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864933177756535e-05, + "loss": 3.9538, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685656360904975e-05, + "loss": 3.9572, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684817766153923e-05, + "loss": 3.9507, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683979171402871e-05, + "loss": 3.9477, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683140576651819e-05, + "loss": 3.9483, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.68230361978114e-05, + "loss": 3.9577, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681465025030088e-05, + "loss": 3.9579, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680626430279036e-05, + "loss": 3.9442, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679787835527984e-05, + "loss": 3.9324, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678950878657305e-05, + "loss": 3.9385, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678112283906253e-05, + "loss": 3.9459, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677273689155201e-05, + "loss": 3.9496, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676435094404149e-05, + "loss": 3.9422, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755981375334704e-05, + "loss": 3.9386, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747595427824184e-05, + "loss": 3.9524, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739209480313664e-05, + "loss": 3.9352, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730823532803144e-05, + "loss": 3.9365, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672245396409635e-05, + "loss": 3.9473, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671406801658583e-05, + "loss": 3.9357, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670568206907531e-05, + "loss": 3.9547, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669729612156479e-05, + "loss": 3.9415, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688926552858e-05, + "loss": 3.9251, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668054060534748e-05, + "loss": 3.9406, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667215465783696e-05, + "loss": 3.9365, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666376871032644e-05, + "loss": 3.9517, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665539914161966e-05, + "loss": 3.9418, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664701319410914e-05, + "loss": 3.9347, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663862724659862e-05, + "loss": 3.9238, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66302412990881e-05, + "loss": 3.9405, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662187173038131e-05, + "loss": 3.922, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661348578287079e-05, + "loss": 3.9327, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660509983536027e-05, + "loss": 3.9349, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659671388784975e-05, + "loss": 3.9315, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588344319142956e-05, + "loss": 3.9209, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579958371632436e-05, + "loss": 3.9382, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571572424121916e-05, + "loss": 3.9242, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6563186476611396e-05, + "loss": 3.9285, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655481690790461e-05, + "loss": 3.9329, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654643096039409e-05, + "loss": 3.9244, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653804501288357e-05, + "loss": 3.9455, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652965906537305e-05, + "loss": 3.934, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652128949666626e-05, + "loss": 3.9342, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651290354915574e-05, + "loss": 3.9213, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650451760164522e-05, + "loss": 3.9301, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.64961316541347e-05, + "loss": 3.9303, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648776208542791e-05, + "loss": 3.9161, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647937613791739e-05, + "loss": 3.9328, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647099019040687e-05, + "loss": 3.9263, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646260424289635e-05, + "loss": 3.9239, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645423467418956e-05, + "loss": 3.9216, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445848726679045e-05, + "loss": 3.9232, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437462779168525e-05, + "loss": 3.9166, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429076831658005e-05, + "loss": 3.9262, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420690884147485e-05, + "loss": 3.9127, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412321315440694e-05, + "loss": 3.9354, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403935367930174e-05, + "loss": 3.9322, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395549420419654e-05, + "loss": 3.9177, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387163472909134e-05, + "loss": 3.9151, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637879390420234e-05, + "loss": 3.9194, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637040795669182e-05, + "loss": 3.9253, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.63620220091813e-05, + "loss": 3.9253, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635363606167078e-05, + "loss": 3.9182, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345266492964e-05, + "loss": 3.9272, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633688054545348e-05, + "loss": 3.9231, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632849459794296e-05, + "loss": 3.9282, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632010865043244e-05, + "loss": 3.9123, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631173908172565e-05, + "loss": 3.9281, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630335313421513e-05, + "loss": 3.9193, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629496718670461e-05, + "loss": 3.9122, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628659761799782e-05, + "loss": 3.9207, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.62782116704873e-05, + "loss": 3.9224, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626982572297678e-05, + "loss": 3.9164, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626143977546626e-05, + "loss": 3.9072, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6253070206759466e-05, + "loss": 3.9092, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9577343463897705, + "eval_runtime": 303.0161, + "eval_samples_per_second": 1259.309, + "eval_steps_per_second": 39.354, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624468425924895e-05, + "loss": 3.9092, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623629831173843e-05, + "loss": 3.9007, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622791236422791e-05, + "loss": 3.926, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621954279552112e-05, + "loss": 3.9197, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.62111568480106e-05, + "loss": 3.9192, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620277090050008e-05, + "loss": 3.8996, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619438495298956e-05, + "loss": 3.9141, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618599900547904e-05, + "loss": 3.8917, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617762943677225e-05, + "loss": 3.9183, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616924348926173e-05, + "loss": 3.9117, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616085754175121e-05, + "loss": 3.9046, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615248797304442e-05, + "loss": 3.9158, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144118404337635e-05, + "loss": 3.899, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135732456827115e-05, + "loss": 3.9026, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127346509316595e-05, + "loss": 3.8916, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118960561806075e-05, + "loss": 3.8983, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110574614295555e-05, + "loss": 3.8968, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102188666785035e-05, + "loss": 3.8947, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093802719274515e-05, + "loss": 3.8983, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085416771763995e-05, + "loss": 3.9199, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6077047203057204e-05, + "loss": 3.8983, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068661255546684e-05, + "loss": 3.9057, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060275308036164e-05, + "loss": 3.9001, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051889360525644e-05, + "loss": 3.9063, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604351979181886e-05, + "loss": 3.8915, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603513384430834e-05, + "loss": 3.8998, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602674789679782e-05, + "loss": 3.8916, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.60183619492873e-05, + "loss": 3.8917, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600999238058051e-05, + "loss": 3.8866, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600160643306999e-05, + "loss": 3.8926, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599322048555947e-05, + "loss": 3.8928, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598483453804895e-05, + "loss": 3.9036, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597646496934216e-05, + "loss": 3.8956, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596807902183164e-05, + "loss": 3.8964, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595969307432112e-05, + "loss": 3.8879, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.59513071268106e-05, + "loss": 3.9012, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942937558103813e-05, + "loss": 3.884, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934551610593293e-05, + "loss": 3.8933, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926165663082773e-05, + "loss": 3.8708, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917779715572247e-05, + "loss": 3.8902, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590941014686546e-05, + "loss": 3.8828, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590102419935494e-05, + "loss": 3.9003, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589263825184442e-05, + "loss": 3.8837, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884252304333896e-05, + "loss": 3.8869, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587588273562711e-05, + "loss": 3.8909, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586749678811659e-05, + "loss": 3.8971, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5859110840606065e-05, + "loss": 3.886, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585072489309555e-05, + "loss": 3.875, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584235532438877e-05, + "loss": 3.8689, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583396937687825e-05, + "loss": 3.8911, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582558342936772e-05, + "loss": 3.8886, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.58171974818572e-05, + "loss": 3.8821, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808827913150416e-05, + "loss": 3.8753, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800441965639896e-05, + "loss": 3.8811, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579205601812937e-05, + "loss": 3.8623, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578367007061885e-05, + "loss": 3.8821, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5775300501912065e-05, + "loss": 3.8652, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576691455440154e-05, + "loss": 3.8788, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575852860689102e-05, + "loss": 3.8849, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750142659380505e-05, + "loss": 3.8737, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741773090673714e-05, + "loss": 3.8644, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733387143163194e-05, + "loss": 3.8755, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5725001195652674e-05, + "loss": 3.8627, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571663162694589e-05, + "loss": 3.8637, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570824567943537e-05, + "loss": 3.8795, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569985973192484e-05, + "loss": 3.87, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569147378441432e-05, + "loss": 3.8641, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568310421570754e-05, + "loss": 3.8594, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567471826819701e-05, + "loss": 3.8679, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566633232068649e-05, + "loss": 3.8729, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565794637317597e-05, + "loss": 3.8745, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564957680446919e-05, + "loss": 3.8676, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564119085695867e-05, + "loss": 3.8782, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563280490944815e-05, + "loss": 3.8777, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562441896193763e-05, + "loss": 3.8659, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5616049393230843e-05, + "loss": 3.866, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560766344572032e-05, + "loss": 3.874, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.55992774982098e-05, + "loss": 3.8693, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559090792950301e-05, + "loss": 3.8644, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582521981992486e-05, + "loss": 3.8645, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5574136034481966e-05, + "loss": 3.8712, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565750086971446e-05, + "loss": 3.8729, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557364139460926e-05, + "loss": 3.8634, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548978191950405e-05, + "loss": 3.8512, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554059224443989e-05, + "loss": 3.8504, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553220629692937e-05, + "loss": 3.8614, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552383672822258e-05, + "loss": 3.8691, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551545078071206e-05, + "loss": 3.8623, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550706483320154e-05, + "loss": 3.8516, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549867888569102e-05, + "loss": 3.8691, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549030931698423e-05, + "loss": 3.8595, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548192336947371e-05, + "loss": 3.8561, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547353742196319e-05, + "loss": 3.8588, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546515147445267e-05, + "loss": 3.8632, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545678190574588e-05, + "loss": 3.8726, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544839595823536e-05, + "loss": 3.8554, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5440010010724846e-05, + "loss": 3.8443, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431624063214326e-05, + "loss": 3.8633, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423254494507535e-05, + "loss": 3.8548, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414868546997015e-05, + "loss": 3.8695, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406482599486495e-05, + "loss": 3.8646, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5398096651975975e-05, + "loss": 3.8522, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389727083269184e-05, + "loss": 3.8463, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381341135758664e-05, + "loss": 3.8617, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372955188248144e-05, + "loss": 3.8437, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364569240737624e-05, + "loss": 3.8542, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535619967203083e-05, + "loss": 3.8518, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534781372452031e-05, + "loss": 3.8567, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.53394277770098e-05, + "loss": 3.8411, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533104182949928e-05, + "loss": 3.8603, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532267226079249e-05, + "loss": 3.8462, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531428631328197e-05, + "loss": 3.8494, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530590036577145e-05, + "loss": 3.8587, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529751441826093e-05, + "loss": 3.8471, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528914484955414e-05, + "loss": 3.8686, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528075890204362e-05, + "loss": 3.8584, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.52723729545331e-05, + "loss": 3.8546, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526398700702258e-05, + "loss": 3.8452, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255617438315787e-05, + "loss": 3.8548, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247231490805266e-05, + "loss": 3.8495, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523884554329475e-05, + "loss": 3.844, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523047597458796e-05, + "loss": 3.855, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522209002707744e-05, + "loss": 3.8503, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521370407956692e-05, + "loss": 3.8479, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.52053181320564e-05, + "loss": 3.8459, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519693218454588e-05, + "loss": 3.8501, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518854623703536e-05, + "loss": 3.8432, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518016028952484e-05, + "loss": 3.8534, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517177434201432e-05, + "loss": 3.8394, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516342115211126e-05, + "loss": 3.8572, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515503520460074e-05, + "loss": 3.8535, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514664925709022e-05, + "loss": 3.8495, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513826330957971e-05, + "loss": 3.84, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512987736206919e-05, + "loss": 3.8464, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512149141455867e-05, + "loss": 3.8509, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511310546704815e-05, + "loss": 3.8528, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510471951953762e-05, + "loss": 3.8403, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096349950830836e-05, + "loss": 3.8523, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087964003320316e-05, + "loss": 3.8479, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079578055809796e-05, + "loss": 3.8577, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507119210829927e-05, + "loss": 3.8412, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062822539592485e-05, + "loss": 3.8535, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054436592081965e-05, + "loss": 3.8484, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5046050644571445e-05, + "loss": 3.8403, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503768107586466e-05, + "loss": 3.8456, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502929512835414e-05, + "loss": 3.8533, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502090918084362e-05, + "loss": 3.8429, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012523233333094e-05, + "loss": 3.833, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004137285822574e-05, + "loss": 3.8447, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9168317317962646, + "eval_runtime": 303.4989, + "eval_samples_per_second": 1257.306, + "eval_steps_per_second": 39.292, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995751338312054e-05, + "loss": 3.8312, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987365390801534e-05, + "loss": 3.8296, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978979443291013e-05, + "loss": 3.8488, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970593495780493e-05, + "loss": 3.8502, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496220754826997e-05, + "loss": 3.8489, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495382160075945e-05, + "loss": 3.8357, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494543565324893e-05, + "loss": 3.8396, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493704970573841e-05, + "loss": 3.8207, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492868013703162e-05, + "loss": 3.8474, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492029418952111e-05, + "loss": 3.8434, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491190824201059e-05, + "loss": 3.8341, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490352229450007e-05, + "loss": 3.8454, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489516910459701e-05, + "loss": 3.8283, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488678315708649e-05, + "loss": 3.8335, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487839720957597e-05, + "loss": 3.8246, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.487001126206545e-05, + "loss": 3.8239, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486162531455493e-05, + "loss": 3.8292, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485323936704441e-05, + "loss": 3.8267, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484485341953389e-05, + "loss": 3.8313, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483646747202337e-05, + "loss": 3.8478, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4828097903316576e-05, + "loss": 3.8322, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481971195580606e-05, + "loss": 3.8394, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481132600829554e-05, + "loss": 3.8308, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480294006078502e-05, + "loss": 3.8365, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479457049207823e-05, + "loss": 3.8254, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478618454456771e-05, + "loss": 3.8315, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477779859705719e-05, + "loss": 3.8289, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476941264954667e-05, + "loss": 3.8224, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476104308083988e-05, + "loss": 3.8192, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475265713332936e-05, + "loss": 3.8254, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474427118581884e-05, + "loss": 3.8259, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473590161711205e-05, + "loss": 3.8356, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472751566960153e-05, + "loss": 3.8311, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4719129722091016e-05, + "loss": 3.8308, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710743774580496e-05, + "loss": 3.8197, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702374205873705e-05, + "loss": 3.8363, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693988258363185e-05, + "loss": 3.8205, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685602310852665e-05, + "loss": 3.8234, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677216363342145e-05, + "loss": 3.8087, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668846794635354e-05, + "loss": 3.8225, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660460847124834e-05, + "loss": 3.8201, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4652074899614314e-05, + "loss": 3.8329, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643688952103794e-05, + "loss": 3.8186, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635319383397003e-05, + "loss": 3.8243, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462693343588648e-05, + "loss": 3.8249, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461854748837597e-05, + "loss": 3.8314, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461016154086545e-05, + "loss": 3.8234, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460179197215866e-05, + "loss": 3.8108, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459340602464814e-05, + "loss": 3.8025, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458502007713762e-05, + "loss": 3.8308, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.45766341296271e-05, + "loss": 3.8236, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456826456092031e-05, + "loss": 3.8177, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455987861340979e-05, + "loss": 3.8143, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455149266589927e-05, + "loss": 3.8159, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454310671838875e-05, + "loss": 3.7978, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453473714968196e-05, + "loss": 3.8152, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452635120217144e-05, + "loss": 3.8075, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517965254660924e-05, + "loss": 3.8144, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509579307150404e-05, + "loss": 3.8231, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450120973844361e-05, + "loss": 3.8097, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449282379093309e-05, + "loss": 3.801, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448443784342257e-05, + "loss": 3.8187, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447605189591205e-05, + "loss": 3.7974, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446768232720526e-05, + "loss": 3.8041, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445929637969474e-05, + "loss": 3.8132, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445091043218422e-05, + "loss": 3.8115, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442524484673695e-05, + "loss": 3.8017, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443415491596691e-05, + "loss": 3.8036, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442576896845639e-05, + "loss": 3.8029, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441738302094588e-05, + "loss": 3.8115, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440899707343535e-05, + "loss": 3.8107, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400627504728566e-05, + "loss": 3.8065, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392241557218046e-05, + "loss": 3.8177, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383855609707526e-05, + "loss": 3.8184, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375469662197e-05, + "loss": 3.8059, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.4367100093490215e-05, + "loss": 3.8007, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358714145979695e-05, + "loss": 3.8192, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435032819846917e-05, + "loss": 3.8091, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341958629762384e-05, + "loss": 3.8005, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333572682251864e-05, + "loss": 3.8059, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325186734741344e-05, + "loss": 3.81, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316800787230824e-05, + "loss": 3.8173, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308414839720304e-05, + "loss": 3.7989, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4300028892209784e-05, + "loss": 3.7897, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291642944699264e-05, + "loss": 3.798, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283256997188744e-05, + "loss": 3.7965, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427488742848195e-05, + "loss": 3.808, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426650148097143e-05, + "loss": 3.8045, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425811553346091e-05, + "loss": 3.7916, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424972958595039e-05, + "loss": 3.8099, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.42413600172436e-05, + "loss": 3.7979, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423297406973308e-05, + "loss": 3.801, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422458812222257e-05, + "loss": 3.7968, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421620217471205e-05, + "loss": 3.8031, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420783260600526e-05, + "loss": 3.816, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419944665849474e-05, + "loss": 3.8025, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419106071098422e-05, + "loss": 3.782, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.41826747634737e-05, + "loss": 3.8027, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417430519476691e-05, + "loss": 3.7983, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416591924725639e-05, + "loss": 3.8054, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415753329974587e-05, + "loss": 3.8095, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414914735223535e-05, + "loss": 3.7955, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140777783528556e-05, + "loss": 3.7904, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132391836018036e-05, + "loss": 3.8041, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412402226731125e-05, + "loss": 3.7824, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411563631980073e-05, + "loss": 3.7995, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410725037229021e-05, + "loss": 3.7921, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409886442477969e-05, + "loss": 3.8018, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409047847726917e-05, + "loss": 3.7858, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408209252975865e-05, + "loss": 3.8, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407370658224813e-05, + "loss": 3.7869, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406532063473761e-05, + "loss": 3.7924, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405695106603082e-05, + "loss": 3.8028, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.40485651185203e-05, + "loss": 3.7958, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404017917100978e-05, + "loss": 3.8078, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403180960230299e-05, + "loss": 3.8004, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402342365479247e-05, + "loss": 3.7946, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4015037707281956e-05, + "loss": 3.7987, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006651759771436e-05, + "loss": 3.7922, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3998265812260916e-05, + "loss": 3.7962, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989879864750396e-05, + "loss": 3.7865, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981510296043605e-05, + "loss": 3.7998, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3973124348533085e-05, + "loss": 3.7894, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964738401022565e-05, + "loss": 3.7898, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956352453512045e-05, + "loss": 3.7884, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947966506001525e-05, + "loss": 3.7972, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939580558491005e-05, + "loss": 3.7872, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931210989784214e-05, + "loss": 3.7969, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922825042273694e-05, + "loss": 3.7849, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914439094763174e-05, + "loss": 3.8019, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3906053147252654e-05, + "loss": 3.7956, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897667199742134e-05, + "loss": 3.7943, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388929763103535e-05, + "loss": 3.7872, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388091168352483e-05, + "loss": 3.7895, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.38725257360143e-05, + "loss": 3.8002, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386413978850378e-05, + "loss": 3.7939, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385575384099326e-05, + "loss": 3.7839, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384736789348274e-05, + "loss": 3.7994, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383898194597222e-05, + "loss": 3.7946, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383061237726543e-05, + "loss": 3.8051, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382222642975491e-05, + "loss": 3.7887, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381384048224439e-05, + "loss": 3.7985, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380545453473388e-05, + "loss": 3.7929, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379706858722336e-05, + "loss": 3.7851, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378869901851657e-05, + "loss": 3.7943, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378031307100605e-05, + "loss": 3.7954, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377192712349553e-05, + "loss": 3.7928, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376354117598501e-05, + "loss": 3.7767, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375515522847449e-05, + "loss": 3.7901, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8920512199401855, + "eval_runtime": 302.1491, + "eval_samples_per_second": 1262.923, + "eval_steps_per_second": 39.467, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374676928096397e-05, + "loss": 3.784, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373838333345345e-05, + "loss": 3.7757, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372999738594293e-05, + "loss": 3.7944, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721644196039865e-05, + "loss": 3.7973, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3713258248529345e-05, + "loss": 3.7937, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370487230101883e-05, + "loss": 3.7846, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369648635350831e-05, + "loss": 3.7844, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368810040599779e-05, + "loss": 3.7705, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679730837291e-05, + "loss": 3.7919, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367134488978048e-05, + "loss": 3.7921, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366295894226996e-05, + "loss": 3.7814, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365457299475944e-05, + "loss": 3.7896, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364618704724892e-05, + "loss": 3.7796, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363781747854213e-05, + "loss": 3.7815, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362943153103161e-05, + "loss": 3.7716, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362104558352109e-05, + "loss": 3.7743, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361265963601057e-05, + "loss": 3.7763, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360427368850005e-05, + "loss": 3.7756, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359588774098953e-05, + "loss": 3.7793, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358750179347901e-05, + "loss": 3.7924, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3579132224772226e-05, + "loss": 3.7867, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570762656065435e-05, + "loss": 3.7867, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562376708554915e-05, + "loss": 3.7781, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553990761044395e-05, + "loss": 3.7869, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545604813533875e-05, + "loss": 3.7706, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537218866023355e-05, + "loss": 3.7854, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528832918512834e-05, + "loss": 3.7761, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520446971002314e-05, + "loss": 3.7684, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351206102349179e-05, + "loss": 3.7716, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503691454785003e-05, + "loss": 3.7716, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495305507274483e-05, + "loss": 3.7783, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486919559763963e-05, + "loss": 3.7812, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347853361225344e-05, + "loss": 3.7838, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347018042235039e-05, + "loss": 3.7805, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346179447483987e-05, + "loss": 3.77, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345340852732935e-05, + "loss": 3.7818, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344502257981883e-05, + "loss": 3.7736, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343663663230831e-05, + "loss": 3.7688, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342826706360152e-05, + "loss": 3.7647, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419881116091e-05, + "loss": 3.7699, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341149516858048e-05, + "loss": 3.7741, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340310922106996e-05, + "loss": 3.7803, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339472327355944e-05, + "loss": 3.7693, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338633732604892e-05, + "loss": 3.7721, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337796775734213e-05, + "loss": 3.7765, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336958180983161e-05, + "loss": 3.7793, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3361195862321086e-05, + "loss": 3.7765, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352809914810566e-05, + "loss": 3.7616, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344423967300046e-05, + "loss": 3.7474, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3336038019789526e-05, + "loss": 3.7824, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327668451082735e-05, + "loss": 3.7757, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3319282503572215e-05, + "loss": 3.7702, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.3310896556061695e-05, + "loss": 3.7682, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302510608551175e-05, + "loss": 3.7632, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294124661040655e-05, + "loss": 3.7525, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328573871353014e-05, + "loss": 3.7655, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327735276601962e-05, + "loss": 3.7574, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326898319731283e-05, + "loss": 3.7661, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326059724980231e-05, + "loss": 3.7747, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325222768109552e-05, + "loss": 3.7602, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243841733585e-05, + "loss": 3.7528, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323545578607448e-05, + "loss": 3.7716, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322706983856396e-05, + "loss": 3.7526, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321868389105344e-05, + "loss": 3.7528, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321031432234665e-05, + "loss": 3.7688, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320192837483613e-05, + "loss": 3.763, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319354242732561e-05, + "loss": 3.7548, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185156479815095e-05, + "loss": 3.7547, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176770532304575e-05, + "loss": 3.7548, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168384584794055e-05, + "loss": 3.7608, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3159998637283535e-05, + "loss": 3.768, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151612689773015e-05, + "loss": 3.7573, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143243121066224e-05, + "loss": 3.7674, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313487355235943e-05, + "loss": 3.7687, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312648760484891e-05, + "loss": 3.7672, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311810165733839e-05, + "loss": 3.7508, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310971570982787e-05, + "loss": 3.7696, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310132976231735e-05, + "loss": 3.7655, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309296019361056e-05, + "loss": 3.7505, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308457424610005e-05, + "loss": 3.7659, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307618829858953e-05, + "loss": 3.7584, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306780235107901e-05, + "loss": 3.7698, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305941640356849e-05, + "loss": 3.7553, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.30510468348617e-05, + "loss": 3.7403, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304266088735118e-05, + "loss": 3.7538, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303427493984066e-05, + "loss": 3.7535, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302588899233014e-05, + "loss": 3.7586, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301751942362335e-05, + "loss": 3.7576, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300913347611283e-05, + "loss": 3.7483, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300074752860231e-05, + "loss": 3.7599, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299236158109179e-05, + "loss": 3.7559, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298397563358127e-05, + "loss": 3.7481, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297560606487448e-05, + "loss": 3.7545, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296722011736396e-05, + "loss": 3.7599, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295883416985344e-05, + "loss": 3.7703, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295044822234292e-05, + "loss": 3.754, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2942062274832396e-05, + "loss": 3.7409, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933676327321876e-05, + "loss": 3.7576, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925290379811355e-05, + "loss": 3.7511, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916904432300835e-05, + "loss": 3.7598, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908534863594045e-05, + "loss": 3.7641, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900148916083525e-05, + "loss": 3.745, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289177934737674e-05, + "loss": 3.7461, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288339339986622e-05, + "loss": 3.7597, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.28750074523557e-05, + "loss": 3.7377, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286662150484518e-05, + "loss": 3.7552, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285823555733466e-05, + "loss": 3.742, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284986598862787e-05, + "loss": 3.7591, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284148004111735e-05, + "loss": 3.7393, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283309409360683e-05, + "loss": 3.7556, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282470814609631e-05, + "loss": 3.7482, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281633857738952e-05, + "loss": 3.7437, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807952629879e-05, + "loss": 3.758, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279956668236848e-05, + "loss": 3.749, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279118073485796e-05, + "loss": 3.7638, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278279478734744e-05, + "loss": 3.7599, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774425218640654e-05, + "loss": 3.7475, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2766039271130134e-05, + "loss": 3.756, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757653323619614e-05, + "loss": 3.7476, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749267376109094e-05, + "loss": 3.7507, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.27408978074023e-05, + "loss": 3.745, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273251185989178e-05, + "loss": 3.754, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272412591238126e-05, + "loss": 3.7464, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271573996487074e-05, + "loss": 3.7453, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270735401736022e-05, + "loss": 3.7489, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.26989680698497e-05, + "loss": 3.751, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269059850114291e-05, + "loss": 3.7423, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268221255363239e-05, + "loss": 3.7544, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267382660612187e-05, + "loss": 3.7388, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266544065861136e-05, + "loss": 3.764, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265705471110084e-05, + "loss": 3.7464, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264868514239405e-05, + "loss": 3.7556, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264029919488353e-05, + "loss": 3.7411, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263191324737301e-05, + "loss": 3.7481, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262352729986249e-05, + "loss": 3.7542, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615157731155696e-05, + "loss": 3.748, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606771783645176e-05, + "loss": 3.7418, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598385836134656e-05, + "loss": 3.7563, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589999888624136e-05, + "loss": 3.7513, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581630319917345e-05, + "loss": 3.7608, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2573244372406825e-05, + "loss": 3.7417, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256485842489631e-05, + "loss": 3.7539, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255647247738579e-05, + "loss": 3.7483, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254808652987527e-05, + "loss": 3.7444, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253971696116848e-05, + "loss": 3.751, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253133101365796e-05, + "loss": 3.7516, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252294506614744e-05, + "loss": 3.7547, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251455911863692e-05, + "loss": 3.7278, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250618954993013e-05, + "loss": 3.7531, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.87595272064209, + "eval_runtime": 302.116, + "eval_samples_per_second": 1263.061, + "eval_steps_per_second": 39.472, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249780360241961e-05, + "loss": 3.7403, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248941765490909e-05, + "loss": 3.7314, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248103170739857e-05, + "loss": 3.7498, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247264575988805e-05, + "loss": 3.758, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464276191181266e-05, + "loss": 3.7514, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455890243670746e-05, + "loss": 3.7392, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447504296160226e-05, + "loss": 3.7435, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.24391183486497e-05, + "loss": 3.7305, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430748779942915e-05, + "loss": 3.747, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422362832432395e-05, + "loss": 3.7473, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413976884921875e-05, + "loss": 3.7465, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240559093741135e-05, + "loss": 3.7452, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239720498990083e-05, + "loss": 3.7399, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388835421194044e-05, + "loss": 3.7387, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380449473683524e-05, + "loss": 3.7305, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2372063526173004e-05, + "loss": 3.7275, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363677578662484e-05, + "loss": 3.7366, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.23553080099557e-05, + "loss": 3.7332, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234692206244517e-05, + "loss": 3.7371, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233853611493465e-05, + "loss": 3.7508, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233015016742413e-05, + "loss": 3.7495, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232178059871735e-05, + "loss": 3.7434, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231339465120682e-05, + "loss": 3.7387, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.23050087036963e-05, + "loss": 3.7432, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229662275618578e-05, + "loss": 3.7283, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288253187479e-05, + "loss": 3.7463, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227986723996847e-05, + "loss": 3.7348, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227148129245796e-05, + "loss": 3.7245, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226309534494744e-05, + "loss": 3.7317, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225470939743692e-05, + "loss": 3.7323, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246339828730126e-05, + "loss": 3.7344, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237953881219606e-05, + "loss": 3.7429, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229567933709086e-05, + "loss": 3.7409, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221181986198566e-05, + "loss": 3.7402, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212812417491775e-05, + "loss": 3.728, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204426469981255e-05, + "loss": 3.749, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2196040522470735e-05, + "loss": 3.7314, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187654574960215e-05, + "loss": 3.7241, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179285006253424e-05, + "loss": 3.73, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217089905874291e-05, + "loss": 3.7257, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216251311123239e-05, + "loss": 3.7348, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215412716372187e-05, + "loss": 3.7426, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214575759501508e-05, + "loss": 3.7285, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213737164750456e-05, + "loss": 3.7308, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212898569999404e-05, + "loss": 3.7385, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212059975248352e-05, + "loss": 3.7421, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112213804973e-05, + "loss": 3.7379, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210382785746248e-05, + "loss": 3.724, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209545828875569e-05, + "loss": 3.7013, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208707234124517e-05, + "loss": 3.7447, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207868639373465e-05, + "loss": 3.7369, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207030044622413e-05, + "loss": 3.7338, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061930877517345e-05, + "loss": 3.7267, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053544930006824e-05, + "loss": 3.7233, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045158982496304e-05, + "loss": 3.7148, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036773034985784e-05, + "loss": 3.7238, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028387087475264e-05, + "loss": 3.7213, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2020017518768473e-05, + "loss": 3.7262, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011631571257953e-05, + "loss": 3.7372, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200324562374743e-05, + "loss": 3.7178, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199485967623691e-05, + "loss": 3.7147, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198649010753012e-05, + "loss": 3.7326, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.19781041600196e-05, + "loss": 3.7165, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196971821250908e-05, + "loss": 3.7143, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196133226499856e-05, + "loss": 3.7275, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195296269629178e-05, + "loss": 3.7238, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194457674878126e-05, + "loss": 3.7155, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193619080127074e-05, + "loss": 3.7147, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192780485376022e-05, + "loss": 3.7153, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.19194189062497e-05, + "loss": 3.7271, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191104933754291e-05, + "loss": 3.7239, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190266339003239e-05, + "loss": 3.7216, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189427744252187e-05, + "loss": 3.7257, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188589149501135e-05, + "loss": 3.7321, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877521926304556e-05, + "loss": 3.7291, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1869135978794036e-05, + "loss": 3.714, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860750031283516e-05, + "loss": 3.7286, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1852364083772996e-05, + "loss": 3.7283, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184399451506621e-05, + "loss": 3.7069, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183560856755569e-05, + "loss": 3.7276, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182722262004517e-05, + "loss": 3.723, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181883667253465e-05, + "loss": 3.7276, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181045072502413e-05, + "loss": 3.7193, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180208115631734e-05, + "loss": 3.7042, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179369520880682e-05, + "loss": 3.7136, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.17853092612963e-05, + "loss": 3.7157, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776923313785774e-05, + "loss": 3.7248, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176855374507899e-05, + "loss": 3.7155, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176016779756847e-05, + "loss": 3.7129, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175178185005795e-05, + "loss": 3.7213, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174339590254743e-05, + "loss": 3.7238, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1735026333840645e-05, + "loss": 3.7083, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726640386330125e-05, + "loss": 3.7157, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718254438819605e-05, + "loss": 3.7234, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170986849130908e-05, + "loss": 3.7298, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701498922602294e-05, + "loss": 3.7168, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693112975091774e-05, + "loss": 3.7055, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168472702758125e-05, + "loss": 3.7204, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167634108007073e-05, + "loss": 3.7107, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166797151136394e-05, + "loss": 3.7244, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165958556385342e-05, + "loss": 3.7281, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.16511996163429e-05, + "loss": 3.7127, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164281366883238e-05, + "loss": 3.7106, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163442772132186e-05, + "loss": 3.7176, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162605815261508e-05, + "loss": 3.7011, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161767220510455e-05, + "loss": 3.7197, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160928625759403e-05, + "loss": 3.7014, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160090031008351e-05, + "loss": 3.7224, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159251436257299e-05, + "loss": 3.7052, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.15841447938662e-05, + "loss": 3.7157, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157575884635568e-05, + "loss": 3.7113, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156737289884516e-05, + "loss": 3.7109, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155898695133464e-05, + "loss": 3.7179, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155061738262786e-05, + "loss": 3.7104, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154223143511734e-05, + "loss": 3.7283, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153384548760682e-05, + "loss": 3.7213, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15254595400963e-05, + "loss": 3.7154, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1517089971389506e-05, + "loss": 3.7182, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508704023878986e-05, + "loss": 3.7103, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500318076368466e-05, + "loss": 3.7153, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491932128857946e-05, + "loss": 3.7113, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483562560151155e-05, + "loss": 3.7115, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475176612640635e-05, + "loss": 3.7131, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466790665130115e-05, + "loss": 3.712, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458404717619595e-05, + "loss": 3.7122, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.145003514891281e-05, + "loss": 3.7135, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144164920140229e-05, + "loss": 3.71, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143326325389177e-05, + "loss": 3.715, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142487730638125e-05, + "loss": 3.7024, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141650773767446e-05, + "loss": 3.7247, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140812179016394e-05, + "loss": 3.7132, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139973584265342e-05, + "loss": 3.7212, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.13913498951429e-05, + "loss": 3.7005, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138296394763238e-05, + "loss": 3.7163, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137459437892559e-05, + "loss": 3.7175, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136620843141507e-05, + "loss": 3.7178, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135782248390455e-05, + "loss": 3.7023, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349436536394035e-05, + "loss": 3.7212, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1341066967687244e-05, + "loss": 3.7129, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332681020176724e-05, + "loss": 3.7271, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324295072666204e-05, + "loss": 3.7041, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315909125155684e-05, + "loss": 3.7206, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130753955644889e-05, + "loss": 3.713, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129915360893837e-05, + "loss": 3.7105, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129076766142785e-05, + "loss": 3.7131, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128238171391733e-05, + "loss": 3.7174, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127401214521054e-05, + "loss": 3.7167, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126562619770002e-05, + "loss": 3.6957, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.12572402501895e-05, + "loss": 3.7174, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8659157752990723, + "eval_runtime": 305.0055, + "eval_samples_per_second": 1251.095, + "eval_steps_per_second": 39.098, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124885430267898e-05, + "loss": 3.7047, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.12404847339722e-05, + "loss": 3.697, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123209878646168e-05, + "loss": 3.7118, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122371283895116e-05, + "loss": 3.7218, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121532689144064e-05, + "loss": 3.7162, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120695732273385e-05, + "loss": 3.7048, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119857137522333e-05, + "loss": 3.7101, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119018542771281e-05, + "loss": 3.6964, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118179948020229e-05, + "loss": 3.7127, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1173429911495496e-05, + "loss": 3.7121, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1165043963984976e-05, + "loss": 3.7105, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156658016474456e-05, + "loss": 3.7121, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148272068963936e-05, + "loss": 3.7, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113988612145342e-05, + "loss": 3.7019, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113151655274663e-05, + "loss": 3.7008, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112313060523611e-05, + "loss": 3.6929, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111474465772559e-05, + "loss": 3.703, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110635871021507e-05, + "loss": 3.6989, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109798914150828e-05, + "loss": 3.7028, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108960319399776e-05, + "loss": 3.714, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108121724648724e-05, + "loss": 3.7158, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107283129897672e-05, + "loss": 3.7109, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106446173026993e-05, + "loss": 3.7009, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105607578275941e-05, + "loss": 3.7082, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104768983524889e-05, + "loss": 3.6976, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039303887738376e-05, + "loss": 3.7112, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030934319031585e-05, + "loss": 3.703, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1022548371521065e-05, + "loss": 3.6937, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1014162424010545e-05, + "loss": 3.7012, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005776476500025e-05, + "loss": 3.6932, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997406907793234e-05, + "loss": 3.699, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0989020960282714e-05, + "loss": 3.7112, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980635012772194e-05, + "loss": 3.7051, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972249065261674e-05, + "loss": 3.7049, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096387949655488e-05, + "loss": 3.6936, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095549354904436e-05, + "loss": 3.7158, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094710760153384e-05, + "loss": 3.7013, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093872165402333e-05, + "loss": 3.6904, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093035208531654e-05, + "loss": 3.6988, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092196613780602e-05, + "loss": 3.6906, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.09135801902955e-05, + "loss": 3.6991, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090519424278498e-05, + "loss": 3.7051, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089682467407819e-05, + "loss": 3.7011, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088843872656767e-05, + "loss": 3.6957, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.088005277905715e-05, + "loss": 3.7072, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087166683154663e-05, + "loss": 3.7066, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.08632808840361e-05, + "loss": 3.7077, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085491131532932e-05, + "loss": 3.6893, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.08465253678188e-05, + "loss": 3.6661, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0838139420308277e-05, + "loss": 3.7144, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829753472797757e-05, + "loss": 3.6994, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082138390409097e-05, + "loss": 3.7026, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081299795658045e-05, + "loss": 3.6968, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0804612009069926e-05, + "loss": 3.6849, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0796226061559406e-05, + "loss": 3.6856, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078785649285262e-05, + "loss": 3.6915, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.07794705453421e-05, + "loss": 3.6861, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0771084597831575e-05, + "loss": 3.6903, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762698650321054e-05, + "loss": 3.7091, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075432908161427e-05, + "loss": 3.6847, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074594313410375e-05, + "loss": 3.6801, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073755718659323e-05, + "loss": 3.7046, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072917123908271e-05, + "loss": 3.6799, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720801670375926e-05, + "loss": 3.6813, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.07124157228654e-05, + "loss": 3.6948, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070402977535488e-05, + "loss": 3.6916, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069564382784436e-05, + "loss": 3.68, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0687274259137575e-05, + "loss": 3.6896, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067888831162705e-05, + "loss": 3.6807, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067050236411653e-05, + "loss": 3.692, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066211641660601e-05, + "loss": 3.6934, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065373046909549e-05, + "loss": 3.6877, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645360900388704e-05, + "loss": 3.695, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636974952878184e-05, + "loss": 3.6955, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628589005367664e-05, + "loss": 3.7008, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620203057857144e-05, + "loss": 3.6813, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061183348915035e-05, + "loss": 3.6943, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060344754163983e-05, + "loss": 3.6975, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059506159412931e-05, + "loss": 3.6736, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058667564661879e-05, + "loss": 3.699, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578306077912e-05, + "loss": 3.6886, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056992013040148e-05, + "loss": 3.6958, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056153418289096e-05, + "loss": 3.6901, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055314823538044e-05, + "loss": 3.6749, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054477866667366e-05, + "loss": 3.6748, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053639271916314e-05, + "loss": 3.6846, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052800677165262e-05, + "loss": 3.6945, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.05196208241421e-05, + "loss": 3.6824, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0511251255435307e-05, + "loss": 3.6819, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502865307924787e-05, + "loss": 3.6888, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.0494479360414267e-05, + "loss": 3.6899, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.0486093412903746e-05, + "loss": 3.6803, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0477723844196956e-05, + "loss": 3.681, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469337896686436e-05, + "loss": 3.6929, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460951949175915e-05, + "loss": 3.6949, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452566001665395e-05, + "loss": 3.6894, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044419643295861e-05, + "loss": 3.6729, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043581048544809e-05, + "loss": 3.6886, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042742453793757e-05, + "loss": 3.6796, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041903859042705e-05, + "loss": 3.6933, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041066902172026e-05, + "loss": 3.6896, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040228307420974e-05, + "loss": 3.6842, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039389712669922e-05, + "loss": 3.6818, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.03855111791887e-05, + "loss": 3.6806, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037714161048191e-05, + "loss": 3.675, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036875566297139e-05, + "loss": 3.6856, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036036971546087e-05, + "loss": 3.6735, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035198376795035e-05, + "loss": 3.6912, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343614199243565e-05, + "loss": 3.6774, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335228251733045e-05, + "loss": 3.6806, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326842304222525e-05, + "loss": 3.6786, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318456356712005e-05, + "loss": 3.6753, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0310086788005214e-05, + "loss": 3.6905, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301700840494694e-05, + "loss": 3.681, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293314892984174e-05, + "loss": 3.697, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284928945473654e-05, + "loss": 3.6906, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027655937676686e-05, + "loss": 3.6841, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026817342925634e-05, + "loss": 3.6841, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025978748174582e-05, + "loss": 3.6817, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.02514015342353e-05, + "loss": 3.6819, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024303196552852e-05, + "loss": 3.6842, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234646018018e-05, + "loss": 3.6783, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022626007050748e-05, + "loss": 3.6819, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021787412299696e-05, + "loss": 3.6823, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020950455429017e-05, + "loss": 3.6812, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020111860677965e-05, + "loss": 3.6838, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019273265926913e-05, + "loss": 3.6757, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018434671175861e-05, + "loss": 3.6827, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175977143051817e-05, + "loss": 3.6759, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167591195541297e-05, + "loss": 3.6942, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159205248030776e-05, + "loss": 3.6826, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150819300520256e-05, + "loss": 3.6884, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014244973181347e-05, + "loss": 3.673, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013406378430295e-05, + "loss": 3.6843, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012567783679243e-05, + "loss": 3.6844, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011729188928191e-05, + "loss": 3.6851, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010892232057512e-05, + "loss": 3.6746, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.01005363730646e-05, + "loss": 3.6881, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009215042555408e-05, + "loss": 3.6794, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008376447804356e-05, + "loss": 3.7008, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007539490933677e-05, + "loss": 3.6735, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006700896182625e-05, + "loss": 3.6899, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005862301431573e-05, + "loss": 3.682, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005023706680521e-05, + "loss": 3.6808, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041867498098426e-05, + "loss": 3.6824, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033481550587906e-05, + "loss": 3.6864, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0025095603077386e-05, + "loss": 3.6858, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016709655566866e-05, + "loss": 3.6661, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008340086860075e-05, + "loss": 3.6872, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.85886812210083, + "eval_runtime": 303.7232, + "eval_samples_per_second": 1256.377, + "eval_steps_per_second": 39.263, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999954139349555e-05, + "loss": 3.6706, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991568191839035e-05, + "loss": 3.6672, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983182244328515e-05, + "loss": 3.6789, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974796296817995e-05, + "loss": 3.6933, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9966426728111204e-05, + "loss": 3.6888, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9958040780600684e-05, + "loss": 3.673, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9949654833090164e-05, + "loss": 3.6847, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941268885579644e-05, + "loss": 3.6653, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993289931687286e-05, + "loss": 3.6803, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992451336936234e-05, + "loss": 3.6857, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991612742185182e-05, + "loss": 3.6777, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.99077414743413e-05, + "loss": 3.6793, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989937190563451e-05, + "loss": 3.6781, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989098595812399e-05, + "loss": 3.6707, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988260001061347e-05, + "loss": 3.6669, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987421406310295e-05, + "loss": 3.6646, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986584449439616e-05, + "loss": 3.6704, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985745854688564e-05, + "loss": 3.6744, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984907259937512e-05, + "loss": 3.6681, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.98406866518646e-05, + "loss": 3.6841, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983231708315781e-05, + "loss": 3.6869, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982393113564729e-05, + "loss": 3.6837, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981554518813677e-05, + "loss": 3.6731, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9807159240626246e-05, + "loss": 3.6749, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979878967191946e-05, + "loss": 3.6746, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979040372440894e-05, + "loss": 3.6747, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978201777689842e-05, + "loss": 3.676, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773631829387895e-05, + "loss": 3.6668, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976526226068111e-05, + "loss": 3.6692, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975687631317059e-05, + "loss": 3.6672, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974849036566007e-05, + "loss": 3.6663, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.974010441814955e-05, + "loss": 3.6815, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973173484944277e-05, + "loss": 3.6786, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972334890193225e-05, + "loss": 3.6759, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971496295442172e-05, + "loss": 3.6673, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.97065770069112e-05, + "loss": 3.6794, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9698207438204416e-05, + "loss": 3.673, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689821490693896e-05, + "loss": 3.6645, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968143554318337e-05, + "loss": 3.6696, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967304959567285e-05, + "loss": 3.6604, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664680026966065e-05, + "loss": 3.6679, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9656294079455545e-05, + "loss": 3.6764, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.9647908131945025e-05, + "loss": 3.67, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639522184434505e-05, + "loss": 3.6706, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963115261572772e-05, + "loss": 3.6794, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622766668217194e-05, + "loss": 3.6752, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614380720706674e-05, + "loss": 3.6745, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605994773196154e-05, + "loss": 3.6661, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959762520448937e-05, + "loss": 3.6389, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958923925697884e-05, + "loss": 3.682, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958085330946832e-05, + "loss": 3.6685, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95724673619578e-05, + "loss": 3.6741, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956409779325101e-05, + "loss": 3.6704, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.95557118457405e-05, + "loss": 3.6586, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954732589822998e-05, + "loss": 3.6532, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953893995071946e-05, + "loss": 3.6632, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953057038201267e-05, + "loss": 3.659, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952218443450215e-05, + "loss": 3.6599, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951379848699163e-05, + "loss": 3.6798, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950541253948111e-05, + "loss": 3.6575, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9497042970774316e-05, + "loss": 3.6514, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488657023263796e-05, + "loss": 3.6766, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480271075753276e-05, + "loss": 3.6496, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471885128242756e-05, + "loss": 3.6526, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463515559535965e-05, + "loss": 3.6698, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945512961202545e-05, + "loss": 3.6649, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944674366451493e-05, + "loss": 3.653, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943835771700441e-05, + "loss": 3.6574, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942998814829762e-05, + "loss": 3.6536, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.94216022007871e-05, + "loss": 3.6642, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941321625327658e-05, + "loss": 3.6603, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940483030576606e-05, + "loss": 3.6599, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939646073705927e-05, + "loss": 3.6657, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938807478954875e-05, + "loss": 3.6678, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937968884203823e-05, + "loss": 3.6733, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937130289452771e-05, + "loss": 3.6527, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936293332582092e-05, + "loss": 3.6678, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.93545473783104e-05, + "loss": 3.669, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9346161430799886e-05, + "loss": 3.6441, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337775483289366e-05, + "loss": 3.6684, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329405914582575e-05, + "loss": 3.6654, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9321019967072055e-05, + "loss": 3.6701, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312634019561535e-05, + "loss": 3.6611, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304248072051015e-05, + "loss": 3.6506, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295878503344224e-05, + "loss": 3.6423, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287492555833704e-05, + "loss": 3.6585, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9279106608323184e-05, + "loss": 3.6669, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270720660812664e-05, + "loss": 3.6555, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926235109210587e-05, + "loss": 3.652, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925396514459535e-05, + "loss": 3.6593, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924557919708484e-05, + "loss": 3.6673, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923719324957432e-05, + "loss": 3.6537, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922882368086753e-05, + "loss": 3.6556, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922043773335701e-05, + "loss": 3.6621, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921205178584649e-05, + "loss": 3.6702, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920366583833597e-05, + "loss": 3.6595, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919529626962918e-05, + "loss": 3.6505, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918691032211866e-05, + "loss": 3.6543, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917852437460814e-05, + "loss": 3.6538, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.917013842709762e-05, + "loss": 3.6651, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161768858390826e-05, + "loss": 3.6642, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153382910880306e-05, + "loss": 3.6585, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914499696336979e-05, + "loss": 3.652, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913661101585927e-05, + "loss": 3.6508, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912824144715248e-05, + "loss": 3.6521, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911985549964196e-05, + "loss": 3.657, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911146955213144e-05, + "loss": 3.6455, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910308360462092e-05, + "loss": 3.6678, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909471403591413e-05, + "loss": 3.6501, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908632808840361e-05, + "loss": 3.6532, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907794214089309e-05, + "loss": 3.6496, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906955619338257e-05, + "loss": 3.6463, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906118662467578e-05, + "loss": 3.6661, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905280067716526e-05, + "loss": 3.6491, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904441472965475e-05, + "loss": 3.6716, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903602878214423e-05, + "loss": 3.6643, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027659213437436e-05, + "loss": 3.657, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019273265926916e-05, + "loss": 3.655, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010887318416396e-05, + "loss": 3.6606, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002501370905876e-05, + "loss": 3.6534, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8994131802199085e-05, + "loss": 3.6587, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985745854688565e-05, + "loss": 3.6519, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977359907178045e-05, + "loss": 3.6581, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968973959667525e-05, + "loss": 3.6522, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960604390960734e-05, + "loss": 3.6565, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8952218443450214e-05, + "loss": 3.6576, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.89438324959397e-05, + "loss": 3.647, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893544654842918e-05, + "loss": 3.6598, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892707697972239e-05, + "loss": 3.6479, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891869103221187e-05, + "loss": 3.6655, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891030508470135e-05, + "loss": 3.6575, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890191913719083e-05, + "loss": 3.6596, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889354956848404e-05, + "loss": 3.6453, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888516362097352e-05, + "loss": 3.6632, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876777673463e-05, + "loss": 3.6534, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886840810475621e-05, + "loss": 3.6584, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.886002215724569e-05, + "loss": 3.6492, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885163620973517e-05, + "loss": 3.6592, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843250262224654e-05, + "loss": 3.6558, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883488069351786e-05, + "loss": 3.6744, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882649474600734e-05, + "loss": 3.6467, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881810879849682e-05, + "loss": 3.6615, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.88097228509863e-05, + "loss": 3.6566, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880135328227951e-05, + "loss": 3.6585, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879298371357272e-05, + "loss": 3.6521, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.87845977660622e-05, + "loss": 3.6607, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877621181855168e-05, + "loss": 3.6577, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876782587104116e-05, + "loss": 3.6461, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875943992353064e-05, + "loss": 3.6568, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8543734550476074, + "eval_runtime": 305.9458, + "eval_samples_per_second": 1247.25, + "eval_steps_per_second": 38.977, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875105397602012e-05, + "loss": 3.6469, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874266802850961e-05, + "loss": 3.6401, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873428208099909e-05, + "loss": 3.652, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.87259125122923e-05, + "loss": 3.6699, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871752656478178e-05, + "loss": 3.6639, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870914061727126e-05, + "loss": 3.6425, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870075466976074e-05, + "loss": 3.6586, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8692385101053946e-05, + "loss": 3.6423, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683999153543426e-05, + "loss": 3.6521, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675629584836635e-05, + "loss": 3.6626, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8667243637326115e-05, + "loss": 3.6498, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8658857689815595e-05, + "loss": 3.6515, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8650471742305075e-05, + "loss": 3.6543, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8642085794794555e-05, + "loss": 3.6446, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863369984728404e-05, + "loss": 3.6431, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862533027857725e-05, + "loss": 3.6379, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861694433106673e-05, + "loss": 3.6436, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860855838355621e-05, + "loss": 3.6503, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.860017243604569e-05, + "loss": 3.642, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591786488535164e-05, + "loss": 3.6582, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8583400541024643e-05, + "loss": 3.6603, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8575014593514123e-05, + "loss": 3.6577, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856664502480733e-05, + "loss": 3.6495, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855825907729681e-05, + "loss": 3.645, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854987312978629e-05, + "loss": 3.6517, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854148718227578e-05, + "loss": 3.6496, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853311761356899e-05, + "loss": 3.6472, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852473166605847e-05, + "loss": 3.6453, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851634571854795e-05, + "loss": 3.6415, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850795977103743e-05, + "loss": 3.6436, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849959020233064e-05, + "loss": 3.6426, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849120425482012e-05, + "loss": 3.653, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84828183073096e-05, + "loss": 3.6598, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847443235979908e-05, + "loss": 3.6476, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8466062791092286e-05, + "loss": 3.6452, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457676843581766e-05, + "loss": 3.6438, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449290896071246e-05, + "loss": 3.6538, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844090494856073e-05, + "loss": 3.64, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843253537985394e-05, + "loss": 3.6445, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842414943234342e-05, + "loss": 3.6339, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.84157634848329e-05, + "loss": 3.6477, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840737753732238e-05, + "loss": 3.6463, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839900796861559e-05, + "loss": 3.6468, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839062202110507e-05, + "loss": 3.646, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838223607359455e-05, + "loss": 3.6505, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837385012608403e-05, + "loss": 3.6507, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836548055737724e-05, + "loss": 3.652, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835709460986672e-05, + "loss": 3.6414, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.83487086623562e-05, + "loss": 3.6125, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340322714845687e-05, + "loss": 3.6538, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331953146138896e-05, + "loss": 3.6448, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323567198628376e-05, + "loss": 3.6492, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8315181251117856e-05, + "loss": 3.6464, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306795303607335e-05, + "loss": 3.6352, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298425734900545e-05, + "loss": 3.6292, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8290039787390025e-05, + "loss": 3.6367, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281653839879504e-05, + "loss": 3.6361, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8273267892368984e-05, + "loss": 3.6341, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8264898323662194e-05, + "loss": 3.6545, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8256512376151674e-05, + "loss": 3.6379, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8248126428641153e-05, + "loss": 3.6204, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823974048113064e-05, + "loss": 3.6538, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823137091242385e-05, + "loss": 3.6257, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822298496491333e-05, + "loss": 3.6255, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821459901740281e-05, + "loss": 3.6444, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820621306989229e-05, + "loss": 3.6369, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.81978435011855e-05, + "loss": 3.6337, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818945755367498e-05, + "loss": 3.6324, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818107160616446e-05, + "loss": 3.6316, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817268565865394e-05, + "loss": 3.6391, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816431608994715e-05, + "loss": 3.6352, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815593014243663e-05, + "loss": 3.6393, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814754419492611e-05, + "loss": 3.6388, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8139158247415594e-05, + "loss": 3.6418, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81307886787088e-05, + "loss": 3.6511, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812240273119828e-05, + "loss": 3.6276, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811401678368776e-05, + "loss": 3.6421, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810563083617724e-05, + "loss": 3.6456, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809726126747045e-05, + "loss": 3.62, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808887531995993e-05, + "loss": 3.6389, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808048937244941e-05, + "loss": 3.6425, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807210342493889e-05, + "loss": 3.6432, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.80637338562321e-05, + "loss": 3.6426, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805534790872158e-05, + "loss": 3.6221, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804696196121106e-05, + "loss": 3.6172, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803857601370055e-05, + "loss": 3.6378, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.803020644499376e-05, + "loss": 3.6408, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021820497483237e-05, + "loss": 3.6271, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013434549972717e-05, + "loss": 3.633, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8005048602462196e-05, + "loss": 3.6318, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996679033755406e-05, + "loss": 3.6431, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7988293086244886e-05, + "loss": 3.6331, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979907138734366e-05, + "loss": 3.6329, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971521191223845e-05, + "loss": 3.6325, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7963151622517055e-05, + "loss": 3.6445, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954765675006535e-05, + "loss": 3.638, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946379727496014e-05, + "loss": 3.6245, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.79379937799855e-05, + "loss": 3.6313, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792962421127871e-05, + "loss": 3.6309, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792123826376819e-05, + "loss": 3.6401, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791285231625767e-05, + "loss": 3.638, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790446636874715e-05, + "loss": 3.6342, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789609680004036e-05, + "loss": 3.6297, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788771085252984e-05, + "loss": 3.6258, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787934128382305e-05, + "loss": 3.6315, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787095533631253e-05, + "loss": 3.6277, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786256938880201e-05, + "loss": 3.6242, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785418344129149e-05, + "loss": 3.6424, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784579749378097e-05, + "loss": 3.627, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7837411546270455e-05, + "loss": 3.6303, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7829025598759935e-05, + "loss": 3.627, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7820639651249415e-05, + "loss": 3.6219, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7812270082542624e-05, + "loss": 3.6413, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7803884135032104e-05, + "loss": 3.6276, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795498187521584e-05, + "loss": 3.6452, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7787112240011064e-05, + "loss": 3.6387, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777874267130427e-05, + "loss": 3.6349, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777035672379375e-05, + "loss": 3.6318, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776197077628323e-05, + "loss": 3.6364, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775358482877271e-05, + "loss": 3.6259, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774521526006592e-05, + "loss": 3.6366, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.77368293125554e-05, + "loss": 3.6312, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772845974384862e-05, + "loss": 3.6302, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.77200737963381e-05, + "loss": 3.6258, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771168784882758e-05, + "loss": 3.6331, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770330190131706e-05, + "loss": 3.6341, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769491595380654e-05, + "loss": 3.6247, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768653000629601e-05, + "loss": 3.6365, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767814405878549e-05, + "loss": 3.6175, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766975811127497e-05, + "loss": 3.6494, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7661388542568186e-05, + "loss": 3.6309, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765300259505766e-05, + "loss": 3.6367, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764461664754714e-05, + "loss": 3.6227, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7636230700036626e-05, + "loss": 3.6386, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627861131329835e-05, + "loss": 3.6287, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619475183819315e-05, + "loss": 3.6351, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7611089236308795e-05, + "loss": 3.6276, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760271966760201e-05, + "loss": 3.6313, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7594333720091484e-05, + "loss": 3.6325, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585947772580964e-05, + "loss": 3.6525, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577561825070444e-05, + "loss": 3.6231, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756919225636366e-05, + "loss": 3.6394, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756080630885313e-05, + "loss": 3.6346, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755242036134261e-05, + "loss": 3.633, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754405079263583e-05, + "loss": 3.626, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753566484512531e-05, + "loss": 3.6368, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752727889761479e-05, + "loss": 3.6313, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751889295010427e-05, + "loss": 3.6252, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751050700259375e-05, + "loss": 3.6319, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.851743459701538, + "eval_runtime": 306.1531, + "eval_samples_per_second": 1246.406, + "eval_steps_per_second": 38.951, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750212105508323e-05, + "loss": 3.6235, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749373510757271e-05, + "loss": 3.6145, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748534916006219e-05, + "loss": 3.6315, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747696321255167e-05, + "loss": 3.6447, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746859364384488e-05, + "loss": 3.6423, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.746020769633436e-05, + "loss": 3.6249, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745182174882384e-05, + "loss": 3.6314, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744343580131332e-05, + "loss": 3.6227, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7435066232606534e-05, + "loss": 3.6254, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7426680285096014e-05, + "loss": 3.6383, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7418294337585494e-05, + "loss": 3.6292, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409908390074973e-05, + "loss": 3.6302, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740153882136818e-05, + "loss": 3.633, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739316925266139e-05, + "loss": 3.6209, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738478330515087e-05, + "loss": 3.618, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737639735764035e-05, + "loss": 3.6121, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736801141012983e-05, + "loss": 3.624, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735962546261931e-05, + "loss": 3.6276, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735123951510879e-05, + "loss": 3.6172, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734285356759827e-05, + "loss": 3.6323, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733446762008775e-05, + "loss": 3.6374, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732609805138097e-05, + "loss": 3.6326, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731771210387045e-05, + "loss": 3.6271, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730932615635993e-05, + "loss": 3.6253, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730094020884941e-05, + "loss": 3.6292, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292570640142616e-05, + "loss": 3.6276, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7284184692632096e-05, + "loss": 3.6217, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275798745121576e-05, + "loss": 3.62, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267412797611056e-05, + "loss": 3.6237, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7259043228904265e-05, + "loss": 3.6193, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250657281393745e-05, + "loss": 3.6208, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7242271333883225e-05, + "loss": 3.6283, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233885386372705e-05, + "loss": 3.6316, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722551581766592e-05, + "loss": 3.6299, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.72171298701554e-05, + "loss": 3.6166, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720874392264488e-05, + "loss": 3.6268, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720035797513436e-05, + "loss": 3.6307, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719198840642757e-05, + "loss": 3.6128, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718360245891705e-05, + "loss": 3.624, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717521651140653e-05, + "loss": 3.6123, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716684694269974e-05, + "loss": 3.6248, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715846099518922e-05, + "loss": 3.6201, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.71500750476787e-05, + "loss": 3.6235, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714168910016818e-05, + "loss": 3.6258, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7133319531461395e-05, + "loss": 3.6283, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124933583950875e-05, + "loss": 3.6296, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116547636440355e-05, + "loss": 3.6312, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7108161688929834e-05, + "loss": 3.6186, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7099792120223044e-05, + "loss": 3.5937, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7091406172712524e-05, + "loss": 3.6312, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7083020225202003e-05, + "loss": 3.621, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074634277691483e-05, + "loss": 3.626, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706626470898469e-05, + "loss": 3.6231, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705787876147417e-05, + "loss": 3.614, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704949281396365e-05, + "loss": 3.6039, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704110686645313e-05, + "loss": 3.6137, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703273729774635e-05, + "loss": 3.6173, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702435135023583e-05, + "loss": 3.6055, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701596540272531e-05, + "loss": 3.6329, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700757945521479e-05, + "loss": 3.6162, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6999209886508e-05, + "loss": 3.6006, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699082393899748e-05, + "loss": 3.6276, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698243799148696e-05, + "loss": 3.6063, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697405204397644e-05, + "loss": 3.605, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6965682475269646e-05, + "loss": 3.6199, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6957296527759126e-05, + "loss": 3.6147, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6948910580248606e-05, + "loss": 3.6098, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940524632738086e-05, + "loss": 3.608, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6932155064031295e-05, + "loss": 3.6089, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692376911652078e-05, + "loss": 3.6131, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691538316901026e-05, + "loss": 3.6196, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690699722149974e-05, + "loss": 3.6147, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689862765279295e-05, + "loss": 3.6175, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.689024170528243e-05, + "loss": 3.6122, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688185575777191e-05, + "loss": 3.6324, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873469810261384e-05, + "loss": 3.6096, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.68651002415546e-05, + "loss": 3.6198, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685671429404408e-05, + "loss": 3.6184, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684832834653356e-05, + "loss": 3.6053, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683994239902303e-05, + "loss": 3.6152, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683157283031625e-05, + "loss": 3.6192, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6823186882805736e-05, + "loss": 3.6193, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814800935295216e-05, + "loss": 3.6222, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680641498778469e-05, + "loss": 3.5969, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6798045419077905e-05, + "loss": 3.5993, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789659471567385e-05, + "loss": 3.6138, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678127352405686e-05, + "loss": 3.6185, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677288757654634e-05, + "loss": 3.6056, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764518007839554e-05, + "loss": 3.6117, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6756132060329033e-05, + "loss": 3.6114, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674774611281851e-05, + "loss": 3.6194, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673936016530799e-05, + "loss": 3.6102, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.67309905966012e-05, + "loss": 3.6099, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672260464909069e-05, + "loss": 3.6139, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671421870158016e-05, + "loss": 3.621, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670584913287338e-05, + "loss": 3.6164, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669746318536286e-05, + "loss": 3.601, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668907723785233e-05, + "loss": 3.6069, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668069129034181e-05, + "loss": 3.6118, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667232172163503e-05, + "loss": 3.6179, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666393577412451e-05, + "loss": 3.6175, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665554982661398e-05, + "loss": 3.6141, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664716387910346e-05, + "loss": 3.6064, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638794310396676e-05, + "loss": 3.6033, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630408362886156e-05, + "loss": 3.6108, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6622022415375636e-05, + "loss": 3.6045, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613636467865116e-05, + "loss": 3.6051, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660526689915833e-05, + "loss": 3.6187, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596880951647805e-05, + "loss": 3.606, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588495004137285e-05, + "loss": 3.6065, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6580109056626765e-05, + "loss": 3.604, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657173948791998e-05, + "loss": 3.6002, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6563353540409454e-05, + "loss": 3.6197, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6554967592898934e-05, + "loss": 3.6115, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6546581645388414e-05, + "loss": 3.6178, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653821207668163e-05, + "loss": 3.6174, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652982612917111e-05, + "loss": 3.6159, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652144018166059e-05, + "loss": 3.6104, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651305423415007e-05, + "loss": 3.6144, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650468466544328e-05, + "loss": 3.6073, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649629871793276e-05, + "loss": 3.6146, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648791277042224e-05, + "loss": 3.6069, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647952682291172e-05, + "loss": 3.6133, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647115725420493e-05, + "loss": 3.6022, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646277130669441e-05, + "loss": 3.6132, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645438535918389e-05, + "loss": 3.6086, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644599941167337e-05, + "loss": 3.6067, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437629842966584e-05, + "loss": 3.6109, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6429243895456064e-05, + "loss": 3.5964, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420857947945543e-05, + "loss": 3.6284, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412472000435023e-05, + "loss": 3.6078, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640410243172823e-05, + "loss": 3.6184, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639571648421771e-05, + "loss": 3.6013, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638733053670719e-05, + "loss": 3.6129, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637894458919667e-05, + "loss": 3.6114, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637057502048988e-05, + "loss": 3.6142, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636218907297936e-05, + "loss": 3.6058, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635380312546884e-05, + "loss": 3.6079, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634541717795832e-05, + "loss": 3.614, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633704760925154e-05, + "loss": 3.6329, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632866166174102e-05, + "loss": 3.5988, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.63202757142305e-05, + "loss": 3.62, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631188976671998e-05, + "loss": 3.6141, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303520198013186e-05, + "loss": 3.6073, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.62951506293064e-05, + "loss": 3.6072, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286764681795875e-05, + "loss": 3.6149, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278378734285355e-05, + "loss": 3.613, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269992786774835e-05, + "loss": 3.6099, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261606839264315e-05, + "loss": 3.6089, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8503987789154053, + "eval_runtime": 316.5647, + "eval_samples_per_second": 1205.412, + "eval_steps_per_second": 37.67, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6253220891753795e-05, + "loss": 3.6042, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244834944243275e-05, + "loss": 3.5935, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236448996732755e-05, + "loss": 3.6098, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622807942802597e-05, + "loss": 3.6216, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621969348051545e-05, + "loss": 3.6232, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621130753300493e-05, + "loss": 3.6023, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620292158549441e-05, + "loss": 3.6143, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619455201678762e-05, + "loss": 3.6027, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.61861660692771e-05, + "loss": 3.6025, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617779650057031e-05, + "loss": 3.6138, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616941055305979e-05, + "loss": 3.6145, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616102460554927e-05, + "loss": 3.6128, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615263865803875e-05, + "loss": 3.6069, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6144269089331965e-05, + "loss": 3.6001, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135883141821445e-05, + "loss": 3.6003, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127497194310925e-05, + "loss": 3.588, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6119111246800404e-05, + "loss": 3.6068, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110725299289884e-05, + "loss": 3.6053, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6102339351779364e-05, + "loss": 3.5956, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093953404268844e-05, + "loss": 3.6098, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085567456758324e-05, + "loss": 3.6186, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607719788805153e-05, + "loss": 3.6097, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606881194054101e-05, + "loss": 3.6084, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606042599303049e-05, + "loss": 3.6029, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605204004551997e-05, + "loss": 3.6108, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604367047681318e-05, + "loss": 3.6063, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603528452930266e-05, + "loss": 3.6006, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602689858179214e-05, + "loss": 3.5981, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601851263428163e-05, + "loss": 3.6019, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.601014306557484e-05, + "loss": 3.5984, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600175711806432e-05, + "loss": 3.6056, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.59933711705538e-05, + "loss": 3.6049, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598498522304328e-05, + "loss": 3.6052, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597661565433649e-05, + "loss": 3.6133, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596822970682597e-05, + "loss": 3.5957, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595984375931545e-05, + "loss": 3.6058, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595145781180493e-05, + "loss": 3.6095, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5943088243098136e-05, + "loss": 3.5916, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934702295587616e-05, + "loss": 3.6039, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5926316348077096e-05, + "loss": 3.5931, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591793040056658e-05, + "loss": 3.5996, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590956083185979e-05, + "loss": 3.6009, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590117488434927e-05, + "loss": 3.6035, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589278893683875e-05, + "loss": 3.6063, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588441936813196e-05, + "loss": 3.6059, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587603342062144e-05, + "loss": 3.6087, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586764747311092e-05, + "loss": 3.6086, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.58592615256004e-05, + "loss": 3.5998, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585089195689361e-05, + "loss": 3.5741, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584250600938309e-05, + "loss": 3.6121, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583412006187257e-05, + "loss": 3.6007, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582573411436205e-05, + "loss": 3.6087, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5817364545655265e-05, + "loss": 3.6007, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808978598144745e-05, + "loss": 3.5899, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800592650634225e-05, + "loss": 3.5907, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5792206703123705e-05, + "loss": 3.5871, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783837134416914e-05, + "loss": 3.6002, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775451186906394e-05, + "loss": 3.5809, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5767065239395874e-05, + "loss": 3.6179, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758679291885354e-05, + "loss": 3.597, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5750309723178563e-05, + "loss": 3.5761, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574192377566804e-05, + "loss": 3.6072, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573353782815752e-05, + "loss": 3.5852, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5725151880647e-05, + "loss": 3.5865, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571678231194022e-05, + "loss": 3.5959, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.57083963644297e-05, + "loss": 3.5957, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.570001041691918e-05, + "loss": 3.5899, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569162446940865e-05, + "loss": 3.5932, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568325490070187e-05, + "loss": 3.5848, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567486895319135e-05, + "loss": 3.5951, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566648300568083e-05, + "loss": 3.5989, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.56580970581703e-05, + "loss": 3.5923, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564972748946352e-05, + "loss": 3.6008, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5641341541953e-05, + "loss": 3.5894, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563295559444248e-05, + "loss": 3.6158, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562456964693196e-05, + "loss": 3.5861, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561620007822517e-05, + "loss": 3.6039, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560781413071465e-05, + "loss": 3.5899, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599428183204126e-05, + "loss": 3.5895, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5591042235693606e-05, + "loss": 3.5946, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558267266698682e-05, + "loss": 3.5996, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.55742867194763e-05, + "loss": 3.6018, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565900771965775e-05, + "loss": 3.6011, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557514824455255e-05, + "loss": 3.5776, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554914525574847e-05, + "loss": 3.5796, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554075930823795e-05, + "loss": 3.5931, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553237336072743e-05, + "loss": 3.6007, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552398741321691e-05, + "loss": 3.5865, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515617844510126e-05, + "loss": 3.5895, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.55072318969996e-05, + "loss": 3.5924, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549884594948908e-05, + "loss": 3.5944, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549046000197856e-05, + "loss": 3.5932, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5482090433271775e-05, + "loss": 3.5915, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547370448576125e-05, + "loss": 3.5935, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546531853825073e-05, + "loss": 3.6003, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545693259074021e-05, + "loss": 3.6017, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448563022033424e-05, + "loss": 3.5813, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5440177074522904e-05, + "loss": 3.5868, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431791127012384e-05, + "loss": 3.593, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.54234215583056e-05, + "loss": 3.5961, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541503561079507e-05, + "loss": 3.5997, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540664966328455e-05, + "loss": 3.5928, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539826371577403e-05, + "loss": 3.5883, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538989414706725e-05, + "loss": 3.586, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538152457836046e-05, + "loss": 3.5894, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537313863084994e-05, + "loss": 3.588, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536475268333942e-05, + "loss": 3.5839, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.53563667358289e-05, + "loss": 3.5961, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534798078831837e-05, + "loss": 3.588, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533961121961159e-05, + "loss": 3.5844, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5331225272101074e-05, + "loss": 3.5858, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532283932459055e-05, + "loss": 3.5788, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531445337708003e-05, + "loss": 3.6002, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530606742956951e-05, + "loss": 3.5906, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529768148205899e-05, + "loss": 3.5983, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528929553454847e-05, + "loss": 3.5938, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528090958703795e-05, + "loss": 3.6005, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5272540018331156e-05, + "loss": 3.5924, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5264154070820636e-05, + "loss": 3.5892, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5255768123310116e-05, + "loss": 3.5947, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5247398554603325e-05, + "loss": 3.5889, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523901260709281e-05, + "loss": 3.5855, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523064303838602e-05, + "loss": 3.5949, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.52222570908755e-05, + "loss": 3.5851, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521387114336498e-05, + "loss": 3.5916, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520548519585446e-05, + "loss": 3.5881, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519709924834394e-05, + "loss": 3.5872, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518871330083342e-05, + "loss": 3.5923, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.51803273533229e-05, + "loss": 3.5807, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517194140581238e-05, + "loss": 3.6059, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516357183710559e-05, + "loss": 3.5889, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515518588959507e-05, + "loss": 3.6, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514679994208455e-05, + "loss": 3.5806, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513841399457403e-05, + "loss": 3.5946, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5130044425867245e-05, + "loss": 3.5927, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121658478356725e-05, + "loss": 3.5936, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5113272530846205e-05, + "loss": 3.5883, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104886583335685e-05, + "loss": 3.5855, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096517014628894e-05, + "loss": 3.5908, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5088131067118374e-05, + "loss": 3.6114, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079745119607854e-05, + "loss": 3.5843, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507137555090106e-05, + "loss": 3.5996, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506298960339054e-05, + "loss": 3.5954, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505462003468375e-05, + "loss": 3.5855, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504623408717323e-05, + "loss": 3.595, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503784813966271e-05, + "loss": 3.5903, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.50294621921522e-05, + "loss": 3.5902, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502107624464168e-05, + "loss": 3.591, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501269029713116e-05, + "loss": 3.5884, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.849526882171631, + "eval_runtime": 310.9633, + "eval_samples_per_second": 1227.125, + "eval_steps_per_second": 38.349, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500430434962064e-05, + "loss": 3.6009, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499591840211012e-05, + "loss": 3.5694, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.49875324545996e-05, + "loss": 3.5882, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497914650708908e-05, + "loss": 3.6055, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497077693838229e-05, + "loss": 3.5981, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496239099087177e-05, + "loss": 3.5856, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495400504336125e-05, + "loss": 3.5988, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494561909585073e-05, + "loss": 3.5811, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.49372331483402e-05, + "loss": 3.5812, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492886357963342e-05, + "loss": 3.5978, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.49204776321229e-05, + "loss": 3.5949, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4912091684612383e-05, + "loss": 3.5882, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903705737101857e-05, + "loss": 3.593, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489533616839507e-05, + "loss": 3.5789, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488695022088455e-05, + "loss": 3.5785, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487856427337403e-05, + "loss": 3.5723, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4870178325863506e-05, + "loss": 3.5866, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861792378352986e-05, + "loss": 3.5886, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4853406430842465e-05, + "loss": 3.5807, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4845020483331945e-05, + "loss": 3.5842, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4836634535821425e-05, + "loss": 3.6059, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4828264967114634e-05, + "loss": 3.5865, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481987901960412e-05, + "loss": 3.5886, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.48114930720936e-05, + "loss": 3.5851, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480310712458308e-05, + "loss": 3.5924, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479473755587629e-05, + "loss": 3.5844, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478635160836577e-05, + "loss": 3.5828, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477796566085525e-05, + "loss": 3.5776, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476957971334473e-05, + "loss": 3.5835, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476121014463794e-05, + "loss": 3.5757, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475282419712742e-05, + "loss": 3.5876, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.47444382496169e-05, + "loss": 3.5831, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473605230210638e-05, + "loss": 3.5901, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472768273339959e-05, + "loss": 3.5917, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4719296785889075e-05, + "loss": 3.5802, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4710910838378555e-05, + "loss": 3.5859, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702524890868035e-05, + "loss": 3.5911, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4694155322161244e-05, + "loss": 3.5712, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4685769374650724e-05, + "loss": 3.5858, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4677383427140204e-05, + "loss": 3.5754, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668997479629684e-05, + "loss": 3.58, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466062791092289e-05, + "loss": 3.5829, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465224196341237e-05, + "loss": 3.5847, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464385601590185e-05, + "loss": 3.5872, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463547006839133e-05, + "loss": 3.5836, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462710049968454e-05, + "loss": 3.591, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461871455217403e-05, + "loss": 3.589, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.461032860466351e-05, + "loss": 3.5834, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460195903595672e-05, + "loss": 3.5545, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.45935730884462e-05, + "loss": 3.5899, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458518714093568e-05, + "loss": 3.5849, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457680119342516e-05, + "loss": 3.588, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4568431624718367e-05, + "loss": 3.5834, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4560045677207847e-05, + "loss": 3.5761, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551659729697326e-05, + "loss": 3.5655, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4543273782186806e-05, + "loss": 3.5725, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534904213480016e-05, + "loss": 3.5785, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526518265969495e-05, + "loss": 3.5615, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451813231845898e-05, + "loss": 3.599, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450974637094846e-05, + "loss": 3.5796, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450137680224167e-05, + "loss": 3.5585, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449299085473115e-05, + "loss": 3.5867, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448460490722063e-05, + "loss": 3.5712, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447621895971011e-05, + "loss": 3.5686, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446784939100332e-05, + "loss": 3.5752, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.44594634434928e-05, + "loss": 3.5797, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445107749598228e-05, + "loss": 3.5628, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444269154847176e-05, + "loss": 3.5806, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443432197976497e-05, + "loss": 3.5668, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442593603225445e-05, + "loss": 3.5748, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417550084743936e-05, + "loss": 3.5819, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4409164137233416e-05, + "loss": 3.5778, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400794568526625e-05, + "loss": 3.5781, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392408621016105e-05, + "loss": 3.5747, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4384022673505585e-05, + "loss": 3.5991, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4375636725995065e-05, + "loss": 3.5653, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4367267157288274e-05, + "loss": 3.5885, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358881209777754e-05, + "loss": 3.5714, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4350495262267234e-05, + "loss": 3.5705, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4342109314756714e-05, + "loss": 3.5784, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433373974604992e-05, + "loss": 3.5762, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.43253537985394e-05, + "loss": 3.5873, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431696785102888e-05, + "loss": 3.5831, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430858190351837e-05, + "loss": 3.5583, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.430021233481158e-05, + "loss": 3.5618, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429182638730106e-05, + "loss": 3.569, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428344043979054e-05, + "loss": 3.5826, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427505449228002e-05, + "loss": 3.5696, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426668492357323e-05, + "loss": 3.5698, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425829897606271e-05, + "loss": 3.5806, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249929407355917e-05, + "loss": 3.5759, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4241543459845397e-05, + "loss": 3.5763, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4233157512334877e-05, + "loss": 3.5719, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224771564824356e-05, + "loss": 3.5764, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4216385617313836e-05, + "loss": 3.58, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420799966980332e-05, + "loss": 3.5833, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.41996137222928e-05, + "loss": 3.5622, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419122777478228e-05, + "loss": 3.5688, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418285820607549e-05, + "loss": 3.5754, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417447225856497e-05, + "loss": 3.5743, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416608631105445e-05, + "loss": 3.5848, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415770036354393e-05, + "loss": 3.5718, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414933079483714e-05, + "loss": 3.5698, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414094484732662e-05, + "loss": 3.5709, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413257527861983e-05, + "loss": 3.5671, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412418933110931e-05, + "loss": 3.5707, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411580338359879e-05, + "loss": 3.5705, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410741743608828e-05, + "loss": 3.5763, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409903148857776e-05, + "loss": 3.5709, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090661919870966e-05, + "loss": 3.5673, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4082275972360446e-05, + "loss": 3.5706, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073890024849926e-05, + "loss": 3.5571, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4065504077339406e-05, + "loss": 3.5791, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405711812982888e-05, + "loss": 3.5769, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404873218231836e-05, + "loss": 3.575, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404034623480784e-05, + "loss": 3.5786, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403196028729732e-05, + "loss": 3.5797, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402359071859053e-05, + "loss": 3.5733, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4015221149883744e-05, + "loss": 3.5694, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400683520237323e-05, + "loss": 3.5776, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3998449254862704e-05, + "loss": 3.5697, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.3990063307352184e-05, + "loss": 3.5702, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39816937386454e-05, + "loss": 3.5769, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397330779113488e-05, + "loss": 3.5678, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396492184362435e-05, + "loss": 3.5751, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395653589611383e-05, + "loss": 3.5682, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394814994860331e-05, + "loss": 3.5708, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393976400109279e-05, + "loss": 3.5747, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931394432386e-05, + "loss": 3.5666, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392300848487548e-05, + "loss": 3.5859, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391462253736497e-05, + "loss": 3.5734, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390623658985445e-05, + "loss": 3.5811, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389785064234393e-05, + "loss": 3.5654, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388946469483341e-05, + "loss": 3.571, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388107874732289e-05, + "loss": 3.5783, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387269279981237e-05, + "loss": 3.5788, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386432323110558e-05, + "loss": 3.5699, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385593728359506e-05, + "loss": 3.5646, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384755133608454e-05, + "loss": 3.5761, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383916538857402e-05, + "loss": 3.5905, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830795819867226e-05, + "loss": 3.5726, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3822409872356706e-05, + "loss": 3.5776, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3814023924846186e-05, + "loss": 3.5791, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805637977335666e-05, + "loss": 3.5706, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379726840862888e-05, + "loss": 3.5781, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378888246111836e-05, + "loss": 3.5738, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378049651360784e-05, + "loss": 3.5716, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377211056609732e-05, + "loss": 3.5766, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.37637246185868e-05, + "loss": 3.566, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.850027084350586, + "eval_runtime": 305.0956, + "eval_samples_per_second": 1250.726, + "eval_steps_per_second": 39.086, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375533867107628e-05, + "loss": 3.5705, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374695272356576e-05, + "loss": 3.5516, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373856677605524e-05, + "loss": 3.5706, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.373019720734845e-05, + "loss": 3.5908, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372182763864166e-05, + "loss": 3.5795, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371344169113114e-05, + "loss": 3.5697, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370505574362062e-05, + "loss": 3.5751, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.36966697961101e-05, + "loss": 3.5661, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3688283848599586e-05, + "loss": 3.5642, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679914279892795e-05, + "loss": 3.5832, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3671528332382275e-05, + "loss": 3.5728, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3663142384871755e-05, + "loss": 3.5738, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654756437361235e-05, + "loss": 3.5752, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3646386868654444e-05, + "loss": 3.5594, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3638000921143924e-05, + "loss": 3.56, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629614973633404e-05, + "loss": 3.5555, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3621229026122884e-05, + "loss": 3.5709, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361284307861236e-05, + "loss": 3.5682, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3604457131101844e-05, + "loss": 3.5642, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3596071183591324e-05, + "loss": 3.5666, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587685236080804e-05, + "loss": 3.5887, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357931566737401e-05, + "loss": 3.5683, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357092971986349e-05, + "loss": 3.5708, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356254377235297e-05, + "loss": 3.5703, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355415782484245e-05, + "loss": 3.5767, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354578825613566e-05, + "loss": 3.5639, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353740230862514e-05, + "loss": 3.5666, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352901636111462e-05, + "loss": 3.568, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.35206304136041e-05, + "loss": 3.5602, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351226084489731e-05, + "loss": 3.5604, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350387489738679e-05, + "loss": 3.5684, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349548894987628e-05, + "loss": 3.5625, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348710300236576e-05, + "loss": 3.5747, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347873343365897e-05, + "loss": 3.5701, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347034748614845e-05, + "loss": 3.5637, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346196153863793e-05, + "loss": 3.5722, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345357559112741e-05, + "loss": 3.5719, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3445206022420616e-05, + "loss": 3.5538, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436820074910096e-05, + "loss": 3.5684, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3428434127399576e-05, + "loss": 3.5578, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3420048179889056e-05, + "loss": 3.5623, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411678611182265e-05, + "loss": 3.5651, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3403292663671745e-05, + "loss": 3.5725, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339490671616123e-05, + "loss": 3.5682, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338653714745444e-05, + "loss": 3.5676, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337815119994392e-05, + "loss": 3.5707, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.33697652524334e-05, + "loss": 3.5706, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336137930492288e-05, + "loss": 3.5669, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335299335741236e-05, + "loss": 3.5419, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334460740990184e-05, + "loss": 3.5675, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333622146239132e-05, + "loss": 3.5705, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.33278355148808e-05, + "loss": 3.5685, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331946594617401e-05, + "loss": 3.5646, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331107999866349e-05, + "loss": 3.5582, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330269405115297e-05, + "loss": 3.5497, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329430810364245e-05, + "loss": 3.5503, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285938534935665e-05, + "loss": 3.5654, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277552587425145e-05, + "loss": 3.5482, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3269166639914625e-05, + "loss": 3.5742, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260780692404105e-05, + "loss": 3.5667, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3252411123697314e-05, + "loss": 3.5481, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3244025176186794e-05, + "loss": 3.5654, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3235639228676274e-05, + "loss": 3.55, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3227253281165754e-05, + "loss": 3.5542, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321888371245896e-05, + "loss": 3.5539, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321049776494844e-05, + "loss": 3.567, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320211181743792e-05, + "loss": 3.5486, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.31937258699274e-05, + "loss": 3.5606, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318535630122062e-05, + "loss": 3.5487, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.31769703537101e-05, + "loss": 3.5595, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316858440619958e-05, + "loss": 3.5637, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.316019845868906e-05, + "loss": 3.5609, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315182888998227e-05, + "loss": 3.5594, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314344294247175e-05, + "loss": 3.56, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313505699496123e-05, + "loss": 3.5794, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312668742625444e-05, + "loss": 3.5468, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311830147874392e-05, + "loss": 3.5721, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.31099155312334e-05, + "loss": 3.5558, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101529583722877e-05, + "loss": 3.5521, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309316001501609e-05, + "loss": 3.5603, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308477406750557e-05, + "loss": 3.5611, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307638811999505e-05, + "loss": 3.5683, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306800217248453e-05, + "loss": 3.5682, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305963260377774e-05, + "loss": 3.5469, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305124665626722e-05, + "loss": 3.5434, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.30428607087567e-05, + "loss": 3.5544, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303447476124618e-05, + "loss": 3.5635, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302610519253939e-05, + "loss": 3.5533, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301771924502887e-05, + "loss": 3.554, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300933329751835e-05, + "loss": 3.5619, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300094735000783e-05, + "loss": 3.5574, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2992577781301046e-05, + "loss": 3.5636, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2984191833790526e-05, + "loss": 3.5507, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975805886280006e-05, + "loss": 3.5617, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2967419938769486e-05, + "loss": 3.5594, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2959050370062695e-05, + "loss": 3.5692, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2950664422552175e-05, + "loss": 3.5443, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2942278475041655e-05, + "loss": 3.5513, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2933892527531135e-05, + "loss": 3.5626, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2925522958824344e-05, + "loss": 3.5575, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2917137011313824e-05, + "loss": 3.5652, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908751063803304e-05, + "loss": 3.556, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2900365116292784e-05, + "loss": 3.5511, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891995547586e-05, + "loss": 3.5553, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288362597887921e-05, + "loss": 3.5548, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287524003136869e-05, + "loss": 3.5523, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286685408385817e-05, + "loss": 3.5507, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285846813634765e-05, + "loss": 3.5602, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.285008218883713e-05, + "loss": 3.5525, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284171262013034e-05, + "loss": 3.5512, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283332667261982e-05, + "loss": 3.5536, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.28249407251093e-05, + "loss": 3.5404, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281655477759878e-05, + "loss": 3.5641, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280816883008826e-05, + "loss": 3.5574, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279978288257774e-05, + "loss": 3.5587, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279139693506722e-05, + "loss": 3.5638, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.27830109875567e-05, + "loss": 3.562, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277464141884991e-05, + "loss": 3.5555, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2766255471339387e-05, + "loss": 3.5542, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757869523828867e-05, + "loss": 3.5617, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2749483576318346e-05, + "loss": 3.5533, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274111400761156e-05, + "loss": 3.5508, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273274443890477e-05, + "loss": 3.5621, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272435849139425e-05, + "loss": 3.5532, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271597254388373e-05, + "loss": 3.559, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707586596373205e-05, + "loss": 3.5521, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2699200648862684e-05, + "loss": 3.552, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269081470135217e-05, + "loss": 3.5597, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268244513264539e-05, + "loss": 3.549, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267405918513486e-05, + "loss": 3.5622, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266567323762434e-05, + "loss": 3.563, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265728729011382e-05, + "loss": 3.5615, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.26489013426033e-05, + "loss": 3.5492, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264051539509278e-05, + "loss": 3.5601, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263212944758226e-05, + "loss": 3.5608, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262374350007174e-05, + "loss": 3.5574, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261537393136495e-05, + "loss": 3.5546, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260700436265816e-05, + "loss": 3.5504, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259861841514764e-05, + "loss": 3.5632, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2590232467637125e-05, + "loss": 3.5732, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581846520126605e-05, + "loss": 3.5545, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2573460572616085e-05, + "loss": 3.5618, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2565074625105565e-05, + "loss": 3.5613, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556705056398774e-05, + "loss": 3.5544, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2548319108888254e-05, + "loss": 3.5604, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539933161377734e-05, + "loss": 3.5561, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531547213867214e-05, + "loss": 3.5533, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2523161266356694e-05, + "loss": 3.5646, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514775318846174e-05, + "loss": 3.5449, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.850156307220459, + "eval_runtime": 305.8035, + "eval_samples_per_second": 1247.831, + "eval_steps_per_second": 38.996, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2506389371335654e-05, + "loss": 3.5633, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2498003423825134e-05, + "loss": 3.5393, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489617476314613e-05, + "loss": 3.552, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2481231528804093e-05, + "loss": 3.5705, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247286196009731e-05, + "loss": 3.5667, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246447601258679e-05, + "loss": 3.5527, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245610644388e-05, + "loss": 3.5556, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244772049636948e-05, + "loss": 3.5489, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243933454885896e-05, + "loss": 3.548, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243094860134844e-05, + "loss": 3.5639, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242256265383792e-05, + "loss": 3.5593, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.24141767063274e-05, + "loss": 3.5582, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240580713762061e-05, + "loss": 3.5584, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239742119011009e-05, + "loss": 3.5443, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238903524259957e-05, + "loss": 3.543, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238064929508905e-05, + "loss": 3.538, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237226334757853e-05, + "loss": 3.5551, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236387740006801e-05, + "loss": 3.5479, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235549145255749e-05, + "loss": 3.5501, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234710550504697e-05, + "loss": 3.5516, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338735936340176e-05, + "loss": 3.5687, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330349988829656e-05, + "loss": 3.559, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321964041319136e-05, + "loss": 3.5509, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313578093808616e-05, + "loss": 3.5543, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2305208525101825e-05, + "loss": 3.5606, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296822577591305e-05, + "loss": 3.5513, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288436630080785e-05, + "loss": 3.5463, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2280050682570265e-05, + "loss": 3.5512, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227168111386348e-05, + "loss": 3.5421, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226329516635296e-05, + "loss": 3.5473, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225490921884244e-05, + "loss": 3.5525, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224652327133192e-05, + "loss": 3.5495, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223815370262513e-05, + "loss": 3.5541, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222976775511461e-05, + "loss": 3.5562, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222139818640782e-05, + "loss": 3.5502, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.22130122388973e-05, + "loss": 3.5542, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220462629138678e-05, + "loss": 3.5579, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219624034387626e-05, + "loss": 3.539, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218785439636574e-05, + "loss": 3.5564, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217946844885522e-05, + "loss": 3.5369, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.21710825013447e-05, + "loss": 3.5475, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216269655383418e-05, + "loss": 3.5454, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2154326985127394e-05, + "loss": 3.5612, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145941037616874e-05, + "loss": 3.5492, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213757146891008e-05, + "loss": 3.5493, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212918552139956e-05, + "loss": 3.5595, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212079957388904e-05, + "loss": 3.5538, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211241362637852e-05, + "loss": 3.5518, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2104027678868e-05, + "loss": 3.5225, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209564173135748e-05, + "loss": 3.5499, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208725578384696e-05, + "loss": 3.5554, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207886983633644e-05, + "loss": 3.5524, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207050026762965e-05, + "loss": 3.5491, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206211432011913e-05, + "loss": 3.5394, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205372837260862e-05, + "loss": 3.5419, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.20453424250981e-05, + "loss": 3.5304, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203697285639131e-05, + "loss": 3.5544, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202858690888079e-05, + "loss": 3.5315, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.202020096137027e-05, + "loss": 3.5558, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201181501385975e-05, + "loss": 3.5471, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200344544515296e-05, + "loss": 3.5351, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199505949764244e-05, + "loss": 3.5505, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198667355013192e-05, + "loss": 3.5351, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.19782876026214e-05, + "loss": 3.5378, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969918033914606e-05, + "loss": 3.5358, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961532086404086e-05, + "loss": 3.5498, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195314613889357e-05, + "loss": 3.533, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194476019138305e-05, + "loss": 3.5455, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193639062267626e-05, + "loss": 3.5337, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192800467516574e-05, + "loss": 3.5406, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191961872765522e-05, + "loss": 3.5501, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.19112327801447e-05, + "loss": 3.5469, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190286321143791e-05, + "loss": 3.5394, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189447726392739e-05, + "loss": 3.5471, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188609131641687e-05, + "loss": 3.5581, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187770536890635e-05, + "loss": 3.5337, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186933580019956e-05, + "loss": 3.5543, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186094985268904e-05, + "loss": 3.5386, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852563905178526e-05, + "loss": 3.5402, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1844194336471735e-05, + "loss": 3.5416, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835808388961215e-05, + "loss": 3.5437, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1827422441450695e-05, + "loss": 3.5539, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1819036493940175e-05, + "loss": 3.5512, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810666925233384e-05, + "loss": 3.5357, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1802280977722864e-05, + "loss": 3.5237, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793895030212344e-05, + "loss": 3.5379, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785509082701824e-05, + "loss": 3.5473, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177713951399503e-05, + "loss": 3.5387, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176875356648451e-05, + "loss": 3.5381, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176036761897399e-05, + "loss": 3.546, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175199805026721e-05, + "loss": 3.5414, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174361210275669e-05, + "loss": 3.544, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173522615524617e-05, + "loss": 3.5369, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172684020773565e-05, + "loss": 3.5479, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171845426022512e-05, + "loss": 3.539, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.17100683127146e-05, + "loss": 3.5514, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170168236520408e-05, + "loss": 3.5319, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169329641769356e-05, + "loss": 3.5351, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168492684898677e-05, + "loss": 3.5477, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167654090147625e-05, + "loss": 3.5393, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166815495396573e-05, + "loss": 3.5498, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165976900645522e-05, + "loss": 3.5419, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165139943774843e-05, + "loss": 3.5359, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164301349023791e-05, + "loss": 3.5372, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163464392153112e-05, + "loss": 3.5413, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1626257974020596e-05, + "loss": 3.5327, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617872026510076e-05, + "loss": 3.5379, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1609486078999556e-05, + "loss": 3.5445, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1601100131489036e-05, + "loss": 3.5364, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592730562782245e-05, + "loss": 3.5338, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1584344615271725e-05, + "loss": 3.5426, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575958667761205e-05, + "loss": 3.5243, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567572720250685e-05, + "loss": 3.5487, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155918677274017e-05, + "loss": 3.5403, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155080082522965e-05, + "loss": 3.5443, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154241487771913e-05, + "loss": 3.5458, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153402893020861e-05, + "loss": 3.5484, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152565936150182e-05, + "loss": 3.5385, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.15172734139913e-05, + "loss": 3.5412, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150888746648078e-05, + "loss": 3.5436, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150050151897026e-05, + "loss": 3.5394, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149213195026347e-05, + "loss": 3.5288, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148376238155668e-05, + "loss": 3.5485, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147537643404616e-05, + "loss": 3.5354, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146699048653564e-05, + "loss": 3.5449, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458604539025125e-05, + "loss": 3.5374, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1450218591514605e-05, + "loss": 3.5337, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441832644004085e-05, + "loss": 3.5466, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1433446696493565e-05, + "loss": 3.5361, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1425060748983045e-05, + "loss": 3.5389, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416691180276254e-05, + "loss": 3.5482, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1408305232765734e-05, + "loss": 3.5438, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399919285255214e-05, + "loss": 3.5351, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391533337744694e-05, + "loss": 3.5441, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.13831637690379e-05, + "loss": 3.5445, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137477782152738e-05, + "loss": 3.5418, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136639187401686e-05, + "loss": 3.5338, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135802230531007e-05, + "loss": 3.538, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134963635779956e-05, + "loss": 3.5538, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134125041028904e-05, + "loss": 3.5532, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133286446277852e-05, + "loss": 3.5412, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324478515268e-05, + "loss": 3.5421, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131609256775748e-05, + "loss": 3.5462, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130772299905069e-05, + "loss": 3.5404, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129933705154017e-05, + "loss": 3.5447, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129095110402965e-05, + "loss": 3.5403, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128256515651913e-05, + "loss": 3.5369, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127417920900861e-05, + "loss": 3.5511, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126579326149808e-05, + "loss": 3.5304, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8498470783233643, + "eval_runtime": 307.8201, + "eval_samples_per_second": 1239.656, + "eval_steps_per_second": 38.74, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125740731398756e-05, + "loss": 3.537, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124902136647704e-05, + "loss": 3.5274, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240651797770256e-05, + "loss": 3.5328, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1232265850259736e-05, + "loss": 3.5558, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223879902749216e-05, + "loss": 3.5534, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1215493955238696e-05, + "loss": 3.5385, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120714076533564e-05, + "loss": 3.5412, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119875481782512e-05, + "loss": 3.5349, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.11903688703146e-05, + "loss": 3.5362, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118198292280408e-05, + "loss": 3.5474, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1173596975293554e-05, + "loss": 3.5414, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1165211027783034e-05, + "loss": 3.5431, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156825080272514e-05, + "loss": 3.5441, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114845551156573e-05, + "loss": 3.5323, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.114006956405521e-05, + "loss": 3.5269, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113168361654469e-05, + "loss": 3.5247, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112329766903417e-05, + "loss": 3.5374, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111491172152365e-05, + "loss": 3.5362, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110652577401313e-05, + "loss": 3.5333, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109813982650261e-05, + "loss": 3.5378, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108975387899209e-05, + "loss": 3.5515, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.10813843102853e-05, + "loss": 3.539, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107299836277478e-05, + "loss": 3.5406, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106462879406799e-05, + "loss": 3.5352, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105624284655747e-05, + "loss": 3.5482, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104785689904695e-05, + "loss": 3.532, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1039470951536434e-05, + "loss": 3.5363, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1031085004025914e-05, + "loss": 3.5333, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1022699056515394e-05, + "loss": 3.5289, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1014313109004874e-05, + "loss": 3.5328, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005927161494354e-05, + "loss": 3.5335, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997557592787563e-05, + "loss": 3.5354, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098917164527704e-05, + "loss": 3.5382, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098078569776652e-05, + "loss": 3.542, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097241612905973e-05, + "loss": 3.5374, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096403018154921e-05, + "loss": 3.536, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095564423403869e-05, + "loss": 3.5438, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094725828652817e-05, + "loss": 3.5232, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093887233901765e-05, + "loss": 3.5436, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093050277031087e-05, + "loss": 3.5164, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092211682280035e-05, + "loss": 3.5338, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091373087528983e-05, + "loss": 3.533, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090534492777931e-05, + "loss": 3.5442, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089695898026879e-05, + "loss": 3.532, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888589411562e-05, + "loss": 3.5387, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.088020346405148e-05, + "loss": 3.5427, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087181751654096e-05, + "loss": 3.5393, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086343156903044e-05, + "loss": 3.5349, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085504562151991e-05, + "loss": 3.5121, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084665967400939e-05, + "loss": 3.5337, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0838290105302606e-05, + "loss": 3.5409, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829904157792086e-05, + "loss": 3.5379, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0821518210281566e-05, + "loss": 3.5343, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0813132262771046e-05, + "loss": 3.5253, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804746315260526e-05, + "loss": 3.5271, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0796360367750006e-05, + "loss": 3.5158, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787974420239486e-05, + "loss": 3.54, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779588472728966e-05, + "loss": 3.5158, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0771218904022175e-05, + "loss": 3.5366, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762832956511655e-05, + "loss": 3.5328, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754447009001135e-05, + "loss": 3.5224, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0746061061490615e-05, + "loss": 3.5326, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0737691492783824e-05, + "loss": 3.5213, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0729305545273304e-05, + "loss": 3.526, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072091959776279e-05, + "loss": 3.5147, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071253365025227e-05, + "loss": 3.5387, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070416408154548e-05, + "loss": 3.5205, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069577813403496e-05, + "loss": 3.5236, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068739218652444e-05, + "loss": 3.5204, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067900623901392e-05, + "loss": 3.5278, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067063667030713e-05, + "loss": 3.5362, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066225072279661e-05, + "loss": 3.5305, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065386477528609e-05, + "loss": 3.5231, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064547882777557e-05, + "loss": 3.5337, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063710925906878e-05, + "loss": 3.5432, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062872331155826e-05, + "loss": 3.5201, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620337364047744e-05, + "loss": 3.5413, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611951416537224e-05, + "loss": 3.5272, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060358184783043e-05, + "loss": 3.5249, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059519590031991e-05, + "loss": 3.5234, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058680995280939e-05, + "loss": 3.5297, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.05784403841026e-05, + "loss": 3.5369, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.057007081539581e-05, + "loss": 3.5361, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056168486788529e-05, + "loss": 3.5242, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055329892037477e-05, + "loss": 3.505, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054491297286425e-05, + "loss": 3.5253, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053652702535373e-05, + "loss": 3.5279, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052814107784321e-05, + "loss": 3.5315, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.05197551303327e-05, + "loss": 3.5175, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511369182822174e-05, + "loss": 3.532, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502999614115387e-05, + "loss": 3.5286, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494613666604867e-05, + "loss": 3.529, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0486227719094347e-05, + "loss": 3.5195, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477841771583827e-05, + "loss": 3.533, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469472202877036e-05, + "loss": 3.5238, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0461086255366516e-05, + "loss": 3.5372, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452700307855996e-05, + "loss": 3.5233, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444314360345476e-05, + "loss": 3.5177, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435944791638688e-05, + "loss": 3.5328, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427558844128168e-05, + "loss": 3.5277, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419172896617648e-05, + "loss": 3.532, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410786949107128e-05, + "loss": 3.5277, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040241738040034e-05, + "loss": 3.5198, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039404781169355e-05, + "loss": 3.5226, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038566186418303e-05, + "loss": 3.5296, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037727591667251e-05, + "loss": 3.5147, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036888996916199e-05, + "loss": 3.5283, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036050402165147e-05, + "loss": 3.5276, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035211807414095e-05, + "loss": 3.5251, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343748505434162e-05, + "loss": 3.514, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335362557923642e-05, + "loss": 3.528, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032697661041312e-05, + "loss": 3.5148, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.03185906629026e-05, + "loss": 3.5306, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.031020471539208e-05, + "loss": 3.5258, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030181876788156e-05, + "loss": 3.5269, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029343282037104e-05, + "loss": 3.5297, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0285046872860518e-05, + "loss": 3.5329, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276677304153734e-05, + "loss": 3.5294, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268291356643214e-05, + "loss": 3.5217, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259905409132694e-05, + "loss": 3.5307, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251519461622167e-05, + "loss": 3.5251, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024313351411165e-05, + "loss": 3.5183, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234763945404866e-05, + "loss": 3.5318, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226377997894346e-05, + "loss": 3.5224, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021799205038382e-05, + "loss": 3.5311, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.02096061028733e-05, + "loss": 3.5213, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020122015536278e-05, + "loss": 3.5211, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019283420785226e-05, + "loss": 3.5292, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184464639145472e-05, + "loss": 3.5201, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017607869163495e-05, + "loss": 3.5232, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016769274412443e-05, + "loss": 3.5387, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015930679661391e-05, + "loss": 3.5311, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015092084910339e-05, + "loss": 3.52, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014253490159287e-05, + "loss": 3.5267, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013414895408235e-05, + "loss": 3.5283, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125763006571835e-05, + "loss": 3.5271, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117393437865044e-05, + "loss": 3.5262, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0109023869158253e-05, + "loss": 3.5217, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100637921647733e-05, + "loss": 3.5354, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092251974137213e-05, + "loss": 3.5372, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083866026626696e-05, + "loss": 3.5284, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075480079116176e-05, + "loss": 3.5255, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0067094131605656e-05, + "loss": 3.5344, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058724562898865e-05, + "loss": 3.5223, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050338615388345e-05, + "loss": 3.5306, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041952667877825e-05, + "loss": 3.5268, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033566720367305e-05, + "loss": 3.5233, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002518077285679e-05, + "loss": 3.5353, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001679482534627e-05, + "loss": 3.5188, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000840887783575e-05, + "loss": 3.5208, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.850959062576294, + "eval_runtime": 308.7697, + "eval_samples_per_second": 1235.844, + "eval_steps_per_second": 38.621, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 3.000002293032523e-05, + "loss": 3.5116, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991636982814708e-05, + "loss": 3.5189, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983267414107917e-05, + "loss": 3.5402, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974881466597397e-05, + "loss": 3.5389, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996649551908688e-05, + "loss": 3.5255, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9958109571576354e-05, + "loss": 3.5252, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949723624065834e-05, + "loss": 3.5211, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941337676555314e-05, + "loss": 3.5149, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993296810784853e-05, + "loss": 3.535, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924582160338006e-05, + "loss": 3.5251, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9916196212827486e-05, + "loss": 3.5302, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907810265316966e-05, + "loss": 3.5271, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899440696610182e-05, + "loss": 3.5225, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9891054749099655e-05, + "loss": 3.5131, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882668801589135e-05, + "loss": 3.5084, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987428285407862e-05, + "loss": 3.5203, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.98658969065681e-05, + "loss": 3.5204, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985751095905758e-05, + "loss": 3.5202, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984912501154706e-05, + "loss": 3.519, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840739064036538e-05, + "loss": 3.5415, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832369495329747e-05, + "loss": 3.5239, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982399992662296e-05, + "loss": 3.5249, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981561397911244e-05, + "loss": 3.5233, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980722803160192e-05, + "loss": 3.5383, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.97988420840914e-05, + "loss": 3.5121, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.979045613658088e-05, + "loss": 3.5226, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978207018907036e-05, + "loss": 3.5187, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977368424155984e-05, + "loss": 3.5175, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765314672853052e-05, + "loss": 3.5169, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756928725342532e-05, + "loss": 3.5182, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748542777832012e-05, + "loss": 3.5192, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740156830321492e-05, + "loss": 3.5254, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.97317872616147e-05, + "loss": 3.5234, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723417692907914e-05, + "loss": 3.527, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9715031745397394e-05, + "loss": 3.5204, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706645797886873e-05, + "loss": 3.5311, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698259850376353e-05, + "loss": 3.5091, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689873902865833e-05, + "loss": 3.5291, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681504334159042e-05, + "loss": 3.502, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9673118386648522e-05, + "loss": 3.5223, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664732439138006e-05, + "loss": 3.5158, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656346491627486e-05, + "loss": 3.5276, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647960544116966e-05, + "loss": 3.5142, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639590975410175e-05, + "loss": 3.5265, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631205027899655e-05, + "loss": 3.5245, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622819080389135e-05, + "loss": 3.5253, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614433132878615e-05, + "loss": 3.5232, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9606047185368098e-05, + "loss": 3.4984, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597677616661307e-05, + "loss": 3.5214, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589291669150787e-05, + "loss": 3.526, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580905721640267e-05, + "loss": 3.5217, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572519774129747e-05, + "loss": 3.5209, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564133826619227e-05, + "loss": 3.5095, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555747879108707e-05, + "loss": 3.5135, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954736193159819e-05, + "loss": 3.4991, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538975984087663e-05, + "loss": 3.5282, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.953060641538088e-05, + "loss": 3.5, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952222046787036e-05, + "loss": 3.5263, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951383452035984e-05, + "loss": 3.5164, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950546495165305e-05, + "loss": 3.5066, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949707900414253e-05, + "loss": 3.5166, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948869305663201e-05, + "loss": 3.5125, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480307109121485e-05, + "loss": 3.5112, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471921161610965e-05, + "loss": 3.5022, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463535214100445e-05, + "loss": 3.5217, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455149266589928e-05, + "loss": 3.5094, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446763319079408e-05, + "loss": 3.5091, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438393750372617e-05, + "loss": 3.506, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9430007802862097e-05, + "loss": 3.5093, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421621855351577e-05, + "loss": 3.5198, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413235907841057e-05, + "loss": 3.5191, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940486633913427e-05, + "loss": 3.5089, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939648039162375e-05, + "loss": 3.5214, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938809444411323e-05, + "loss": 3.5261, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937972487540644e-05, + "loss": 3.5059, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937133892789592e-05, + "loss": 3.5234, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.93629529803854e-05, + "loss": 3.5149, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935456703287488e-05, + "loss": 3.514, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934619746416809e-05, + "loss": 3.5109, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933781151665757e-05, + "loss": 3.5149, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932942556914705e-05, + "loss": 3.5211, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932103962163653e-05, + "loss": 3.5287, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312670052929743e-05, + "loss": 3.5064, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930430048422296e-05, + "loss": 3.4917, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295914536712432e-05, + "loss": 3.5101, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287528589201912e-05, + "loss": 3.5138, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9279142641691392e-05, + "loss": 3.5177, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270756694180872e-05, + "loss": 3.5074, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262370746670352e-05, + "loss": 3.5167, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9254001177963564e-05, + "loss": 3.5156, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245615230453044e-05, + "loss": 3.5125, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237229282942524e-05, + "loss": 3.5058, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228843335432004e-05, + "loss": 3.5181, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220473766725213e-05, + "loss": 3.5087, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9212087819214697e-05, + "loss": 3.5207, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203701871704177e-05, + "loss": 3.5148, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195315924193657e-05, + "loss": 3.5007, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186929976683137e-05, + "loss": 3.5136, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178544029172617e-05, + "loss": 3.5137, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170158081662097e-05, + "loss": 3.5198, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161772134151577e-05, + "loss": 3.5126, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915340256544479e-05, + "loss": 3.5095, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914501661793427e-05, + "loss": 3.5068, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136647049227478e-05, + "loss": 3.5171, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128261101716958e-05, + "loss": 3.5002, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119875154206438e-05, + "loss": 3.5095, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111489206695918e-05, + "loss": 3.5158, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9103103259185398e-05, + "loss": 3.5118, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909473369047861e-05, + "loss": 3.5006, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908634774296809e-05, + "loss": 3.5119, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907796179545757e-05, + "loss": 3.5053, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906957584794705e-05, + "loss": 3.5154, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.906118990043653e-05, + "loss": 3.5095, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905280395292601e-05, + "loss": 3.5116, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904441800541549e-05, + "loss": 3.5197, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903603205790497e-05, + "loss": 3.5206, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027662489198183e-05, + "loss": 3.517, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019276541687662e-05, + "loss": 3.5085, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010890594177142e-05, + "loss": 3.5145, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002504646666616e-05, + "loss": 3.5072, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.89941186991561e-05, + "loss": 3.505, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985749130449315e-05, + "loss": 3.521, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977363182938795e-05, + "loss": 3.5074, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968977235428268e-05, + "loss": 3.5172, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960591287917748e-05, + "loss": 3.5034, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952205340407228e-05, + "loss": 3.5082, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943819392896708e-05, + "loss": 3.5151, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893544982418992e-05, + "loss": 3.5078, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.89270638766794e-05, + "loss": 3.5027, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891867792916888e-05, + "loss": 3.5258, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891029198165836e-05, + "loss": 3.5176, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890190603414784e-05, + "loss": 3.5102, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889352008663732e-05, + "loss": 3.5074, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.88851341391268e-05, + "loss": 3.513, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876748191616283e-05, + "loss": 3.5139, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868378622909493e-05, + "loss": 3.5131, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.88600090542027e-05, + "loss": 3.5109, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885162310669218e-05, + "loss": 3.5221, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884323715918166e-05, + "loss": 3.517, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834851211671145e-05, + "loss": 3.5193, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826465264160625e-05, + "loss": 3.5116, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818079316650105e-05, + "loss": 3.5171, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809709747943314e-05, + "loss": 3.5121, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801323800432794e-05, + "loss": 3.5153, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792937852922274e-05, + "loss": 3.5141, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784551905411754e-05, + "loss": 3.5137, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776165957901237e-05, + "loss": 3.5184, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767780010390717e-05, + "loss": 3.5052, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759394062880197e-05, + "loss": 3.5053, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8518497943878174, + "eval_runtime": 303.2639, + "eval_samples_per_second": 1258.28, + "eval_steps_per_second": 39.322, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8751008115369677e-05, + "loss": 3.4993, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742638546662886e-05, + "loss": 3.505, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.87342689779561e-05, + "loss": 3.5281, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872588303044558e-05, + "loss": 3.52, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871749708293506e-05, + "loss": 3.5171, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870911113542454e-05, + "loss": 3.5084, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870072518791402e-05, + "loss": 3.5095, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692339240403498e-05, + "loss": 3.5002, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683969671696707e-05, + "loss": 3.5173, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867558372418619e-05, + "loss": 3.516, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866719777667567e-05, + "loss": 3.5127, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865881182916515e-05, + "loss": 3.5147, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865044226045836e-05, + "loss": 3.5059, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864205631294784e-05, + "loss": 3.5029, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863367036543732e-05, + "loss": 3.4981, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.86252844179268e-05, + "loss": 3.4985, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861689847041628e-05, + "loss": 3.5102, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608512522905756e-05, + "loss": 3.5031, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8600126575395236e-05, + "loss": 3.5075, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591740627884716e-05, + "loss": 3.5278, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858337105917793e-05, + "loss": 3.5107, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8575001490471144e-05, + "loss": 3.5121, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566615542960624e-05, + "loss": 3.5068, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558229595450104e-05, + "loss": 3.5206, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549843647939577e-05, + "loss": 3.5017, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541457700429057e-05, + "loss": 3.5085, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533071752918537e-05, + "loss": 3.5035, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524685805408017e-05, + "loss": 3.5068, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.85162998578975e-05, + "loss": 3.5015, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850793028919071e-05, + "loss": 3.5024, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849954434168019e-05, + "loss": 3.5076, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849115839416967e-05, + "loss": 3.5155, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482788825462882e-05, + "loss": 3.5092, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474402877952362e-05, + "loss": 3.5109, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8466016930441842e-05, + "loss": 3.5039, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457630982931322e-05, + "loss": 3.5162, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844926141422453e-05, + "loss": 3.498, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844087546671401e-05, + "loss": 3.5108, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432505898007224e-05, + "loss": 3.4902, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8424119950496704e-05, + "loss": 3.5119, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415734002986184e-05, + "loss": 3.5008, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407348055475663e-05, + "loss": 3.5159, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398962107965143e-05, + "loss": 3.5016, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390592539258353e-05, + "loss": 3.5122, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382206591747832e-05, + "loss": 3.5135, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373820644237316e-05, + "loss": 3.5118, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365434696726796e-05, + "loss": 3.5115, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8357048749216276e-05, + "loss": 3.4866, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348662801705756e-05, + "loss": 3.4995, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340293232998965e-05, + "loss": 3.5121, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331907285488445e-05, + "loss": 3.5093, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323521337977925e-05, + "loss": 3.5059, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315135390467408e-05, + "loss": 3.4987, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306749442956888e-05, + "loss": 3.4986, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298363495446368e-05, + "loss": 3.4925, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289977547935848e-05, + "loss": 3.5084, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281591600425328e-05, + "loss": 3.4925, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273222031718537e-05, + "loss": 3.5039, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264836084208017e-05, + "loss": 3.5077, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825646651550123e-05, + "loss": 3.4963, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824808056799071e-05, + "loss": 3.4976, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823969462048019e-05, + "loss": 3.4997, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823130867296967e-05, + "loss": 3.4931, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822293910426288e-05, + "loss": 3.4897, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214553156752362e-05, + "loss": 3.5116, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820616720924184e-05, + "loss": 3.4965, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819778126173132e-05, + "loss": 3.4933, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.81893953142208e-05, + "loss": 3.4959, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.818100936671028e-05, + "loss": 3.4964, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817262341919976e-05, + "loss": 3.5068, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164237471689238e-05, + "loss": 3.5027, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155867902982454e-05, + "loss": 3.4972, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147481955471934e-05, + "loss": 3.508, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8139112386765143e-05, + "loss": 3.51, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130726439254623e-05, + "loss": 3.4958, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122340491744103e-05, + "loss": 3.5064, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113954544233583e-05, + "loss": 3.5011, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810556859672306e-05, + "loss": 3.5013, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809718264921254e-05, + "loss": 3.4976, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808879670170202e-05, + "loss": 3.5, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080427132995235e-05, + "loss": 3.51, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8072057564288444e-05, + "loss": 3.5051, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063671616777924e-05, + "loss": 3.4982, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055285669267408e-05, + "loss": 3.478, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046899721756888e-05, + "loss": 3.4941, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803851377424636e-05, + "loss": 3.5048, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.803012782673584e-05, + "loss": 3.5044, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802174187922532e-05, + "loss": 3.4977, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.80133559317148e-05, + "loss": 3.4974, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004986363008013e-05, + "loss": 3.5044, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996600415497493e-05, + "loss": 3.4981, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988214467986973e-05, + "loss": 3.4903, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979828520476453e-05, + "loss": 3.5109, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971442572965933e-05, + "loss": 3.4929, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963056625455413e-05, + "loss": 3.5105, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954670677944893e-05, + "loss": 3.5037, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946284730434373e-05, + "loss": 3.4861, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937915161727585e-05, + "loss": 3.5047, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929529214217065e-05, + "loss": 3.498, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921143266706545e-05, + "loss": 3.5091, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912757319196025e-05, + "loss": 3.5004, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904387750489238e-05, + "loss": 3.4948, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7896018181782447e-05, + "loss": 3.4928, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887632234271927e-05, + "loss": 3.505, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879246286761407e-05, + "loss": 3.4868, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870860339250887e-05, + "loss": 3.4962, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862474391740367e-05, + "loss": 3.5041, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854088444229846e-05, + "loss": 3.4962, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784571887552306e-05, + "loss": 3.4852, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783733292801254e-05, + "loss": 3.5028, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782894698050202e-05, + "loss": 3.4912, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.78205610329915e-05, + "loss": 3.4976, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.781217508548098e-05, + "loss": 3.4986, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803805516774188e-05, + "loss": 3.4926, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779541956926367e-05, + "loss": 3.5128, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778703362175315e-05, + "loss": 3.506, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777864767424263e-05, + "loss": 3.5013, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.777026172673211e-05, + "loss": 3.4921, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776187577922159e-05, + "loss": 3.5007, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775348983171107e-05, + "loss": 3.4964, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745103884200548e-05, + "loss": 3.4899, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736750694297493e-05, + "loss": 3.5076, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728364746786973e-05, + "loss": 3.4977, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719978799276452e-05, + "loss": 3.498, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711592851765932e-05, + "loss": 3.4969, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703206904255412e-05, + "loss": 3.4965, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694820956744892e-05, + "loss": 3.4978, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768643500923437e-05, + "loss": 3.4932, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767804906172385e-05, + "loss": 3.4878, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669679493017065e-05, + "loss": 3.5141, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661293545506545e-05, + "loss": 3.5075, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652907597996018e-05, + "loss": 3.4971, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.76445216504855e-05, + "loss": 3.4947, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763613570297498e-05, + "loss": 3.4955, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762774975546446e-05, + "loss": 3.5048, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761936380795394e-05, + "loss": 3.5023, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.761099423924715e-05, + "loss": 3.4965, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760260829173663e-05, + "loss": 3.5103, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759422234422611e-05, + "loss": 3.4998, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585836396715593e-05, + "loss": 3.5107, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577450449205073e-05, + "loss": 3.4985, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569080880498283e-05, + "loss": 3.5065, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560694932987762e-05, + "loss": 3.4991, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552308985477242e-05, + "loss": 3.5006, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543923037966722e-05, + "loss": 3.5021, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535537090456202e-05, + "loss": 3.5013, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527167521749415e-05, + "loss": 3.505, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518781574238895e-05, + "loss": 3.4923, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510395626728375e-05, + "loss": 3.4939, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8523263931274414, + "eval_runtime": 306.4935, + "eval_samples_per_second": 1245.021, + "eval_steps_per_second": 38.908, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502009679217855e-05, + "loss": 3.4852, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493623731707335e-05, + "loss": 3.492, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485254163000547e-05, + "loss": 3.5132, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476868215490027e-05, + "loss": 3.51, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468482267979507e-05, + "loss": 3.5028, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460096320468987e-05, + "loss": 3.4941, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451710372958467e-05, + "loss": 3.4971, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443324425447947e-05, + "loss": 3.4873, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434954856741156e-05, + "loss": 3.5069, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742656890923064e-05, + "loss": 3.5023, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741818296172012e-05, + "loss": 3.4959, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.74097970142096e-05, + "loss": 3.4998, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740142744550281e-05, + "loss": 3.491, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393041497992288e-05, + "loss": 3.4905, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384655550481768e-05, + "loss": 3.4896, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376269602971248e-05, + "loss": 3.4887, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367883655460728e-05, + "loss": 3.4934, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359497707950205e-05, + "loss": 3.4893, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351111760439685e-05, + "loss": 3.4959, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342725812929165e-05, + "loss": 3.5168, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733435624422238e-05, + "loss": 3.4969, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325986675515593e-05, + "loss": 3.4971, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317600728005073e-05, + "loss": 3.4975, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309214780494553e-05, + "loss": 3.5045, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300828832984026e-05, + "loss": 3.4881, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292459264277242e-05, + "loss": 3.4996, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284073316766722e-05, + "loss": 3.4885, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275687369256202e-05, + "loss": 3.4922, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726730142174568e-05, + "loss": 3.4878, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725891547423516e-05, + "loss": 3.4905, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725052952672464e-05, + "loss": 3.4936, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242159958017847e-05, + "loss": 3.5016, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723377401050733e-05, + "loss": 3.4946, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722538806299681e-05, + "loss": 3.5022, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.721700211548629e-05, + "loss": 3.4859, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720861616797577e-05, + "loss": 3.5057, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.720023022046525e-05, + "loss": 3.4828, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.719184427295473e-05, + "loss": 3.5014, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718347470424794e-05, + "loss": 3.4768, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717508875673742e-05, + "loss": 3.4984, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166702809226903e-05, + "loss": 3.4866, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158316861716383e-05, + "loss": 3.5062, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149930914205863e-05, + "loss": 3.4913, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141561345499072e-05, + "loss": 3.4942, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133175397988552e-05, + "loss": 3.5006, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124789450478032e-05, + "loss": 3.5015, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116403502967512e-05, + "loss": 3.4964, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108017555456995e-05, + "loss": 3.4799, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099631607946475e-05, + "loss": 3.4822, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091262039239684e-05, + "loss": 3.5024, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082876091729164e-05, + "loss": 3.4968, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074490144218644e-05, + "loss": 3.4909, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066104196708124e-05, + "loss": 3.4882, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057718249197604e-05, + "loss": 3.4885, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049332301687087e-05, + "loss": 3.4781, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040962732980297e-05, + "loss": 3.4905, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032576785469776e-05, + "loss": 3.4799, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024190837959256e-05, + "loss": 3.4934, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015804890448736e-05, + "loss": 3.4981, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007418942938213e-05, + "loss": 3.4822, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999032995427693e-05, + "loss": 3.4839, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990647047917173e-05, + "loss": 3.4873, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982261100406653e-05, + "loss": 3.4811, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973907910503598e-05, + "loss": 3.4736, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965521962993078e-05, + "loss": 3.497, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957136015482558e-05, + "loss": 3.4843, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694875006797204e-05, + "loss": 3.4821, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940364120461514e-05, + "loss": 3.4821, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931978172950994e-05, + "loss": 3.4871, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923592225440474e-05, + "loss": 3.4933, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915206277929954e-05, + "loss": 3.4917, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906836709223167e-05, + "loss": 3.482, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898450761712647e-05, + "loss": 3.4977, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6890081193005862e-05, + "loss": 3.4958, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881695245495336e-05, + "loss": 3.4841, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873309297984816e-05, + "loss": 3.4903, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864923350474296e-05, + "loss": 3.4919, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685653740296378e-05, + "loss": 3.4908, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684815145545326e-05, + "loss": 3.4853, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683976550794274e-05, + "loss": 3.4865, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831395939235948e-05, + "loss": 3.4953, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823009991725428e-05, + "loss": 3.4964, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681464042301864e-05, + "loss": 3.4822, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680625447550812e-05, + "loss": 3.4721, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.67978685279976e-05, + "loss": 3.4796, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.678948258048708e-05, + "loss": 3.4897, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.678109663297656e-05, + "loss": 3.4926, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677271068546604e-05, + "loss": 3.4841, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676432473795552e-05, + "loss": 3.4834, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755955169248733e-05, + "loss": 3.4941, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747569221738212e-05, + "loss": 3.4779, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739183274227692e-05, + "loss": 3.4807, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730797326717172e-05, + "loss": 3.4931, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722411379206652e-05, + "loss": 3.4833, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714025431696132e-05, + "loss": 3.4982, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705639484185612e-05, + "loss": 3.4884, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669726991547882e-05, + "loss": 3.4763, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688883967968305e-05, + "loss": 3.4906, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680498020457785e-05, + "loss": 3.4821, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672112072947265e-05, + "loss": 3.4978, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663726125436745e-05, + "loss": 3.4896, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655340177926225e-05, + "loss": 3.4826, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646970609219434e-05, + "loss": 3.4774, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638584661708914e-05, + "loss": 3.493, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630198714198397e-05, + "loss": 3.4745, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662181276668787e-05, + "loss": 3.4872, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661342681917735e-05, + "loss": 3.4886, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.660504087166683e-05, + "loss": 3.4823, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596671302960046e-05, + "loss": 3.4722, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588285355449522e-05, + "loss": 3.4933, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579899407939002e-05, + "loss": 3.4781, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571513460428482e-05, + "loss": 3.4828, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563127512917962e-05, + "loss": 3.4898, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655475794421117e-05, + "loss": 3.4818, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654637199670065e-05, + "loss": 3.4978, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537986049190135e-05, + "loss": 3.4917, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529600101679615e-05, + "loss": 3.4908, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521214154169095e-05, + "loss": 3.481, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512828206658575e-05, + "loss": 3.4872, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504442259148055e-05, + "loss": 3.4879, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496056311637534e-05, + "loss": 3.4749, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487703121734476e-05, + "loss": 3.4905, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479317174223956e-05, + "loss": 3.4861, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470931226713436e-05, + "loss": 3.4861, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462545279202916e-05, + "loss": 3.4875, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454159331692396e-05, + "loss": 3.4856, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445773384181876e-05, + "loss": 3.4785, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437387436671356e-05, + "loss": 3.4854, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429001489160836e-05, + "loss": 3.4773, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420631920454048e-05, + "loss": 3.4981, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412245972943528e-05, + "loss": 3.5003, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403860025433008e-05, + "loss": 3.4826, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395474077922488e-05, + "loss": 3.4828, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387088130411968e-05, + "loss": 3.483, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378702182901448e-05, + "loss": 3.4871, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.637033261419466e-05, + "loss": 3.4906, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636194666668414e-05, + "loss": 3.4837, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635356071917362e-05, + "loss": 3.4943, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.63451747716631e-05, + "loss": 3.4889, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633680520295631e-05, + "loss": 3.4991, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632841925544579e-05, + "loss": 3.4838, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320033307935273e-05, + "loss": 3.4967, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311647360424753e-05, + "loss": 3.4873, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303261412914233e-05, + "loss": 3.4847, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294891844207442e-05, + "loss": 3.4923, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286505896696922e-05, + "loss": 3.4908, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278119949186402e-05, + "loss": 3.4899, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269734001675882e-05, + "loss": 3.4771, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261348054165358e-05, + "loss": 3.4765, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8561015129089355, + "eval_runtime": 309.8293, + "eval_samples_per_second": 1231.617, + "eval_steps_per_second": 38.489, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252962106654838e-05, + "loss": 3.4793, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244576159144318e-05, + "loss": 3.4774, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236206590437534e-05, + "loss": 3.4966, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622782064292701e-05, + "loss": 3.4963, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621943469541649e-05, + "loss": 3.4953, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621104874790597e-05, + "loss": 3.4764, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620266280039545e-05, + "loss": 3.4885, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619427685288493e-05, + "loss": 3.4709, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618590728417814e-05, + "loss": 3.4962, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617752133666762e-05, + "loss": 3.4913, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169135389157103e-05, + "loss": 3.4793, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160749441646583e-05, + "loss": 3.4916, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152379872939792e-05, + "loss": 3.4776, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143993925429272e-05, + "loss": 3.4807, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135607977918752e-05, + "loss": 3.4727, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127222030408232e-05, + "loss": 3.4813, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118836082897712e-05, + "loss": 3.4794, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611045013538719e-05, + "loss": 3.4782, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102064187876675e-05, + "loss": 3.4828, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093678240366155e-05, + "loss": 3.5016, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085308671659364e-05, + "loss": 3.4855, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076939102952573e-05, + "loss": 3.4857, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068553155442053e-05, + "loss": 3.486, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060167207931536e-05, + "loss": 3.4913, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051781260421016e-05, + "loss": 3.4773, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043395312910496e-05, + "loss": 3.4871, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035009365399976e-05, + "loss": 3.4774, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026639796693185e-05, + "loss": 3.4768, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018253849182665e-05, + "loss": 3.4732, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009867901672145e-05, + "loss": 3.4831, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600148195416163e-05, + "loss": 3.4801, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599309600665111e-05, + "loss": 3.4888, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598471005914059e-05, + "loss": 3.4848, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976340490433798e-05, + "loss": 3.4861, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967954542923278e-05, + "loss": 3.4765, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959568595412758e-05, + "loss": 3.4904, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951182647902238e-05, + "loss": 3.4758, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594279670039172e-05, + "loss": 3.4879, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593442713168493e-05, + "loss": 3.4639, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592604118417441e-05, + "loss": 3.4822, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591765523666389e-05, + "loss": 3.4769, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909269289153366e-05, + "loss": 3.4943, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900883341642846e-05, + "loss": 3.4788, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892513772936062e-05, + "loss": 3.483, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884127825425542e-05, + "loss": 3.4874, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875741877915015e-05, + "loss": 3.4907, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867355930404495e-05, + "loss": 3.4804, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5858969982893975e-05, + "loss": 3.4698, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.585058403538346e-05, + "loss": 3.4652, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842214466676668e-05, + "loss": 3.4894, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833828519166148e-05, + "loss": 3.4857, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825442571655628e-05, + "loss": 3.4806, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817056624145108e-05, + "loss": 3.4722, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808670676634588e-05, + "loss": 3.4799, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.58003011079278e-05, + "loss": 3.4626, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.579191516041728e-05, + "loss": 3.4814, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578352921290676e-05, + "loss": 3.4674, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577514326539624e-05, + "loss": 3.4789, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576675731788572e-05, + "loss": 3.4824, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.57583713703752e-05, + "loss": 3.4747, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.574998542286468e-05, + "loss": 3.4696, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.574159947535416e-05, + "loss": 3.4776, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733229906647372e-05, + "loss": 3.4668, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.572486033794058e-05, + "loss": 3.466, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571647439043006e-05, + "loss": 3.4816, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570808844291954e-05, + "loss": 3.4736, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569970249540902e-05, + "loss": 3.4684, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691316547898505e-05, + "loss": 3.468, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682930600387985e-05, + "loss": 3.4736, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674544652877464e-05, + "loss": 3.4761, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666158705366944e-05, + "loss": 3.4809, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657789136660154e-05, + "loss": 3.4717, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649403189149633e-05, + "loss": 3.4838, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641017241639113e-05, + "loss": 3.4826, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632631294128597e-05, + "loss": 3.4724, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624261725421806e-05, + "loss": 3.4775, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615875777911286e-05, + "loss": 3.4806, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607489830400766e-05, + "loss": 3.4795, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599103882890246e-05, + "loss": 3.4731, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590734314183458e-05, + "loss": 3.4738, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582348366672938e-05, + "loss": 3.4819, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5573962419162418e-05, + "loss": 3.4831, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565592850455627e-05, + "loss": 3.4718, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557206902945107e-05, + "loss": 3.4605, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548820955434587e-05, + "loss": 3.4615, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540435007924067e-05, + "loss": 3.4772, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532049060413547e-05, + "loss": 3.4836, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552366311290303e-05, + "loss": 3.4754, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515277165392504e-05, + "loss": 3.4649, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550690759668572e-05, + "loss": 3.4813, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.54985216491752e-05, + "loss": 3.473, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490135701664676e-05, + "loss": 3.4675, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481766132957892e-05, + "loss": 3.474, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473380185447372e-05, + "loss": 3.4783, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5464994237936852e-05, + "loss": 3.4866, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456608290426325e-05, + "loss": 3.4719, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.544823872171954e-05, + "loss": 3.4612, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543985277420902e-05, + "loss": 3.4813, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431466826698497e-05, + "loss": 3.4689, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423080879187977e-05, + "loss": 3.4828, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414694931677457e-05, + "loss": 3.4805, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406308984166937e-05, + "loss": 3.4679, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397939415460146e-05, + "loss": 3.465, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538955346794963e-05, + "loss": 3.4795, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538116752043911e-05, + "loss": 3.4615, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537278157292859e-05, + "loss": 3.4769, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536439562541807e-05, + "loss": 3.4721, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535600967790755e-05, + "loss": 3.4767, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534764010920076e-05, + "loss": 3.4592, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533925416169024e-05, + "loss": 3.4789, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5330868214179722e-05, + "loss": 3.4661, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322482266669202e-05, + "loss": 3.47, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314096319158682e-05, + "loss": 3.479, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530572675045189e-05, + "loss": 3.4705, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529734080294137e-05, + "loss": 3.4861, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528895485543085e-05, + "loss": 3.4811, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.528056890792033e-05, + "loss": 3.4768, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272182960409814e-05, + "loss": 3.4689, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5263797012899294e-05, + "loss": 3.4765, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255411065388774e-05, + "loss": 3.4709, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247041496681983e-05, + "loss": 3.4658, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238655549171463e-05, + "loss": 3.4758, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230269601660943e-05, + "loss": 3.4746, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221883654150423e-05, + "loss": 3.4739, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213497706639906e-05, + "loss": 3.4722, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205111759129386e-05, + "loss": 3.4769, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519672581161886e-05, + "loss": 3.4687, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518833986410834e-05, + "loss": 3.4739, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5179970295401555e-05, + "loss": 3.4643, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171600726694768e-05, + "loss": 3.4827, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163214779184248e-05, + "loss": 3.4826, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154828831673728e-05, + "loss": 3.4763, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146442884163208e-05, + "loss": 3.4697, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138056936652688e-05, + "loss": 3.4713, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512967098914216e-05, + "loss": 3.4756, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121285041631644e-05, + "loss": 3.4805, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511291547292486e-05, + "loss": 3.468, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104529525414333e-05, + "loss": 3.4789, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096143577903813e-05, + "loss": 3.4759, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087757630393293e-05, + "loss": 3.4879, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079371682882773e-05, + "loss": 3.4726, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071002114175986e-05, + "loss": 3.4833, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062616166665465e-05, + "loss": 3.4773, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054230219154945e-05, + "loss": 3.4704, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5045844271644425e-05, + "loss": 3.4763, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037458324133905e-05, + "loss": 3.4841, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029088755427114e-05, + "loss": 3.4761, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020702807916598e-05, + "loss": 3.4621, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012316860406078e-05, + "loss": 3.4718, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.856826066970825, + "eval_runtime": 304.5463, + "eval_samples_per_second": 1252.982, + "eval_steps_per_second": 39.157, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5003930912895558e-05, + "loss": 3.4602, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995544965385038e-05, + "loss": 3.4662, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498717539667825e-05, + "loss": 3.4822, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978789449167727e-05, + "loss": 3.4848, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970403501657207e-05, + "loss": 3.482, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496201755414669e-05, + "loss": 3.4703, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495363160663617e-05, + "loss": 3.4739, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494526203792938e-05, + "loss": 3.4554, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493687609041886e-05, + "loss": 3.4839, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492849014290834e-05, + "loss": 3.4807, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492010419539782e-05, + "loss": 3.4691, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491173462669103e-05, + "loss": 3.4781, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.490334867918051e-05, + "loss": 3.4662, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489496273166999e-05, + "loss": 3.4707, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488657678415947e-05, + "loss": 3.4621, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487819083664895e-05, + "loss": 3.464, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869804889138428e-05, + "loss": 3.4675, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861418941627908e-05, + "loss": 3.4655, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485303299411739e-05, + "loss": 3.4717, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844663425410604e-05, + "loss": 3.4888, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483627747790008e-05, + "loss": 3.4729, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4827907909193293e-05, + "loss": 3.4783, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819521961682773e-05, + "loss": 3.4695, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811136014172253e-05, + "loss": 3.4777, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802750066661732e-05, + "loss": 3.465, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794364119151212e-05, + "loss": 3.4738, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4785994550444425e-05, + "loss": 3.4695, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.47776086029339e-05, + "loss": 3.4644, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476922265542338e-05, + "loss": 3.4594, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476083670791286e-05, + "loss": 3.4729, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752450760402345e-05, + "loss": 3.4684, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744081191695554e-05, + "loss": 3.4757, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735695244185034e-05, + "loss": 3.4744, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727309296674514e-05, + "loss": 3.4736, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4718923349163994e-05, + "loss": 3.4636, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710537401653474e-05, + "loss": 3.4794, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702151454142954e-05, + "loss": 3.4645, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693765506632434e-05, + "loss": 3.4716, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685395937925646e-05, + "loss": 3.4527, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677009990415126e-05, + "loss": 3.4683, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668624042904606e-05, + "loss": 3.4678, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660238095394083e-05, + "loss": 3.4798, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651852147883562e-05, + "loss": 3.4671, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643466200373046e-05, + "loss": 3.471, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635080252862526e-05, + "loss": 3.4772, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626710684155735e-05, + "loss": 3.4769, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618324736645215e-05, + "loss": 3.4704, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609938789134695e-05, + "loss": 3.458, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601552841624175e-05, + "loss": 3.4504, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593166894113655e-05, + "loss": 3.4799, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584780946603138e-05, + "loss": 3.4735, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576394999092618e-05, + "loss": 3.4682, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568025430385827e-05, + "loss": 3.4635, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559639482875307e-05, + "loss": 3.4655, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551253535364787e-05, + "loss": 3.4488, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542867587854264e-05, + "loss": 3.4655, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534481640343747e-05, + "loss": 3.4572, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526095692833227e-05, + "loss": 3.4667, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517709745322707e-05, + "loss": 3.4726, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509323797812187e-05, + "loss": 3.4635, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4500954229105396e-05, + "loss": 3.4537, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.449258466039861e-05, + "loss": 3.4702, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484198712888092e-05, + "loss": 3.4527, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475812765377568e-05, + "loss": 3.456, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467426817867048e-05, + "loss": 3.4669, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459040870356528e-05, + "loss": 3.4634, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450654922846008e-05, + "loss": 3.4559, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442285354139217e-05, + "loss": 3.4604, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.44338994066287e-05, + "loss": 3.4597, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442551345911818e-05, + "loss": 3.4648, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441712751160766e-05, + "loss": 3.4665, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440874156409714e-05, + "loss": 3.4605, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440035561658662e-05, + "loss": 3.4749, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439198604787983e-05, + "loss": 3.4716, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438360010036931e-05, + "loss": 3.4625, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375214152858793e-05, + "loss": 3.4572, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366828205348273e-05, + "loss": 3.4747, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358458636641482e-05, + "loss": 3.4671, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350072689130962e-05, + "loss": 3.4595, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341686741620442e-05, + "loss": 3.4653, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433330079410992e-05, + "loss": 3.4673, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.43249148465994e-05, + "loss": 3.4743, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316545277892614e-05, + "loss": 3.4582, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308159330382094e-05, + "loss": 3.4498, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.429977338287157e-05, + "loss": 3.4564, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429138743536105e-05, + "loss": 3.4581, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428300148785053e-05, + "loss": 3.4698, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427461554034001e-05, + "loss": 3.463, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266229592829494e-05, + "loss": 3.4538, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257860024122703e-05, + "loss": 3.4698, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249474076612183e-05, + "loss": 3.4575, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241088129101663e-05, + "loss": 3.4624, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232702181591143e-05, + "loss": 3.4603, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224316234080623e-05, + "loss": 3.4668, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4215930286570103e-05, + "loss": 3.4744, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207544339059583e-05, + "loss": 3.4647, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199158391549063e-05, + "loss": 3.4464, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190805201646004e-05, + "loss": 3.4686, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182419254135484e-05, + "loss": 3.4592, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174033306624964e-05, + "loss": 3.4659, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165647359114448e-05, + "loss": 3.4704, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157261411603924e-05, + "loss": 3.4593, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148891842897137e-05, + "loss": 3.4567, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140505895386617e-05, + "loss": 3.4666, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132119947876097e-05, + "loss": 3.4502, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123734000365576e-05, + "loss": 3.4647, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115348052855056e-05, + "loss": 3.4582, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4106962105344536e-05, + "loss": 3.4662, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409859253663775e-05, + "loss": 3.4483, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090206589127225e-05, + "loss": 3.4669, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4081820641616705e-05, + "loss": 3.4534, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073434694106185e-05, + "loss": 3.4569, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065048746595665e-05, + "loss": 3.4675, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056679177888878e-05, + "loss": 3.4624, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048293230378358e-05, + "loss": 3.4721, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4039907282867838e-05, + "loss": 3.4681, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031521335357318e-05, + "loss": 3.4618, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023135387846798e-05, + "loss": 3.4645, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014749440336278e-05, + "loss": 3.4596, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006363492825758e-05, + "loss": 3.463, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399799392411897e-05, + "loss": 3.4538, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398960797660845e-05, + "loss": 3.4668, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398122202909793e-05, + "loss": 3.458, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972836081587407e-05, + "loss": 3.46, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964450134076886e-05, + "loss": 3.4597, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395606418656637e-05, + "loss": 3.4678, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394767823905585e-05, + "loss": 3.4573, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393929229154533e-05, + "loss": 3.4636, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393092272283854e-05, + "loss": 3.4549, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392255315413175e-05, + "loss": 3.4709, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391416720662123e-05, + "loss": 3.4674, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.390578125911071e-05, + "loss": 3.4637, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.389739531160019e-05, + "loss": 3.4596, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388900936408967e-05, + "loss": 3.4586, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388062341657915e-05, + "loss": 3.4684, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387223746906863e-05, + "loss": 3.4639, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386386790036184e-05, + "loss": 3.4557, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855481952851323e-05, + "loss": 3.4678, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847096005340803e-05, + "loss": 3.4649, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838710057830283e-05, + "loss": 3.4742, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.383032411031976e-05, + "loss": 3.4622, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382193816280924e-05, + "loss": 3.4683, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813568594102452e-05, + "loss": 3.4649, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805182646591932e-05, + "loss": 3.4586, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796796699081412e-05, + "loss": 3.4677, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788410751570892e-05, + "loss": 3.4675, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780041182864105e-05, + "loss": 3.465, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771655235353585e-05, + "loss": 3.4498, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376326928784306e-05, + "loss": 3.4599, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.85941743850708, + "eval_runtime": 308.1144, + "eval_samples_per_second": 1238.472, + "eval_steps_per_second": 38.703, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375488334033254e-05, + "loss": 3.4552, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746497392822025e-05, + "loss": 3.4547, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738127824115234e-05, + "loss": 3.471, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729741876604714e-05, + "loss": 3.4765, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721355929094194e-05, + "loss": 3.4691, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3712969981583674e-05, + "loss": 3.4595, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3704584034073153e-05, + "loss": 3.4609, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696214465366366e-05, + "loss": 3.4474, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3687828517855846e-05, + "loss": 3.4672, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679442570345326e-05, + "loss": 3.4688, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671056622834806e-05, + "loss": 3.4585, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662687054128015e-05, + "loss": 3.4655, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654301106617495e-05, + "loss": 3.455, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3645915159106978e-05, + "loss": 3.46, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637529211596458e-05, + "loss": 3.4503, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629143264085938e-05, + "loss": 3.4536, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620757316575415e-05, + "loss": 3.4536, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612371369064895e-05, + "loss": 3.4534, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3603985421554375e-05, + "loss": 3.4625, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595615852847587e-05, + "loss": 3.4709, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587229905337067e-05, + "loss": 3.4682, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357886033663028e-05, + "loss": 3.4647, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357047438911976e-05, + "loss": 3.459, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562088441609236e-05, + "loss": 3.4669, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553702494098716e-05, + "loss": 3.4505, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545316546588196e-05, + "loss": 3.4664, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3536946977881412e-05, + "loss": 3.4556, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.352856103037089e-05, + "loss": 3.4487, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.352017508286037e-05, + "loss": 3.4519, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.351178913534985e-05, + "loss": 3.4576, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503403187839328e-05, + "loss": 3.4594, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.349503361913254e-05, + "loss": 3.4597, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.348664767162202e-05, + "loss": 3.4657, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.34782617241115e-05, + "loss": 3.4634, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.346987577660098e-05, + "loss": 3.451, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346148982909046e-05, + "loss": 3.4635, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345310388157994e-05, + "loss": 3.4553, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444717934069417e-05, + "loss": 3.4553, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436348365362633e-05, + "loss": 3.4472, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3427962417852113e-05, + "loss": 3.4546, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419576470341593e-05, + "loss": 3.4582, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.341119052283107e-05, + "loss": 3.4661, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340280457532055e-05, + "loss": 3.4567, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339441862781003e-05, + "loss": 3.4572, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386049059103242e-05, + "loss": 3.465, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377663111592722e-05, + "loss": 3.4635, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369277164082202e-05, + "loss": 3.4626, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3360891216571682e-05, + "loss": 3.4464, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.335250526906116e-05, + "loss": 3.4359, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334413570035437e-05, + "loss": 3.4708, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333574975284385e-05, + "loss": 3.4631, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327363805333334e-05, + "loss": 3.4585, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3318977857822814e-05, + "loss": 3.4553, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310591910312294e-05, + "loss": 3.4498, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302205962801774e-05, + "loss": 3.4398, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329382001529125e-05, + "loss": 3.452, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.328543406778073e-05, + "loss": 3.4448, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277064499073943e-05, + "loss": 3.456, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268678551563426e-05, + "loss": 3.462, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260308982856635e-05, + "loss": 3.4504, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3251923035346115e-05, + "loss": 3.444, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243537087835595e-05, + "loss": 3.4624, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235151140325072e-05, + "loss": 3.4426, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3226765192814555e-05, + "loss": 3.4432, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3218395624107768e-05, + "loss": 3.4581, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210009676597248e-05, + "loss": 3.4555, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201623729086724e-05, + "loss": 3.4457, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193237781576204e-05, + "loss": 3.4461, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3184851834065684e-05, + "loss": 3.448, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176465886555164e-05, + "loss": 3.4503, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168079939044644e-05, + "loss": 3.4578, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3159710370337857e-05, + "loss": 3.4457, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151324422827336e-05, + "loss": 3.4596, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3142954854120546e-05, + "loss": 3.4585, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134568906610026e-05, + "loss": 3.4579, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126182959099506e-05, + "loss": 3.4437, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311779701158899e-05, + "loss": 3.4587, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109427442882198e-05, + "loss": 3.4586, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101041495371678e-05, + "loss": 3.4428, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3092655547861158e-05, + "loss": 3.4584, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084269600350638e-05, + "loss": 3.4534, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3075883652840118e-05, + "loss": 3.4636, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.306751408413333e-05, + "loss": 3.4485, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305912813662281e-05, + "loss": 3.4337, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305074218911229e-05, + "loss": 3.4483, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304235624160177e-05, + "loss": 3.4497, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303397029409125e-05, + "loss": 3.4551, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025584346580727e-05, + "loss": 3.4522, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301719839907021e-05, + "loss": 3.444, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3008828830363422e-05, + "loss": 3.4546, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000442882852902e-05, + "loss": 3.4513, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299205693534238e-05, + "loss": 3.445, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298367098783186e-05, + "loss": 3.4533, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297528504032134e-05, + "loss": 3.458, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296691547161455e-05, + "loss": 3.4646, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.295852952410403e-05, + "loss": 3.4499, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.295014357659351e-05, + "loss": 3.4366, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.294175762908299e-05, + "loss": 3.4578, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.29333880603762e-05, + "loss": 3.4469, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292500211286568e-05, + "loss": 3.4562, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916616165355164e-05, + "loss": 3.4586, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908230217844644e-05, + "loss": 3.4436, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2899844270334124e-05, + "loss": 3.4473, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891458322823604e-05, + "loss": 3.4543, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883088754116813e-05, + "loss": 3.4401, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2874702806606293e-05, + "loss": 3.455, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866316859095773e-05, + "loss": 3.4396, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2857930911585252e-05, + "loss": 3.4568, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849561342878465e-05, + "loss": 3.4382, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841175395367945e-05, + "loss": 3.4543, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2832789447857425e-05, + "loss": 3.4457, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824403500346905e-05, + "loss": 3.442, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281601755283638e-05, + "loss": 3.4573, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2807647984129597e-05, + "loss": 3.4476, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799262036619077e-05, + "loss": 3.4603, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2790876089108557e-05, + "loss": 3.4601, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782490141598034e-05, + "loss": 3.4483, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774104194087514e-05, + "loss": 3.4557, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2765718246576994e-05, + "loss": 3.4487, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757332299066474e-05, + "loss": 3.4511, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2748946351555957e-05, + "loss": 3.447, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740576782849166e-05, + "loss": 3.4534, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732190835338646e-05, + "loss": 3.4468, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2723804887828126e-05, + "loss": 3.4478, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715418940317606e-05, + "loss": 3.452, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.270704937161082e-05, + "loss": 3.4556, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.26986634241003e-05, + "loss": 3.4432, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.269027747658978e-05, + "loss": 3.4517, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2681891529079258e-05, + "loss": 3.4437, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673521960372467e-05, + "loss": 3.4654, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665136012861947e-05, + "loss": 3.4489, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2656750065351427e-05, + "loss": 3.4582, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264836411784091e-05, + "loss": 3.4456, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2639978170330387e-05, + "loss": 3.4495, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631592222819867e-05, + "loss": 3.457, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623206275309347e-05, + "loss": 3.4512, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.261483670660256e-05, + "loss": 3.4466, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606450759092036e-05, + "loss": 3.4588, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.259806481158152e-05, + "loss": 3.4541, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589678864071e-05, + "loss": 3.4647, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.258129291656048e-05, + "loss": 3.4479, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257290696904996e-05, + "loss": 3.4584, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256452102153944e-05, + "loss": 3.4527, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255615145283265e-05, + "loss": 3.4491, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.254776550532213e-05, + "loss": 3.4558, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539379557811612e-05, + "loss": 3.4556, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.253099361030109e-05, + "loss": 3.4603, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522607662790568e-05, + "loss": 3.4311, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514221715280048e-05, + "loss": 3.4541, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8597023487091064, + "eval_runtime": 308.9133, + "eval_samples_per_second": 1235.269, + "eval_steps_per_second": 38.603, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2505835767769528e-05, + "loss": 3.4423, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497449820259008e-05, + "loss": 3.4434, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248908025155222e-05, + "loss": 3.4572, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.24806943040417e-05, + "loss": 3.4641, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.247230835653118e-05, + "loss": 3.4583, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.246392240902066e-05, + "loss": 3.4453, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245553646151014e-05, + "loss": 3.4505, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244715051399962e-05, + "loss": 3.4384, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243878094529283e-05, + "loss": 3.4541, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430394997782313e-05, + "loss": 3.4557, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422009050271793e-05, + "loss": 3.4549, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413623102761273e-05, + "loss": 3.4498, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240523715525075e-05, + "loss": 3.4481, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2396867586543962e-05, + "loss": 3.4456, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388481639033442e-05, + "loss": 3.4388, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.238009569152292e-05, + "loss": 3.439, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.23717097440124e-05, + "loss": 3.4446, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.236332379650188e-05, + "loss": 3.4433, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.235493784899136e-05, + "loss": 3.4504, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234655190148084e-05, + "loss": 3.4611, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233818233277405e-05, + "loss": 3.4603, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2329812764067266e-05, + "loss": 3.4503, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321426816556746e-05, + "loss": 3.4482, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313040869046223e-05, + "loss": 3.4542, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304654921535703e-05, + "loss": 3.44, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296285352828915e-05, + "loss": 3.4579, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2287899405318395e-05, + "loss": 3.446, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279513457807875e-05, + "loss": 3.435, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271127510297355e-05, + "loss": 3.4435, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2262741562786835e-05, + "loss": 3.4463, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254371994080044e-05, + "loss": 3.4461, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245986046569524e-05, + "loss": 3.4511, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237600099059004e-05, + "loss": 3.4521, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229214151548484e-05, + "loss": 3.4515, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2220828204037968e-05, + "loss": 3.4384, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212442256527448e-05, + "loss": 3.4575, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204056309016927e-05, + "loss": 3.4438, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2195670361506404e-05, + "loss": 3.4402, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187317171603346e-05, + "loss": 3.4422, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.217893122409283e-05, + "loss": 3.44, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.217054527658231e-05, + "loss": 3.4484, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216215932907179e-05, + "loss": 3.4564, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215377338156127e-05, + "loss": 3.4422, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214538743405075e-05, + "loss": 3.4451, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137017865343958e-05, + "loss": 3.4552, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2128631917833438e-05, + "loss": 3.457, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.212024597032292e-05, + "loss": 3.4516, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.21118600228124e-05, + "loss": 3.4366, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210349045410561e-05, + "loss": 3.4167, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209510450659509e-05, + "loss": 3.4625, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208671855908457e-05, + "loss": 3.4519, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207833261157405e-05, + "loss": 3.4492, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2069963042867263e-05, + "loss": 3.4418, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061577095356743e-05, + "loss": 3.4376, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053191147846223e-05, + "loss": 3.4303, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.20448052003357e-05, + "loss": 3.4386, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203641925282518e-05, + "loss": 3.4372, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.202803330531466e-05, + "loss": 3.4426, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.201964735780414e-05, + "loss": 3.4533, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.201127778909735e-05, + "loss": 3.4352, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.200289184158683e-05, + "loss": 3.4326, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.199450589407631e-05, + "loss": 3.4494, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198611994656579e-05, + "loss": 3.4347, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197773399905527e-05, + "loss": 3.4327, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969364430348484e-05, + "loss": 3.4436, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1960978482837964e-05, + "loss": 3.4403, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952592535327444e-05, + "loss": 3.4331, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944206587816924e-05, + "loss": 3.4351, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1935820640306404e-05, + "loss": 3.4349, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192743469279588e-05, + "loss": 3.4453, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191904874528536e-05, + "loss": 3.4418, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1910662797774843e-05, + "loss": 3.4383, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902293229068056e-05, + "loss": 3.4454, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1893923660361265e-05, + "loss": 3.4496, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885537712850745e-05, + "loss": 3.4495, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877151765340225e-05, + "loss": 3.4341, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1868765817829705e-05, + "loss": 3.4448, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860379870319185e-05, + "loss": 3.451, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1851993922808665e-05, + "loss": 3.4276, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1843607975298145e-05, + "loss": 3.4473, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835222027787625e-05, + "loss": 3.4428, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1826852459080834e-05, + "loss": 3.4484, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818482890374046e-05, + "loss": 3.4394, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181009694286353e-05, + "loss": 3.4249, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1801710995353006e-05, + "loss": 3.4352, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793325047842486e-05, + "loss": 3.4379, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1784939100331966e-05, + "loss": 3.4469, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776553152821446e-05, + "loss": 3.4396, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768167205310926e-05, + "loss": 3.4321, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.175979763660414e-05, + "loss": 3.4412, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175141168909362e-05, + "loss": 3.4454, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.17430257415831e-05, + "loss": 3.4308, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173463979407258e-05, + "loss": 3.4394, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172625384656206e-05, + "loss": 3.4492, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1717884277855267e-05, + "loss": 3.4514, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.170949833034475e-05, + "loss": 3.4413, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.170111238283423e-05, + "loss": 3.4272, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.169272643532371e-05, + "loss": 3.4443, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.168435686661692e-05, + "loss": 3.4319, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.16759709191064e-05, + "loss": 3.4453, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166758497159588e-05, + "loss": 3.4482, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165919902408536e-05, + "loss": 3.4356, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1650829455378572e-05, + "loss": 3.4362, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642443507868052e-05, + "loss": 3.4404, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634057560357532e-05, + "loss": 3.4289, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162567161284701e-05, + "loss": 3.4455, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161728566533649e-05, + "loss": 3.427, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.160889971782597e-05, + "loss": 3.4471, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600530149119184e-05, + "loss": 3.4308, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.159214420160866e-05, + "loss": 3.44, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.158375825409814e-05, + "loss": 3.4353, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.157537230658762e-05, + "loss": 3.4342, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.15669863590771e-05, + "loss": 3.4411, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1558616790370313e-05, + "loss": 3.4381, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550230842859793e-05, + "loss": 3.4518, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1541844895349273e-05, + "loss": 3.4459, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533458947838753e-05, + "loss": 3.4385, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525089379131962e-05, + "loss": 3.4433, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1516703431621442e-05, + "loss": 3.4355, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508317484110922e-05, + "loss": 3.4382, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1499931536600406e-05, + "loss": 3.4379, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1491545589089886e-05, + "loss": 3.4371, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483159641579365e-05, + "loss": 3.4384, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1474773694068842e-05, + "loss": 3.4377, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466387746558322e-05, + "loss": 3.4411, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458018177851534e-05, + "loss": 3.4406, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1449632230341014e-05, + "loss": 3.4378, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441246282830494e-05, + "loss": 3.4396, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1432860335319974e-05, + "loss": 3.431, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424490766613187e-05, + "loss": 3.4519, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416104819102663e-05, + "loss": 3.4405, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1407718871592143e-05, + "loss": 3.4487, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399332924081623e-05, + "loss": 3.4308, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1390946976571107e-05, + "loss": 3.442, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1382561029060587e-05, + "loss": 3.4444, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374191460353796e-05, + "loss": 3.4454, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1365805512843276e-05, + "loss": 3.431, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357419565332756e-05, + "loss": 3.4488, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349033617822236e-05, + "loss": 3.4404, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1340664049115448e-05, + "loss": 3.4566, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332278101604928e-05, + "loss": 3.434, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1323892154094408e-05, + "loss": 3.4496, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1315506206583888e-05, + "loss": 3.4412, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307120259073368e-05, + "loss": 3.4403, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1298750690366577e-05, + "loss": 3.442, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.129036474285606e-05, + "loss": 3.4435, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.128197879534554e-05, + "loss": 3.4472, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1273592847835017e-05, + "loss": 3.424, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265206900324497e-05, + "loss": 3.4434, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8610920906066895, + "eval_runtime": 307.3121, + "eval_samples_per_second": 1241.705, + "eval_steps_per_second": 38.804, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1256820952813977e-05, + "loss": 3.4326, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248435005303457e-05, + "loss": 3.4319, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.124006543659667e-05, + "loss": 3.4436, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.123167948908615e-05, + "loss": 3.4537, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.122329354157563e-05, + "loss": 3.4462, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121490759406511e-05, + "loss": 3.4368, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120652164655459e-05, + "loss": 3.4423, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119813569904407e-05, + "loss": 3.4302, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1189766130337278e-05, + "loss": 3.4429, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.118138018282676e-05, + "loss": 3.4439, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.117299423531624e-05, + "loss": 3.4417, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.116460828780572e-05, + "loss": 3.4401, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115623871909893e-05, + "loss": 3.4332, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114785277158841e-05, + "loss": 3.4334, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113946682407789e-05, + "loss": 3.4347, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113108087656737e-05, + "loss": 3.4256, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.112269492905685e-05, + "loss": 3.4337, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111430898154633e-05, + "loss": 3.433, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110592303403581e-05, + "loss": 3.4362, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1097569844132752e-05, + "loss": 3.4458, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1089183896622232e-05, + "loss": 3.4505, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1080797949111715e-05, + "loss": 3.4435, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1072412001601195e-05, + "loss": 3.4352, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106402605409067e-05, + "loss": 3.4423, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1055656485383884e-05, + "loss": 3.4322, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047270537873364e-05, + "loss": 3.4453, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1038884590362844e-05, + "loss": 3.435, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1030498642852324e-05, + "loss": 3.4264, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022112695341804e-05, + "loss": 3.4355, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1013726747831284e-05, + "loss": 3.429, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005357179124496e-05, + "loss": 3.4332, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0996971231613973e-05, + "loss": 3.4433, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0988585284103453e-05, + "loss": 3.4388, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980199336592933e-05, + "loss": 3.4393, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0971813389082416e-05, + "loss": 3.4285, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963427441571896e-05, + "loss": 3.4474, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955041494061376e-05, + "loss": 3.435, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0946655546550853e-05, + "loss": 3.4316, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938302356647794e-05, + "loss": 3.435, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0929916409137278e-05, + "loss": 3.4283, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0921530461626758e-05, + "loss": 3.4359, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913144514116238e-05, + "loss": 3.4414, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0904758566605717e-05, + "loss": 3.4371, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0896372619095197e-05, + "loss": 3.431, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888003050388407e-05, + "loss": 3.4445, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0879617102877886e-05, + "loss": 3.4434, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.087123115536737e-05, + "loss": 3.4427, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086284520785685e-05, + "loss": 3.4266, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0854459260346326e-05, + "loss": 3.4054, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0846073312835806e-05, + "loss": 3.4558, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083770374412902e-05, + "loss": 3.4364, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.08293177966185e-05, + "loss": 3.4388, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.082093184910798e-05, + "loss": 3.434, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081254590159746e-05, + "loss": 3.4239, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080415995408694e-05, + "loss": 3.4233, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079579038538015e-05, + "loss": 3.4263, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0787404437869628e-05, + "loss": 3.425, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0779018490359108e-05, + "loss": 3.4295, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077063254284859e-05, + "loss": 3.4469, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.076224659533807e-05, + "loss": 3.4231, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075386064782755e-05, + "loss": 3.4208, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074547470031703e-05, + "loss": 3.4436, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0737088752806507e-05, + "loss": 3.419, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.072871918409972e-05, + "loss": 3.4224, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0720349615392932e-05, + "loss": 3.4343, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0711963667882412e-05, + "loss": 3.4311, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0703577720371892e-05, + "loss": 3.4194, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695191772861372e-05, + "loss": 3.4304, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0686805825350852e-05, + "loss": 3.4198, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.067841987784033e-05, + "loss": 3.4339, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.067003393032981e-05, + "loss": 3.4321, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0661664361623025e-05, + "loss": 3.4258, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653278414112505e-05, + "loss": 3.4356, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0644908845405714e-05, + "loss": 3.4367, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0636522897895194e-05, + "loss": 3.4416, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628136950384674e-05, + "loss": 3.4233, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0619751002874154e-05, + "loss": 3.4337, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0611365055363633e-05, + "loss": 3.4391, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0602979107853113e-05, + "loss": 3.416, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0594593160342593e-05, + "loss": 3.4409, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586207212832073e-05, + "loss": 3.4322, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0577837644125282e-05, + "loss": 3.4388, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0569468075418495e-05, + "loss": 3.4329, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0561082127907978e-05, + "loss": 3.4159, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0552696180397455e-05, + "loss": 3.4173, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544310232886935e-05, + "loss": 3.4277, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0535924285376415e-05, + "loss": 3.4389, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0527538337865895e-05, + "loss": 3.4252, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519152390355375e-05, + "loss": 3.4255, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0510782821648587e-05, + "loss": 3.4299, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0502396874138067e-05, + "loss": 3.433, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0494010926627547e-05, + "loss": 3.4224, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0485624979117027e-05, + "loss": 3.4259, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477239031606507e-05, + "loss": 3.4373, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0468853084095984e-05, + "loss": 3.4369, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460467136585463e-05, + "loss": 3.4318, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452081189074947e-05, + "loss": 3.4184, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044371162036816e-05, + "loss": 3.4344, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0435325672857636e-05, + "loss": 3.4213, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0426939725347116e-05, + "loss": 3.4358, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0418553777836596e-05, + "loss": 3.4328, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410167830326076e-05, + "loss": 3.4292, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0401798261619288e-05, + "loss": 3.427, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393412314108768e-05, + "loss": 3.4244, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385026366598248e-05, + "loss": 3.4203, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0376640419087728e-05, + "loss": 3.4325, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0368254471577208e-05, + "loss": 3.4184, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0359868524066688e-05, + "loss": 3.4368, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.03514989553599e-05, + "loss": 3.4205, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.034311300784938e-05, + "loss": 3.4277, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.033472706033886e-05, + "loss": 3.4237, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032634111282834e-05, + "loss": 3.42, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0317955165317817e-05, + "loss": 3.4339, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0309569217807297e-05, + "loss": 3.4264, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301183270296777e-05, + "loss": 3.4422, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0292813701589993e-05, + "loss": 3.4359, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.028442775407947e-05, + "loss": 3.427, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.027604180656895e-05, + "loss": 3.4298, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026765585905843e-05, + "loss": 3.4275, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025926991154791e-05, + "loss": 3.4279, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.025088396403739e-05, + "loss": 3.4298, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.024249801652687e-05, + "loss": 3.4246, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.023412844782008e-05, + "loss": 3.4276, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022574250030956e-05, + "loss": 3.4281, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021735655279904e-05, + "loss": 3.4302, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020897060528852e-05, + "loss": 3.4308, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0200584657777998e-05, + "loss": 3.4228, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192198710267478e-05, + "loss": 3.4273, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0183812762756958e-05, + "loss": 3.4225, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0175443194050174e-05, + "loss": 3.4416, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.016705724653965e-05, + "loss": 3.4305, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.015867129902913e-05, + "loss": 3.4343, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.015028535151861e-05, + "loss": 3.4222, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014189940400809e-05, + "loss": 3.4325, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013351345649757e-05, + "loss": 3.431, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125143887790783e-05, + "loss": 3.4336, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0116757940280263e-05, + "loss": 3.4235, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0108371992769743e-05, + "loss": 3.4335, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0099986045259223e-05, + "loss": 3.4296, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.009161647655243e-05, + "loss": 3.4502, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.008323052904191e-05, + "loss": 3.4213, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0074844581531395e-05, + "loss": 3.4387, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0066458634020875e-05, + "loss": 3.432, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.005807268651035e-05, + "loss": 3.4301, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0049703117803564e-05, + "loss": 3.4319, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041317170293044e-05, + "loss": 3.4342, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0032931222782524e-05, + "loss": 3.4352, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0024545275272004e-05, + "loss": 3.4145, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0016159327761484e-05, + "loss": 3.4334, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8616771697998047, + "eval_runtime": 306.6689, + "eval_samples_per_second": 1244.309, + "eval_steps_per_second": 38.886, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0007773380250964e-05, + "loss": 3.4178, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999387432740444e-05, + "loss": 3.42, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991017864033653e-05, + "loss": 3.431, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9982631916523133e-05, + "loss": 3.4436, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9974245969012616e-05, + "loss": 3.4366, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9965860021502096e-05, + "loss": 3.4239, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9957474073991576e-05, + "loss": 3.4341, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949088126481056e-05, + "loss": 3.4188, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9940718557774265e-05, + "loss": 3.4303, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932332610263745e-05, + "loss": 3.437, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9923946662753225e-05, + "loss": 3.4319, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9915560715242705e-05, + "loss": 3.429, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907191146535917e-05, + "loss": 3.4261, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9898805199025397e-05, + "loss": 3.4209, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890419251514877e-05, + "loss": 3.421, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882033304004357e-05, + "loss": 3.4153, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9873647356493834e-05, + "loss": 3.4223, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865261408983317e-05, + "loss": 3.4279, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9856875461472797e-05, + "loss": 3.4224, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9848505892766006e-05, + "loss": 3.4353, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840119945255486e-05, + "loss": 3.4402, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.98317503765487e-05, + "loss": 3.4342, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.982336442903818e-05, + "loss": 3.4253, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.981497848152766e-05, + "loss": 3.4288, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.980659253401714e-05, + "loss": 3.4269, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979820658650662e-05, + "loss": 3.4278, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.978983701779983e-05, + "loss": 3.4262, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9781451070289307e-05, + "loss": 3.4194, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773065122778787e-05, + "loss": 3.4232, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.976467917526827e-05, + "loss": 3.4211, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.975630960656148e-05, + "loss": 3.4194, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.974792365905096e-05, + "loss": 3.432, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.973953771154044e-05, + "loss": 3.4324, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973115176402992e-05, + "loss": 3.4278, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.97227658165194e-05, + "loss": 3.4206, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971437986900888e-05, + "loss": 3.4303, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9705993921498363e-05, + "loss": 3.4246, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969760797398784e-05, + "loss": 3.4226, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.968925478408478e-05, + "loss": 3.4217, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.968086883657426e-05, + "loss": 3.4136, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967248288906374e-05, + "loss": 3.4239, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9664096941553224e-05, + "loss": 3.4315, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9655710994042704e-05, + "loss": 3.425, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9647325046532184e-05, + "loss": 3.4229, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.963893909902166e-05, + "loss": 3.4365, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.963055315151114e-05, + "loss": 3.4291, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622183582804353e-05, + "loss": 3.429, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9613797635293833e-05, + "loss": 3.4226, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9605428066587046e-05, + "loss": 3.3929, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597042119076526e-05, + "loss": 3.44, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9588656171566006e-05, + "loss": 3.4255, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580270224055486e-05, + "loss": 3.4289, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9571900655348695e-05, + "loss": 3.4265, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9563514707838175e-05, + "loss": 3.4142, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555128760327658e-05, + "loss": 3.407, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9546742812817135e-05, + "loss": 3.4187, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9538356865306615e-05, + "loss": 3.4155, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9529970917796095e-05, + "loss": 3.4161, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9521584970285575e-05, + "loss": 3.4363, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513199022775054e-05, + "loss": 3.4161, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9504829454068267e-05, + "loss": 3.4091, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9496443506557747e-05, + "loss": 3.433, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488057559047227e-05, + "loss": 3.4076, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9479671611536707e-05, + "loss": 3.4111, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471302042829916e-05, + "loss": 3.426, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9462916095319396e-05, + "loss": 3.4225, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.945453014780888e-05, + "loss": 3.4101, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.944614420029836e-05, + "loss": 3.4161, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943775825278784e-05, + "loss": 3.4119, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9429372305277316e-05, + "loss": 3.4239, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9420986357766796e-05, + "loss": 3.4199, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9412600410256276e-05, + "loss": 3.416, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404230841549488e-05, + "loss": 3.423, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.93958612728427e-05, + "loss": 3.4239, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.938747532533218e-05, + "loss": 3.4318, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.937908937782166e-05, + "loss": 3.4137, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9370703430311137e-05, + "loss": 3.4246, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362317482800617e-05, + "loss": 3.427, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9353931535290097e-05, + "loss": 3.4037, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.934554558777958e-05, + "loss": 3.4269, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.933715964026906e-05, + "loss": 3.4248, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932879007156227e-05, + "loss": 3.4307, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9320420502855482e-05, + "loss": 3.4218, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9312034555344962e-05, + "loss": 3.4092, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9303648607834442e-05, + "loss": 3.4033, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9295262660323922e-05, + "loss": 3.4167, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.92868767128134e-05, + "loss": 3.4263, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.927849076530288e-05, + "loss": 3.4145, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.927010481779236e-05, + "loss": 3.4129, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.926173524908557e-05, + "loss": 3.4182, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925334930157505e-05, + "loss": 3.4282, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9244963354064534e-05, + "loss": 3.4136, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9236577406554014e-05, + "loss": 3.4156, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228191459043494e-05, + "loss": 3.4243, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.921980551153297e-05, + "loss": 3.4298, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.921141956402245e-05, + "loss": 3.4192, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920303361651193e-05, + "loss": 3.4071, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9194664047805143e-05, + "loss": 3.4195, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186278100294623e-05, + "loss": 3.4141, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9177892152784103e-05, + "loss": 3.4247, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9169506205273583e-05, + "loss": 3.4238, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161120257763063e-05, + "loss": 3.419, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9152750689056272e-05, + "loss": 3.414, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9144364741545752e-05, + "loss": 3.4108, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9135978794035235e-05, + "loss": 3.4166, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9127592846524715e-05, + "loss": 3.4202, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119206899014195e-05, + "loss": 3.4073, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9110820951503675e-05, + "loss": 3.4282, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9102451382796884e-05, + "loss": 3.4117, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094065435286364e-05, + "loss": 3.4134, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9085679487775844e-05, + "loss": 3.4098, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077293540265327e-05, + "loss": 3.4065, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9068907592754804e-05, + "loss": 3.4271, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9060538024048016e-05, + "loss": 3.4113, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052152076537496e-05, + "loss": 3.432, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9043766129026973e-05, + "loss": 3.4271, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9035380181516456e-05, + "loss": 3.4183, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9026994234005936e-05, + "loss": 3.4183, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9018608286495416e-05, + "loss": 3.4213, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010238717788625e-05, + "loss": 3.4157, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9001852770278105e-05, + "loss": 3.4215, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8993466822767585e-05, + "loss": 3.4116, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985080875257065e-05, + "loss": 3.4189, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8976694927746545e-05, + "loss": 3.4136, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896830898023603e-05, + "loss": 3.4215, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.895992303272551e-05, + "loss": 3.4177, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8951537085214985e-05, + "loss": 3.4138, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943167516508197e-05, + "loss": 3.4182, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8934781568997677e-05, + "loss": 3.4132, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.892641200029089e-05, + "loss": 3.4304, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.891802605278037e-05, + "loss": 3.4181, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.890964010526985e-05, + "loss": 3.423, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890125415775933e-05, + "loss": 3.4097, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8892868210248806e-05, + "loss": 3.4254, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8884482262738286e-05, + "loss": 3.4157, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876096315227766e-05, + "loss": 3.4227, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.886771036771725e-05, + "loss": 3.4138, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.885934079901046e-05, + "loss": 3.4236, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.885095485149994e-05, + "loss": 3.4204, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884256890398942e-05, + "loss": 3.441, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.88341829564789e-05, + "loss": 3.41, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.882579700896838e-05, + "loss": 3.4242, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.881742744026159e-05, + "loss": 3.4215, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.880904149275107e-05, + "loss": 3.4228, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.880065554524055e-05, + "loss": 3.4175, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.879226959773003e-05, + "loss": 3.4247, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.878390002902324e-05, + "loss": 3.4224, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.877551408151272e-05, + "loss": 3.4117, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.87671281340022e-05, + "loss": 3.4173, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.863219976425171, + "eval_runtime": 303.3903, + "eval_samples_per_second": 1257.756, + "eval_steps_per_second": 39.306, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8758742186491683e-05, + "loss": 3.4115, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.875035623898116e-05, + "loss": 3.4068, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8741986670274372e-05, + "loss": 3.4187, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8733600722763852e-05, + "loss": 3.4364, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8725214775253332e-05, + "loss": 3.4277, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8716828827742812e-05, + "loss": 3.4108, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8708442880232292e-05, + "loss": 3.4258, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700056932721772e-05, + "loss": 3.4086, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8691670985211252e-05, + "loss": 3.4172, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.868330141650446e-05, + "loss": 3.4277, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.867491546899394e-05, + "loss": 3.4177, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.866652952148342e-05, + "loss": 3.4171, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658143573972904e-05, + "loss": 3.4194, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8649774005266113e-05, + "loss": 3.412, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8641388057755593e-05, + "loss": 3.4099, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633002110245073e-05, + "loss": 3.4062, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8624616162734553e-05, + "loss": 3.4093, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8616230215224033e-05, + "loss": 3.4163, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8607844267713513e-05, + "loss": 3.4109, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8599458320202993e-05, + "loss": 3.4249, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591088751496206e-05, + "loss": 3.4289, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8582702803985686e-05, + "loss": 3.4244, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8574316856475166e-05, + "loss": 3.4177, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8565930908964642e-05, + "loss": 3.4139, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8557561340257858e-05, + "loss": 3.4207, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8549175392747338e-05, + "loss": 3.4161, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8540789445236814e-05, + "loss": 3.4144, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8532403497726294e-05, + "loss": 3.4124, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524017550215774e-05, + "loss": 3.4108, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8515631602705254e-05, + "loss": 3.4115, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8507262033998467e-05, + "loss": 3.4115, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8498876086487947e-05, + "loss": 3.4192, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8490490138977427e-05, + "loss": 3.427, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8482104191466907e-05, + "loss": 3.4135, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8473718243956387e-05, + "loss": 3.4134, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8465332296445867e-05, + "loss": 3.4103, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8456946348935347e-05, + "loss": 3.4215, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8448560401424823e-05, + "loss": 3.4113, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440207211521768e-05, + "loss": 3.4127, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8431821264011248e-05, + "loss": 3.4004, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8423435316500728e-05, + "loss": 3.4176, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8415049368990208e-05, + "loss": 3.4155, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8406663421479688e-05, + "loss": 3.4145, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8398277473969168e-05, + "loss": 3.4154, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.838990790526238e-05, + "loss": 3.421, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.838152195775186e-05, + "loss": 3.42, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837313601024134e-05, + "loss": 3.4205, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.836475006273082e-05, + "loss": 3.4109, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8356364115220297e-05, + "loss": 3.3832, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8347994546513513e-05, + "loss": 3.4272, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8339608599002993e-05, + "loss": 3.4161, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.833122265149247e-05, + "loss": 3.4193, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.832283670398195e-05, + "loss": 3.4154, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.831445075647143e-05, + "loss": 3.4063, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.830606480896091e-05, + "loss": 3.3998, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.829767886145039e-05, + "loss": 3.4045, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.828929291393987e-05, + "loss": 3.407, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.828092334523308e-05, + "loss": 3.4053, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.827253739772256e-05, + "loss": 3.4246, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.826416782901577e-05, + "loss": 3.4087, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.825578188150525e-05, + "loss": 3.3942, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.824739593399473e-05, + "loss": 3.4231, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239009986484214e-05, + "loss": 3.3995, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8230624038973694e-05, + "loss": 3.3989, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8222254470266903e-05, + "loss": 3.4152, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8213868522756383e-05, + "loss": 3.4098, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8205482575245863e-05, + "loss": 3.4031, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197096627735343e-05, + "loss": 3.4046, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.8188710680224823e-05, + "loss": 3.4025, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8180324732714303e-05, + "loss": 3.4101, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8171938785203783e-05, + "loss": 3.4083, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8163552837693263e-05, + "loss": 3.4103, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.815518326898647e-05, + "loss": 3.4121, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8146813700279684e-05, + "loss": 3.4142, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.8138427752769167e-05, + "loss": 3.4233, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8130041805258647e-05, + "loss": 3.4021, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8121655857748124e-05, + "loss": 3.412, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8113269910237604e-05, + "loss": 3.4188, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8104883962727084e-05, + "loss": 3.3943, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8096498015216564e-05, + "loss": 3.4121, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088112067706044e-05, + "loss": 3.418, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8079742498999256e-05, + "loss": 3.4183, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.807137293029247e-05, + "loss": 3.4153, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8062986982781945e-05, + "loss": 3.393, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8054601035271425e-05, + "loss": 3.3913, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046215087760905e-05, + "loss": 3.4107, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8037829140250385e-05, + "loss": 3.4154, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.802944319273987e-05, + "loss": 3.4022, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.802105724522935e-05, + "loss": 3.4075, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8012687676522558e-05, + "loss": 3.4043, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8004301729012038e-05, + "loss": 3.4153, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7995915781501518e-05, + "loss": 3.4062, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7987529833990997e-05, + "loss": 3.4074, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979143886480477e-05, + "loss": 3.4105, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.797077431777369e-05, + "loss": 3.4177, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.796238837026317e-05, + "loss": 3.4126, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795400242275265e-05, + "loss": 3.401, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7945616475242126e-05, + "loss": 3.4072, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7937230527731606e-05, + "loss": 3.4031, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7928860959024822e-05, + "loss": 3.4131, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7920475011514302e-05, + "loss": 3.4118, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.791208906400378e-05, + "loss": 3.409, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.790370311649326e-05, + "loss": 3.4055, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.789531716898274e-05, + "loss": 3.4009, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.788694760027595e-05, + "loss": 3.4104, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.787856165276543e-05, + "loss": 3.4049, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.787017570525491e-05, + "loss": 3.3991, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.786178975774439e-05, + "loss": 3.4172, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.785340381023387e-05, + "loss": 3.4021, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.784503424152708e-05, + "loss": 3.4047, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.783664829401656e-05, + "loss": 3.4015, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782826234650604e-05, + "loss": 3.3954, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7819876398995523e-05, + "loss": 3.4146, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7811490451485003e-05, + "loss": 3.4047, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803120882778212e-05, + "loss": 3.4198, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7794734935267692e-05, + "loss": 3.4145, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7786348987757172e-05, + "loss": 3.4101, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7777979419050385e-05, + "loss": 3.4069, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7769593471539865e-05, + "loss": 3.4105, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7761207524029345e-05, + "loss": 3.4032, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7752821576518825e-05, + "loss": 3.4129, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7744435629008305e-05, + "loss": 3.408, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.773604968149778e-05, + "loss": 3.405, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772766373398726e-05, + "loss": 3.4024, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.7719277786476744e-05, + "loss": 3.4121, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.7710908217769957e-05, + "loss": 3.4104, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7702522270259434e-05, + "loss": 3.4028, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694136322748913e-05, + "loss": 3.4094, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7685750375238393e-05, + "loss": 3.3948, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7677380806531606e-05, + "loss": 3.428, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7668994859021086e-05, + "loss": 3.4064, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7660608911510566e-05, + "loss": 3.4139, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7652222964000046e-05, + "loss": 3.4005, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7643837016489526e-05, + "loss": 3.4158, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7635451068979006e-05, + "loss": 3.4066, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627065121468486e-05, + "loss": 3.4106, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7618679173957962e-05, + "loss": 3.4057, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7610309605251178e-05, + "loss": 3.4073, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7601923657740658e-05, + "loss": 3.4099, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7593537710230138e-05, + "loss": 3.4318, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7585151762719615e-05, + "loss": 3.4005, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7576765815209095e-05, + "loss": 3.4171, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7568379867698574e-05, + "loss": 3.4148, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560010298991787e-05, + "loss": 3.4092, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7551624351481267e-05, + "loss": 3.4057, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7543238403970747e-05, + "loss": 3.4126, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7534852456460227e-05, + "loss": 3.4107, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7526466508949707e-05, + "loss": 3.4042, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518080561439187e-05, + "loss": 3.4093, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8642055988311768, + "eval_runtime": 304.163, + "eval_samples_per_second": 1254.561, + "eval_steps_per_second": 39.206, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7509694613928667e-05, + "loss": 3.3994, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7501308666418147e-05, + "loss": 3.395, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.749293909771136e-05, + "loss": 3.4104, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.748455315020084e-05, + "loss": 3.4231, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.747616720269032e-05, + "loss": 3.4201, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7467781255179796e-05, + "loss": 3.4012, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7459395307669276e-05, + "loss": 3.4111, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451009360158756e-05, + "loss": 3.4028, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7442639791451968e-05, + "loss": 3.4062, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7434253843941448e-05, + "loss": 3.4185, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7425867896430928e-05, + "loss": 3.407, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7417481948920408e-05, + "loss": 3.411, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7409112380213617e-05, + "loss": 3.4096, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.74007264327031e-05, + "loss": 3.4013, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.739234048519258e-05, + "loss": 3.3977, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.738395453768206e-05, + "loss": 3.3918, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.737556859017154e-05, + "loss": 3.4023, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736718264266102e-05, + "loss": 3.409, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.73587966951505e-05, + "loss": 3.397, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7350410747639977e-05, + "loss": 3.4129, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342041178933193e-05, + "loss": 3.4185, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7333655231422672e-05, + "loss": 3.4113, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.732526928391215e-05, + "loss": 3.4086, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.731688333640163e-05, + "loss": 3.4039, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730851376769484e-05, + "loss": 3.4094, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7300144198988054e-05, + "loss": 3.4072, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7291758251477534e-05, + "loss": 3.4, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7283372303967014e-05, + "loss": 3.4002, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7274986356456494e-05, + "loss": 3.4026, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7266600408945974e-05, + "loss": 3.4002, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7258230840239183e-05, + "loss": 3.4019, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7249844892728663e-05, + "loss": 3.4055, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7241458945218146e-05, + "loss": 3.4123, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233072997707623e-05, + "loss": 3.4104, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7224687050197103e-05, + "loss": 3.3964, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7216301102686583e-05, + "loss": 3.4053, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7207915155176063e-05, + "loss": 3.4104, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7199529207665543e-05, + "loss": 3.3975, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7191159638958755e-05, + "loss": 3.4043, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7182790070251968e-05, + "loss": 3.3924, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7174404122741448e-05, + "loss": 3.4069, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7166018175230924e-05, + "loss": 3.4029, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7157632227720404e-05, + "loss": 3.4049, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7149246280209884e-05, + "loss": 3.4073, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7140860332699364e-05, + "loss": 3.4101, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7132474385188847e-05, + "loss": 3.4112, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7124104816482056e-05, + "loss": 3.4144, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7115718868971536e-05, + "loss": 3.3998, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7107332921461016e-05, + "loss": 3.3741, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7098963352754225e-05, + "loss": 3.417, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.709057740524371e-05, + "loss": 3.4058, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.708219145773319e-05, + "loss": 3.4087, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.707380551022267e-05, + "loss": 3.4043, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.706541956271215e-05, + "loss": 3.3957, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057033615201625e-05, + "loss": 3.3871, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7048647667691105e-05, + "loss": 3.3965, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7040261720180585e-05, + "loss": 3.4022, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.70318921514738e-05, + "loss": 3.3895, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7023506203963278e-05, + "loss": 3.4157, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701513663525649e-05, + "loss": 3.3987, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.700675068774597e-05, + "loss": 3.3848, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699836474023545e-05, + "loss": 3.4109, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.698997879272493e-05, + "loss": 3.3881, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.698159284521441e-05, + "loss": 3.3886, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.697320689770389e-05, + "loss": 3.4029, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.696482095019337e-05, + "loss": 3.3994, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.695645138148658e-05, + "loss": 3.3912, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694806543397606e-05, + "loss": 3.394, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.693967948646554e-05, + "loss": 3.3951, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.693129353895502e-05, + "loss": 3.3977, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.692292397024823e-05, + "loss": 3.4057, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.691453802273771e-05, + "loss": 3.3982, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.690615207522719e-05, + "loss": 3.3996, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.68977825065204e-05, + "loss": 3.3979, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.688939655900988e-05, + "loss": 3.4159, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881010611499363e-05, + "loss": 3.394, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6872624663988843e-05, + "loss": 3.404, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6864238716478323e-05, + "loss": 3.4034, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6855852768967803e-05, + "loss": 3.3893, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684746682145728e-05, + "loss": 3.4023, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.683908087394676e-05, + "loss": 3.4062, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6830711305239972e-05, + "loss": 3.4076, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6822341736533185e-05, + "loss": 3.4086, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6813955789022665e-05, + "loss": 3.3796, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6805569841512145e-05, + "loss": 3.3855, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6797183894001625e-05, + "loss": 3.3981, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6788797946491105e-05, + "loss": 3.405, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6780411998980585e-05, + "loss": 3.3922, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6772026051470065e-05, + "loss": 3.3976, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6763656482763277e-05, + "loss": 3.3972, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6755270535252754e-05, + "loss": 3.4051, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6746884587742234e-05, + "loss": 3.3972, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6738498640231714e-05, + "loss": 3.3948, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6730112692721194e-05, + "loss": 3.4009, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6721743124014406e-05, + "loss": 3.408, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6713357176503886e-05, + "loss": 3.4032, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6704971228993366e-05, + "loss": 3.3872, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6696585281482846e-05, + "loss": 3.3957, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6688199333972326e-05, + "loss": 3.3966, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6679829765265538e-05, + "loss": 3.4024, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6671443817755018e-05, + "loss": 3.4013, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6663057870244498e-05, + "loss": 3.3993, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6654671922733978e-05, + "loss": 3.3945, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6646285975223458e-05, + "loss": 3.3905, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6637916406516667e-05, + "loss": 3.3982, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6629530459006147e-05, + "loss": 3.3946, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6621144511495627e-05, + "loss": 3.3906, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.661275856398511e-05, + "loss": 3.4044, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6604372616474587e-05, + "loss": 3.3918, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.65960030477678e-05, + "loss": 3.3936, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.658761710025728e-05, + "loss": 3.3907, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.657923115274676e-05, + "loss": 3.3859, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.657084520523624e-05, + "loss": 3.403, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656245925772572e-05, + "loss": 3.3979, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.65540733102152e-05, + "loss": 3.4047, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654570374150841e-05, + "loss": 3.404, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.653731779399789e-05, + "loss": 3.4029, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652893184648737e-05, + "loss": 3.3969, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6520545898976848e-05, + "loss": 3.4003, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.651215995146633e-05, + "loss": 3.3957, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.650377400395581e-05, + "loss": 3.4015, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.649540443524902e-05, + "loss": 3.3937, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.64870184877385e-05, + "loss": 3.3997, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.647863254022798e-05, + "loss": 3.3883, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.647024659271746e-05, + "loss": 3.4026, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.646186064520694e-05, + "loss": 3.3974, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.645347469769642e-05, + "loss": 3.3944, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.64450887501859e-05, + "loss": 3.396, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.643670280267538e-05, + "loss": 3.3839, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.642833323396859e-05, + "loss": 3.417, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.641994728645807e-05, + "loss": 3.3961, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.641156133894755e-05, + "loss": 3.407, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6403175391437033e-05, + "loss": 3.3925, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6394805822730242e-05, + "loss": 3.4009, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6386419875219722e-05, + "loss": 3.3977, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378033927709202e-05, + "loss": 3.4026, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.636964798019868e-05, + "loss": 3.3927, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6361278411491894e-05, + "loss": 3.395, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6352892463981374e-05, + "loss": 3.4015, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6344506516470854e-05, + "loss": 3.4232, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6336120568960334e-05, + "loss": 3.3867, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6327734621449814e-05, + "loss": 3.4095, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6319348673939294e-05, + "loss": 3.4051, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6310979105232503e-05, + "loss": 3.3975, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6302593157721986e-05, + "loss": 3.3975, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6294207210211466e-05, + "loss": 3.4027, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6285821262700946e-05, + "loss": 3.4012, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6277435315190423e-05, + "loss": 3.3966, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6269049367679903e-05, + "loss": 3.3955, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.8663737773895264, + "eval_runtime": 304.319, + "eval_samples_per_second": 1253.918, + "eval_steps_per_second": 39.186, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.6260663420169383e-05, + "loss": 3.3917, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.6252277472658863e-05, + "loss": 3.3871, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6243924282755808e-05, + "loss": 3.3995, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6235538335245288e-05, + "loss": 3.4121, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6227152387734768e-05, + "loss": 3.4111, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6218766440224244e-05, + "loss": 3.3914, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6210380492713724e-05, + "loss": 3.404, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6201994545203204e-05, + "loss": 3.3943, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.619362497649642e-05, + "loss": 3.3912, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.6185239028985897e-05, + "loss": 3.4029, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.6176853081475377e-05, + "loss": 3.4035, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6168467133964856e-05, + "loss": 3.4014, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6160097565258066e-05, + "loss": 3.3951, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.615171161774755e-05, + "loss": 3.3923, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.614332567023703e-05, + "loss": 3.3906, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.613493972272651e-05, + "loss": 3.3808, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.612655377521599e-05, + "loss": 3.3959, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.611816782770547e-05, + "loss": 3.396, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.610978188019495e-05, + "loss": 3.3886, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6101395932684425e-05, + "loss": 3.4012, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.609302636397764e-05, + "loss": 3.4102, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.608465679527085e-05, + "loss": 3.4018, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.607627084776033e-05, + "loss": 3.3992, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.606788490024981e-05, + "loss": 3.3943, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.605949895273929e-05, + "loss": 3.4031, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.605111300522877e-05, + "loss": 3.3971, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.604272705771825e-05, + "loss": 3.3903, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.603434111020773e-05, + "loss": 3.389, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.602595516269721e-05, + "loss": 3.3918, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6017585593990422e-05, + "loss": 3.3877, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.600921602528363e-05, + "loss": 3.3972, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.600083007777311e-05, + "loss": 3.3953, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5992444130262595e-05, + "loss": 3.3977, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5984058182752075e-05, + "loss": 3.4039, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.597567223524155e-05, + "loss": 3.3866, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.596728628773103e-05, + "loss": 3.3966, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.595890034022051e-05, + "loss": 3.4006, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.595053077151372e-05, + "loss": 3.3863, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.5942144824003204e-05, + "loss": 3.3964, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.5933775255296416e-05, + "loss": 3.3846, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5925389307785896e-05, + "loss": 3.3913, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5917003360275373e-05, + "loss": 3.3912, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5908617412764853e-05, + "loss": 3.3954, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5900231465254333e-05, + "loss": 3.3985, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.5891845517743813e-05, + "loss": 3.3979, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.5883459570233296e-05, + "loss": 3.4034, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.5875090001526505e-05, + "loss": 3.3992, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5866704054015985e-05, + "loss": 3.3919, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5858334485309194e-05, + "loss": 3.3676, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5849948537798674e-05, + "loss": 3.407, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5841562590288157e-05, + "loss": 3.3939, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5833176642777637e-05, + "loss": 3.4002, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5824807074070846e-05, + "loss": 3.3933, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5816421126560326e-05, + "loss": 3.3839, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5808035179049806e-05, + "loss": 3.3837, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.5799649231539286e-05, + "loss": 3.379, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5791263284028766e-05, + "loss": 3.3943, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.578287733651825e-05, + "loss": 3.3756, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.5774491389007726e-05, + "loss": 3.4103, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.576612182030094e-05, + "loss": 3.391, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.575773587279042e-05, + "loss": 3.3724, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.57493499252799e-05, + "loss": 3.4019, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.574096397776938e-05, + "loss": 3.3811, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.573257803025886e-05, + "loss": 3.3807, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.572420846155207e-05, + "loss": 3.3907, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.571582251404155e-05, + "loss": 3.3882, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5707436566531027e-05, + "loss": 3.3828, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5699050619020507e-05, + "loss": 3.3889, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5690664671509987e-05, + "loss": 3.3815, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5682278723999467e-05, + "loss": 3.3898, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.567389277648895e-05, + "loss": 3.394, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.566550682897843e-05, + "loss": 3.3857, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.565713726027164e-05, + "loss": 3.393, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.564876769156485e-05, + "loss": 3.3847, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.564038174405433e-05, + "loss": 3.4091, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5631995796543812e-05, + "loss": 3.3802, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5623609849033292e-05, + "loss": 3.3977, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5615223901522772e-05, + "loss": 3.3868, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5606837954012252e-05, + "loss": 3.3842, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5598452006501732e-05, + "loss": 3.3899, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.559006605899121e-05, + "loss": 3.396, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.558169649028442e-05, + "loss": 3.3983, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5573326921577633e-05, + "loss": 3.3951, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5564940974067113e-05, + "loss": 3.3714, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5556555026556593e-05, + "loss": 3.3754, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5548169079046073e-05, + "loss": 3.387, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5539783131535553e-05, + "loss": 3.3974, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.5531397184025033e-05, + "loss": 3.3823, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.5523011236514513e-05, + "loss": 3.3858, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.5514625289003993e-05, + "loss": 3.3863, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.5506255720297206e-05, + "loss": 3.3905, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.5497869772786682e-05, + "loss": 3.39, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5489483825276162e-05, + "loss": 3.3847, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5481097877765642e-05, + "loss": 3.3927, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5472711930255125e-05, + "loss": 3.3952, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5464325982744605e-05, + "loss": 3.3962, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5455940035234085e-05, + "loss": 3.3773, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5447570466527294e-05, + "loss": 3.3828, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5439184519016774e-05, + "loss": 3.3875, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5430798571506254e-05, + "loss": 3.3886, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5422412623995734e-05, + "loss": 3.3931, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5414026676485214e-05, + "loss": 3.3867, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5405640728974694e-05, + "loss": 3.3869, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5397254781464174e-05, + "loss": 3.3807, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5388885212757387e-05, + "loss": 3.3871, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5380499265246863e-05, + "loss": 3.3858, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5372113317736343e-05, + "loss": 3.3819, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5363727370225827e-05, + "loss": 3.3914, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5355341422715306e-05, + "loss": 3.388, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5346955475204786e-05, + "loss": 3.3825, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.5338569527694266e-05, + "loss": 3.3829, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5330183580183743e-05, + "loss": 3.3747, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5321814011476955e-05, + "loss": 3.3959, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5313428063966435e-05, + "loss": 3.3878, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.530504211645592e-05, + "loss": 3.3943, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5296656168945395e-05, + "loss": 3.3908, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5288270221434875e-05, + "loss": 3.3955, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5279900652728088e-05, + "loss": 3.3901, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5271514705217564e-05, + "loss": 3.3854, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5263128757707044e-05, + "loss": 3.393, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5254742810196526e-05, + "loss": 3.3857, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5246356862686006e-05, + "loss": 3.3829, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5237970915175488e-05, + "loss": 3.3915, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5229584967664967e-05, + "loss": 3.3837, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5221199020154447e-05, + "loss": 3.3906, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5212829451447658e-05, + "loss": 3.3845, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5204443503937138e-05, + "loss": 3.3845, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5196057556426618e-05, + "loss": 3.3871, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5187671608916098e-05, + "loss": 3.3779, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5179318419013038e-05, + "loss": 3.4049, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.517093247150252e-05, + "loss": 3.3866, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5162546523992e-05, + "loss": 3.3996, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.515416057648148e-05, + "loss": 3.3807, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.514577462897096e-05, + "loss": 3.3918, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5137388681460441e-05, + "loss": 3.3893, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5129002733949921e-05, + "loss": 3.3907, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5120616786439398e-05, + "loss": 3.3839, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5112247217732612e-05, + "loss": 3.3833, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.5103861270222092e-05, + "loss": 3.3909, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.5095475322711572e-05, + "loss": 3.41, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.508708937520105e-05, + "loss": 3.3809, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.507870342769053e-05, + "loss": 3.3972, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.507031748018001e-05, + "loss": 3.3948, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.506194791147322e-05, + "loss": 3.3833, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.50535619639627e-05, + "loss": 3.394, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.504517601645218e-05, + "loss": 3.3892, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.503679006894166e-05, + "loss": 3.3905, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5028404121431142e-05, + "loss": 3.3888, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5020018173920622e-05, + "loss": 3.3859, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.8667690753936768, + "eval_runtime": 302.5255, + "eval_samples_per_second": 1261.352, + "eval_steps_per_second": 39.418, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5011632226410102e-05, + "loss": 3.3937, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.500324627889958e-05, + "loss": 3.3713, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4994876710192793e-05, + "loss": 3.387, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4986490762682273e-05, + "loss": 3.404, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4978104815171753e-05, + "loss": 3.3951, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4969718867661231e-05, + "loss": 3.3861, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4961332920150711e-05, + "loss": 3.398, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4952946972640191e-05, + "loss": 3.3811, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4944561025129673e-05, + "loss": 3.3797, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4936191456422882e-05, + "loss": 3.3964, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4927805508912362e-05, + "loss": 3.3919, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4919419561401843e-05, + "loss": 3.3881, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4911033613891323e-05, + "loss": 3.3898, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4902664045184534e-05, + "loss": 3.3783, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4894278097674014e-05, + "loss": 3.3767, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4885892150163494e-05, + "loss": 3.3724, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4877506202652974e-05, + "loss": 3.3854, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4869120255142454e-05, + "loss": 3.3865, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4860734307631936e-05, + "loss": 3.3791, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4852348360121412e-05, + "loss": 3.3846, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4843962412610892e-05, + "loss": 3.4049, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4835609222707835e-05, + "loss": 3.386, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4827223275197315e-05, + "loss": 3.3921, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4818837327686797e-05, + "loss": 3.3863, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4810451380176277e-05, + "loss": 3.3926, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4802065432665757e-05, + "loss": 3.384, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4793695863958968e-05, + "loss": 3.3841, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4785309916448448e-05, + "loss": 3.3782, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4776923968937928e-05, + "loss": 3.3869, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4768538021427408e-05, + "loss": 3.3771, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4760152073916886e-05, + "loss": 3.3863, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4751766126406366e-05, + "loss": 3.3834, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4743396557699578e-05, + "loss": 3.3899, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4735010610189057e-05, + "loss": 3.3915, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4726624662678537e-05, + "loss": 3.3816, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4718238715168017e-05, + "loss": 3.3858, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4709852767657498e-05, + "loss": 3.3902, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4701466820146978e-05, + "loss": 3.3741, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4693080872636458e-05, + "loss": 3.3874, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4684711303929669e-05, + "loss": 3.3745, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4676325356419149e-05, + "loss": 3.3802, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4667939408908629e-05, + "loss": 3.3867, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4659553461398109e-05, + "loss": 3.389, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4651167513887587e-05, + "loss": 3.39, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4642781566377067e-05, + "loss": 3.3845, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4634395618866547e-05, + "loss": 3.3926, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4626009671356029e-05, + "loss": 3.3912, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4617640102649238e-05, + "loss": 3.3836, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.460925415513872e-05, + "loss": 3.3572, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4600884586431932e-05, + "loss": 3.3919, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4592498638921412e-05, + "loss": 3.3866, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.458411269141089e-05, + "loss": 3.3907, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.457572674390037e-05, + "loss": 3.3855, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.456734079638985e-05, + "loss": 3.3764, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.455895484887933e-05, + "loss": 3.3683, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4550568901368812e-05, + "loss": 3.3738, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4542182953858291e-05, + "loss": 3.38, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.45338133851515e-05, + "loss": 3.3668, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4525427437640982e-05, + "loss": 3.4, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4517041490130462e-05, + "loss": 3.3811, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4508671921423673e-05, + "loss": 3.3646, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4500285973913153e-05, + "loss": 3.3877, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4491900026402633e-05, + "loss": 3.3735, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4483514078892113e-05, + "loss": 3.3714, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4475144510185324e-05, + "loss": 3.379, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4466758562674804e-05, + "loss": 3.3812, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4458372615164284e-05, + "loss": 3.3663, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4449986667653763e-05, + "loss": 3.3835, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4441600720143242e-05, + "loss": 3.3696, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4433214772632722e-05, + "loss": 3.3767, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4424828825122202e-05, + "loss": 3.3861, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4416442877611683e-05, + "loss": 3.3785, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4408073308904892e-05, + "loss": 3.3791, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4399703740198107e-05, + "loss": 3.3779, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4391317792687587e-05, + "loss": 3.3998, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4382931845177066e-05, + "loss": 3.3682, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4374545897666545e-05, + "loss": 3.3873, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4366159950156025e-05, + "loss": 3.3749, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4357774002645505e-05, + "loss": 3.3736, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4349388055134985e-05, + "loss": 3.3817, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4341002107624466e-05, + "loss": 3.3821, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4332632538917675e-05, + "loss": 3.3929, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.432426297021089e-05, + "loss": 3.3884, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4315877022700366e-05, + "loss": 3.3626, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4307491075189846e-05, + "loss": 3.365, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4299105127679328e-05, + "loss": 3.372, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4290719180168808e-05, + "loss": 3.3862, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4282333232658288e-05, + "loss": 3.3751, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4273947285147768e-05, + "loss": 3.3738, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4265561337637248e-05, + "loss": 3.3833, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4257191768930458e-05, + "loss": 3.3775, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4248805821419938e-05, + "loss": 3.381, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.424041987390942e-05, + "loss": 3.3737, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4232050305202629e-05, + "loss": 3.3836, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4223664357692109e-05, + "loss": 3.3857, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.421527841018159e-05, + "loss": 3.3868, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.420689246267107e-05, + "loss": 3.3685, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4198522893964281e-05, + "loss": 3.3738, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4190136946453761e-05, + "loss": 3.379, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4181750998943241e-05, + "loss": 3.376, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4173365051432721e-05, + "loss": 3.3871, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.41649791039222e-05, + "loss": 3.3748, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.415659315641168e-05, + "loss": 3.376, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4148223587704892e-05, + "loss": 3.3741, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.413983764019437e-05, + "loss": 3.3736, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.413145169268385e-05, + "loss": 3.3793, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.412306574517333e-05, + "loss": 3.3745, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.411467979766281e-05, + "loss": 3.3806, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4106293850152292e-05, + "loss": 3.3758, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4097907902641772e-05, + "loss": 3.3723, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4089521955131252e-05, + "loss": 3.3734, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4081152386424462e-05, + "loss": 3.3624, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4072782817717672e-05, + "loss": 3.3823, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4064396870207153e-05, + "loss": 3.3822, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4056010922696633e-05, + "loss": 3.3799, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4047624975186113e-05, + "loss": 3.3843, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4039239027675593e-05, + "loss": 3.3829, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4030869458968804e-05, + "loss": 3.381, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4022483511458284e-05, + "loss": 3.3758, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4014097563947764e-05, + "loss": 3.3852, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4005711616437245e-05, + "loss": 3.3758, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3997325668926725e-05, + "loss": 3.3754, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3988939721416202e-05, + "loss": 3.3801, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3980553773905684e-05, + "loss": 3.3721, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3972167826395164e-05, + "loss": 3.3808, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3963798257688374e-05, + "loss": 3.3754, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3955412310177854e-05, + "loss": 3.3753, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3947026362667334e-05, + "loss": 3.377, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3938640415156814e-05, + "loss": 3.3696, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3930287225253758e-05, + "loss": 3.3929, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3921901277743237e-05, + "loss": 3.3773, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3913515330232717e-05, + "loss": 3.3872, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3905129382722199e-05, + "loss": 3.3732, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3896743435211676e-05, + "loss": 3.3784, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3888357487701156e-05, + "loss": 3.3834, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3879971540190637e-05, + "loss": 3.3823, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3871585592680117e-05, + "loss": 3.3772, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3863216023973328e-05, + "loss": 3.3705, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3854830076462808e-05, + "loss": 3.3826, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3846444128952288e-05, + "loss": 3.3957, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3838058181441768e-05, + "loss": 3.3775, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3829672233931248e-05, + "loss": 3.3823, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.382128628642073e-05, + "loss": 3.3856, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3812916717713939e-05, + "loss": 3.3756, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3804530770203419e-05, + "loss": 3.3847, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.37961448226929e-05, + "loss": 3.3776, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.378775887518238e-05, + "loss": 3.3788, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3779372927671857e-05, + "loss": 3.381, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3770986980161338e-05, + "loss": 3.3728, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.86806583404541, + "eval_runtime": 302.9319, + "eval_samples_per_second": 1259.659, + "eval_steps_per_second": 39.365, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3762601032650818e-05, + "loss": 3.3747, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3754215085140298e-05, + "loss": 3.3609, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3745861895237242e-05, + "loss": 3.3775, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3737475947726722e-05, + "loss": 3.398, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3729090000216201e-05, + "loss": 3.3848, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.372070405270568e-05, + "loss": 3.3762, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.371231810519516e-05, + "loss": 3.3826, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.370393215768464e-05, + "loss": 3.3753, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3695546210174121e-05, + "loss": 3.37, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.368717664146733e-05, + "loss": 3.3885, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.367879069395681e-05, + "loss": 3.3792, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3670404746446292e-05, + "loss": 3.3811, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3662018798935772e-05, + "loss": 3.3823, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3653649230228983e-05, + "loss": 3.3692, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3645263282718463e-05, + "loss": 3.3684, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3636877335207943e-05, + "loss": 3.3624, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3628491387697423e-05, + "loss": 3.3765, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3620105440186903e-05, + "loss": 3.3761, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3611719492676384e-05, + "loss": 3.373, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.360333354516586e-05, + "loss": 3.3753, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.359494759765534e-05, + "loss": 3.3957, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3586594407752284e-05, + "loss": 3.3766, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3578208460241764e-05, + "loss": 3.3793, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3569822512731246e-05, + "loss": 3.3782, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3561436565220726e-05, + "loss": 3.3843, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3553050617710206e-05, + "loss": 3.3705, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3544681049003416e-05, + "loss": 3.3705, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3536295101492896e-05, + "loss": 3.374, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3527909153982376e-05, + "loss": 3.3694, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3519523206471856e-05, + "loss": 3.3689, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3511137258961334e-05, + "loss": 3.3772, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3502751311450814e-05, + "loss": 3.3692, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3494365363940294e-05, + "loss": 3.3832, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.3485979416429776e-05, + "loss": 3.3787, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3477609847722985e-05, + "loss": 3.3713, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3469223900212465e-05, + "loss": 3.3793, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3460837952701947e-05, + "loss": 3.3779, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3452452005191427e-05, + "loss": 3.3633, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3444066057680907e-05, + "loss": 3.3766, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3435696488974117e-05, + "loss": 3.3644, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3427310541463597e-05, + "loss": 3.3689, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.3418924593953077e-05, + "loss": 3.3755, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3410538646442557e-05, + "loss": 3.3827, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3402152698932039e-05, + "loss": 3.3777, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3393766751421516e-05, + "loss": 3.3781, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3385380803910995e-05, + "loss": 3.3812, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3376994856400477e-05, + "loss": 3.3813, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3368625287693686e-05, + "loss": 3.3747, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3360239340183168e-05, + "loss": 3.3521, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3351853392672648e-05, + "loss": 3.3797, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.334348382396586e-05, + "loss": 3.3792, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3335097876455339e-05, + "loss": 3.376, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3326728307748551e-05, + "loss": 3.3754, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3318342360238031e-05, + "loss": 3.3686, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3309956412727511e-05, + "loss": 3.3591, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.330157046521699e-05, + "loss": 3.358, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.329318451770647e-05, + "loss": 3.3754, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.328479857019595e-05, + "loss": 3.3599, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.327641262268543e-05, + "loss": 3.3842, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.326802667517491e-05, + "loss": 3.3758, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3259657106468122e-05, + "loss": 3.3575, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3251271158957602e-05, + "loss": 3.3775, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3242885211447081e-05, + "loss": 3.3621, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3234499263936561e-05, + "loss": 3.3654, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3226129695229772e-05, + "loss": 3.3647, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3217743747719252e-05, + "loss": 3.3785, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3209357800208732e-05, + "loss": 3.3575, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3200971852698212e-05, + "loss": 3.3727, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3192602283991423e-05, + "loss": 3.3591, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3184216336480903e-05, + "loss": 3.3681, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3175830388970384e-05, + "loss": 3.3751, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3167444441459864e-05, + "loss": 3.3713, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.3159074872753074e-05, + "loss": 3.3687, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3150688925242555e-05, + "loss": 3.3728, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3142302977732035e-05, + "loss": 3.3877, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.3133917030221515e-05, + "loss": 3.3588, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.3125547461514726e-05, + "loss": 3.3794, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3117161514004206e-05, + "loss": 3.3666, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3108775566493686e-05, + "loss": 3.3633, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3100389618983166e-05, + "loss": 3.37, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.3092020050276377e-05, + "loss": 3.3721, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3083634102765856e-05, + "loss": 3.3808, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.3075248155255338e-05, + "loss": 3.3809, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3066862207744815e-05, + "loss": 3.3563, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3058492639038027e-05, + "loss": 3.3547, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3050106691527509e-05, + "loss": 3.3619, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3041720744016989e-05, + "loss": 3.3754, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3033334796506465e-05, + "loss": 3.3675, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3024948848995947e-05, + "loss": 3.3637, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3016562901485427e-05, + "loss": 3.3719, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3008176953974907e-05, + "loss": 3.3685, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.2999807385268118e-05, + "loss": 3.3756, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2991421437757598e-05, + "loss": 3.3629, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2983035490247078e-05, + "loss": 3.3747, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2974649542736558e-05, + "loss": 3.3722, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2966279974029768e-05, + "loss": 3.3782, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2957894026519248e-05, + "loss": 3.357, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.294950807900873e-05, + "loss": 3.365, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.294112213149821e-05, + "loss": 3.3727, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2932752562791419e-05, + "loss": 3.3676, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.29243666152809e-05, + "loss": 3.3748, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.291598066777038e-05, + "loss": 3.3658, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.290759472025986e-05, + "loss": 3.3653, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2899225151553071e-05, + "loss": 3.3664, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2890855582846284e-05, + "loss": 3.3665, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2882469635335762e-05, + "loss": 3.3659, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2874083687825242e-05, + "loss": 3.3644, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2865697740314722e-05, + "loss": 3.3699, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2857311792804202e-05, + "loss": 3.367, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2848925845293684e-05, + "loss": 3.3636, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2840539897783164e-05, + "loss": 3.366, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2832153950272644e-05, + "loss": 3.3511, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2823784381565854e-05, + "loss": 3.377, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2815398434055334e-05, + "loss": 3.3707, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2807012486544814e-05, + "loss": 3.3716, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2798626539034293e-05, + "loss": 3.377, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2790256970327505e-05, + "loss": 3.376, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2781887401620716e-05, + "loss": 3.368, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2773501454110196e-05, + "loss": 3.3661, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2765115506599676e-05, + "loss": 3.3738, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2756729559089156e-05, + "loss": 3.3661, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2748343611578636e-05, + "loss": 3.3619, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2739957664068117e-05, + "loss": 3.3718, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2731571716557594e-05, + "loss": 3.3653, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2723185769047074e-05, + "loss": 3.3712, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.2714816200340288e-05, + "loss": 3.3663, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2706430252829765e-05, + "loss": 3.3643, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2698044305319246e-05, + "loss": 3.3683, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2689658357808726e-05, + "loss": 3.3623, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2681288789101939e-05, + "loss": 3.3771, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2672902841591417e-05, + "loss": 3.377, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2664516894080897e-05, + "loss": 3.3727, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2656130946570377e-05, + "loss": 3.3615, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.264776137786359e-05, + "loss": 3.3731, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2639375430353068e-05, + "loss": 3.3724, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2630989482842548e-05, + "loss": 3.3698, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2622603535332027e-05, + "loss": 3.3665, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.261425034542897e-05, + "loss": 3.3635, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.260586439791845e-05, + "loss": 3.3771, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2597478450407932e-05, + "loss": 3.3873, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2589092502897412e-05, + "loss": 3.3657, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2580706555386889e-05, + "loss": 3.3756, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.257232060787637e-05, + "loss": 3.3758, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2563951039169583e-05, + "loss": 3.3654, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2555565091659063e-05, + "loss": 3.3743, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2547179144148541e-05, + "loss": 3.3684, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2538793196638021e-05, + "loss": 3.3667, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.2530407249127501e-05, + "loss": 3.3769, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2522021301616981e-05, + "loss": 3.3587, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.8685357570648193, + "eval_runtime": 301.8827, + "eval_samples_per_second": 1264.037, + "eval_steps_per_second": 39.502, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2513635354106463e-05, + "loss": 3.3749, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2505249406595943e-05, + "loss": 3.3548, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2496879837889154e-05, + "loss": 3.3667, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2488493890378633e-05, + "loss": 3.3844, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2480107942868112e-05, + "loss": 3.3808, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2471721995357592e-05, + "loss": 3.3673, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2463336047847073e-05, + "loss": 3.3703, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2454950100336553e-05, + "loss": 3.3636, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2446564152826032e-05, + "loss": 3.3585, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2438194584119244e-05, + "loss": 3.3759, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2429808636608724e-05, + "loss": 3.3726, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2421422689098202e-05, + "loss": 3.3732, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2413036741587682e-05, + "loss": 3.3729, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2404667172880895e-05, + "loss": 3.3589, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2396281225370375e-05, + "loss": 3.3563, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2387895277859855e-05, + "loss": 3.3546, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2379509330349335e-05, + "loss": 3.3688, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2371123382838815e-05, + "loss": 3.3631, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2362737435328293e-05, + "loss": 3.3641, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2354351487817774e-05, + "loss": 3.3683, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2345965540307254e-05, + "loss": 3.384, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2337595971600465e-05, + "loss": 3.3728, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2329210024089945e-05, + "loss": 3.3648, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2320824076579425e-05, + "loss": 3.3686, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2312438129068905e-05, + "loss": 3.3743, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2304068560362118e-05, + "loss": 3.3638, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2295682612851596e-05, + "loss": 3.3598, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2287296665341076e-05, + "loss": 3.3641, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2278910717830556e-05, + "loss": 3.3594, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2270541149123767e-05, + "loss": 3.3623, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2262155201613246e-05, + "loss": 3.3663, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2253769254102728e-05, + "loss": 3.3613, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2245383306592206e-05, + "loss": 3.3678, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2237013737885417e-05, + "loss": 3.3716, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2228627790374899e-05, + "loss": 3.3606, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2220241842864379e-05, + "loss": 3.3713, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2211855895353857e-05, + "loss": 3.3689, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.220348632664707e-05, + "loss": 3.3552, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.219510037913655e-05, + "loss": 3.3713, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2186730810429762e-05, + "loss": 3.3506, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.217834486291924e-05, + "loss": 3.3633, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.216995891540872e-05, + "loss": 3.3616, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.21615729678982e-05, + "loss": 3.3762, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.215318702038768e-05, + "loss": 3.3674, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.214480107287716e-05, + "loss": 3.3655, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.213641512536664e-05, + "loss": 3.374, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.212802917785612e-05, + "loss": 3.3686, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.211965960914933e-05, + "loss": 3.3686, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.211127366163881e-05, + "loss": 3.3393, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.210288771412829e-05, + "loss": 3.3683, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.209450176661777e-05, + "loss": 3.3711, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2086132197910981e-05, + "loss": 3.3682, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2077746250400463e-05, + "loss": 3.3653, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2069360302889943e-05, + "loss": 3.3553, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2060990734183154e-05, + "loss": 3.356, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2052604786672634e-05, + "loss": 3.3444, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2044218839162114e-05, + "loss": 3.3715, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2035832891651594e-05, + "loss": 3.3495, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2027463322944804e-05, + "loss": 3.3711, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2019077375434284e-05, + "loss": 3.3638, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2010691427923764e-05, + "loss": 3.3509, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2002305480413244e-05, + "loss": 3.3676, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1993935911706455e-05, + "loss": 3.3498, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1985549964195935e-05, + "loss": 3.3553, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1977164016685417e-05, + "loss": 3.3527, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1968778069174895e-05, + "loss": 3.369, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1960408500468106e-05, + "loss": 3.3465, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1952022552957587e-05, + "loss": 3.3624, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1943636605447067e-05, + "loss": 3.3506, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1935250657936546e-05, + "loss": 3.3561, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1926881089229758e-05, + "loss": 3.3675, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1918511520522969e-05, + "loss": 3.3651, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.191012557301245e-05, + "loss": 3.3571, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1901739625501929e-05, + "loss": 3.3647, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1893353677991409e-05, + "loss": 3.3758, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1884967730480889e-05, + "loss": 3.3522, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1876581782970369e-05, + "loss": 3.3704, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1868195835459849e-05, + "loss": 3.3548, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1859809887949329e-05, + "loss": 3.3574, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.1851440319242541e-05, + "loss": 3.3589, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.184305437173202e-05, + "loss": 3.3608, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.18346684242215e-05, + "loss": 3.3713, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1826298855514712e-05, + "loss": 3.3698, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.181791290800419e-05, + "loss": 3.3531, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.180952696049367e-05, + "loss": 3.3419, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1801141012983152e-05, + "loss": 3.3529, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1792755065472632e-05, + "loss": 3.3651, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.178436911796211e-05, + "loss": 3.3575, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.177598317045159e-05, + "loss": 3.3519, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1767597222941071e-05, + "loss": 3.3649, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.175922765423428e-05, + "loss": 3.3611, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1750841706723762e-05, + "loss": 3.3615, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1742455759213242e-05, + "loss": 3.3552, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1734069811702722e-05, + "loss": 3.3661, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1725700242995933e-05, + "loss": 3.357, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1717314295485413e-05, + "loss": 3.3695, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1708928347974893e-05, + "loss": 3.3497, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1700558779268105e-05, + "loss": 3.3539, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1692172831757584e-05, + "loss": 3.3668, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1683786884247064e-05, + "loss": 3.3559, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1675400936736543e-05, + "loss": 3.3657, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1667014989226023e-05, + "loss": 3.3584, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1658629041715503e-05, + "loss": 3.3548, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1650243094204983e-05, + "loss": 3.3565, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1641873525498196e-05, + "loss": 3.3598, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1633487577987674e-05, + "loss": 3.3534, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1625101630477154e-05, + "loss": 3.3545, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1616715682966636e-05, + "loss": 3.3613, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1608329735456114e-05, + "loss": 3.3562, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1599943787945594e-05, + "loss": 3.3517, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1591557840435074e-05, + "loss": 3.3623, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1583171892924554e-05, + "loss": 3.3419, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1574802324217765e-05, + "loss": 3.3653, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1566416376707245e-05, + "loss": 3.3603, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1558030429196726e-05, + "loss": 3.3628, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1549644481686204e-05, + "loss": 3.3655, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1541274912979417e-05, + "loss": 3.3668, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1532905344272628e-05, + "loss": 3.3578, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1524519396762108e-05, + "loss": 3.3586, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1516133449251588e-05, + "loss": 3.3625, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1507747501741068e-05, + "loss": 3.357, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1499361554230548e-05, + "loss": 3.3496, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1490975606720026e-05, + "loss": 3.3659, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1482589659209508e-05, + "loss": 3.3535, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1474203711698987e-05, + "loss": 3.3621, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1465834142992198e-05, + "loss": 3.3535, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1457448195481678e-05, + "loss": 3.3537, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1449062247971158e-05, + "loss": 3.3617, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1440676300460638e-05, + "loss": 3.3543, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1432306731753849e-05, + "loss": 3.3597, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1423920784243329e-05, + "loss": 3.367, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1415534836732809e-05, + "loss": 3.363, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.140714888922229e-05, + "loss": 3.3543, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.13987793205155e-05, + "loss": 3.3641, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.139039337300498e-05, + "loss": 3.3624, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1382007425494461e-05, + "loss": 3.3612, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.137362147798394e-05, + "loss": 3.3525, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1365251909277152e-05, + "loss": 3.3554, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1356865961766632e-05, + "loss": 3.3724, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1348480014256112e-05, + "loss": 3.3743, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.134009406674559e-05, + "loss": 3.359, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1331724498038803e-05, + "loss": 3.3609, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1323338550528283e-05, + "loss": 3.3643, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1314968981821495e-05, + "loss": 3.3593, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1306583034310973e-05, + "loss": 3.3648, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1298197086800453e-05, + "loss": 3.3582, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1289811139289933e-05, + "loss": 3.3563, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1281425191779413e-05, + "loss": 3.3694, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1273039244268893e-05, + "loss": 3.3485, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8693718910217285, + "eval_runtime": 307.2038, + "eval_samples_per_second": 1242.143, + "eval_steps_per_second": 38.818, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1264653296758373e-05, + "loss": 3.3551, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1256267349247853e-05, + "loss": 3.3499, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1247914159344795e-05, + "loss": 3.3559, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1239528211834276e-05, + "loss": 3.3739, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1231142264323756e-05, + "loss": 3.3729, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1222756316813236e-05, + "loss": 3.3584, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1214370369302714e-05, + "loss": 3.3605, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1205984421792196e-05, + "loss": 3.3569, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1197598474281676e-05, + "loss": 3.3541, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1189228905574887e-05, + "loss": 3.3655, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1180842958064367e-05, + "loss": 3.3591, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1172457010553847e-05, + "loss": 3.3618, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1164071063043327e-05, + "loss": 3.3634, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1155685115532807e-05, + "loss": 3.3511, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1147299168022287e-05, + "loss": 3.3469, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1138929599315497e-05, + "loss": 3.3458, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1130543651804977e-05, + "loss": 3.3571, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1122157704294457e-05, + "loss": 3.3558, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1113771756783937e-05, + "loss": 3.3548, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.1105385809273417e-05, + "loss": 3.3574, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1096999861762897e-05, + "loss": 3.3725, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1088613914252377e-05, + "loss": 3.3597, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.1080244345545588e-05, + "loss": 3.3605, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1071858398035068e-05, + "loss": 3.3571, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1063472450524548e-05, + "loss": 3.3664, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1055086503014028e-05, + "loss": 3.3517, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1046700555503508e-05, + "loss": 3.3569, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1038314607992988e-05, + "loss": 3.3542, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1029928660482468e-05, + "loss": 3.3508, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.102155909177568e-05, + "loss": 3.3531, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1013173144265158e-05, + "loss": 3.3556, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1004787196754638e-05, + "loss": 3.3552, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0996401249244118e-05, + "loss": 3.3576, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.098803168053733e-05, + "loss": 3.3615, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0979645733026809e-05, + "loss": 3.3571, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.097125978551629e-05, + "loss": 3.3565, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.096287383800577e-05, + "loss": 3.3621, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.095450426929898e-05, + "loss": 3.3438, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0946118321788461e-05, + "loss": 3.3634, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0937748753081672e-05, + "loss": 3.3373, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0929362805571152e-05, + "loss": 3.3551, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0920976858060632e-05, + "loss": 3.354, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0912590910550112e-05, + "loss": 3.3666, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0904204963039592e-05, + "loss": 3.3538, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0895819015529072e-05, + "loss": 3.3609, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0887433068018552e-05, + "loss": 3.3655, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0879047120508032e-05, + "loss": 3.3635, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0870677551801243e-05, + "loss": 3.3543, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0862291604290723e-05, + "loss": 3.3328, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0853905656780203e-05, + "loss": 3.3578, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0845519709269683e-05, + "loss": 3.3644, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0837150140562895e-05, + "loss": 3.359, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0828764193052373e-05, + "loss": 3.3554, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0820378245541853e-05, + "loss": 3.3452, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0811992298031335e-05, + "loss": 3.3483, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0803622729324544e-05, + "loss": 3.3376, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0795236781814026e-05, + "loss": 3.3614, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0786850834303506e-05, + "loss": 3.3396, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0778481265596716e-05, + "loss": 3.3586, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0770095318086196e-05, + "loss": 3.3558, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0761709370575676e-05, + "loss": 3.3446, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0753323423065156e-05, + "loss": 3.3545, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0744953854358369e-05, + "loss": 3.3431, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0736567906847847e-05, + "loss": 3.3487, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0728181959337327e-05, + "loss": 3.3385, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0719796011826807e-05, + "loss": 3.3614, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0711426443120018e-05, + "loss": 3.3424, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0703040495609498e-05, + "loss": 3.3467, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0694654548098978e-05, + "loss": 3.3412, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.068626860058846e-05, + "loss": 3.3496, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0677899031881668e-05, + "loss": 3.3607, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0669529463174881e-05, + "loss": 3.3529, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.066114351566436e-05, + "loss": 3.3446, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.065275756815384e-05, + "loss": 3.3581, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.064437162064332e-05, + "loss": 3.3649, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.06359856731328e-05, + "loss": 3.3415, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.062759972562228e-05, + "loss": 3.3602, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.061921377811176e-05, + "loss": 3.3487, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.061082783060124e-05, + "loss": 3.3473, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.0602458261894451e-05, + "loss": 3.3468, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0594072314383931e-05, + "loss": 3.3544, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0585686366873411e-05, + "loss": 3.3588, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.0577300419362891e-05, + "loss": 3.3596, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0568930850656104e-05, + "loss": 3.3437, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.0560561281949315e-05, + "loss": 3.3282, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.0552175334438793e-05, + "loss": 3.3479, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.0543789386928274e-05, + "loss": 3.3505, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.0535403439417754e-05, + "loss": 3.3546, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.0527017491907233e-05, + "loss": 3.3397, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.0518631544396714e-05, + "loss": 3.3565, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0510245596886194e-05, + "loss": 3.3513, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.0501859649375672e-05, + "loss": 3.3515, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.0493490080668885e-05, + "loss": 3.3433, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.0485104133158365e-05, + "loss": 3.3572, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0476718185647845e-05, + "loss": 3.3474, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0468332238137323e-05, + "loss": 3.3598, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0459962669430536e-05, + "loss": 3.3472, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0451576721920016e-05, + "loss": 3.341, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0443190774409496e-05, + "loss": 3.3554, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0434821205702706e-05, + "loss": 3.3465, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0426435258192186e-05, + "loss": 3.3529, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0418049310681666e-05, + "loss": 3.3523, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0409663363171146e-05, + "loss": 3.3424, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0401293794464357e-05, + "loss": 3.3475, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.039292422575757e-05, + "loss": 3.3519, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.038453827824705e-05, + "loss": 3.3381, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0376152330736528e-05, + "loss": 3.3505, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.036776638322601e-05, + "loss": 3.3507, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.035938043571549e-05, + "loss": 3.35, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0350994488204968e-05, + "loss": 3.3372, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.034260854069445e-05, + "loss": 3.3538, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.033422259318393e-05, + "loss": 3.3366, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.032585302447714e-05, + "loss": 3.3531, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.031746707696662e-05, + "loss": 3.3526, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.03090811294561e-05, + "loss": 3.3506, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.030069518194558e-05, + "loss": 3.3577, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0292325613238792e-05, + "loss": 3.3563, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0283956044532001e-05, + "loss": 3.3509, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0275570097021481e-05, + "loss": 3.3451, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0267184149510963e-05, + "loss": 3.3552, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0258798202000441e-05, + "loss": 3.3472, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0250412254489921e-05, + "loss": 3.342, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0242026306979401e-05, + "loss": 3.352, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0233640359468883e-05, + "loss": 3.3454, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0225254411958361e-05, + "loss": 3.3539, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0216884843251574e-05, + "loss": 3.3464, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0208498895741054e-05, + "loss": 3.3476, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0200112948230532e-05, + "loss": 3.3499, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0191727000720012e-05, + "loss": 3.3444, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0183357432013224e-05, + "loss": 3.3473, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0174971484502704e-05, + "loss": 3.3622, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0166585536992184e-05, + "loss": 3.3554, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.0158199589481664e-05, + "loss": 3.347, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0149830020774875e-05, + "loss": 3.3533, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.0141444073264355e-05, + "loss": 3.3527, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.0133058125753835e-05, + "loss": 3.3521, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0124672178243315e-05, + "loss": 3.3494, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0116302609536527e-05, + "loss": 3.3441, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.0107916662026006e-05, + "loss": 3.3599, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0099530714515485e-05, + "loss": 3.3606, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0091144767004965e-05, + "loss": 3.3526, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0082775198298178e-05, + "loss": 3.351, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0074389250787656e-05, + "loss": 3.3569, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0066019682080869e-05, + "loss": 3.3477, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0057633734570349e-05, + "loss": 3.3531, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0049247787059829e-05, + "loss": 3.3515, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0040861839549309e-05, + "loss": 3.348, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0032475892038788e-05, + "loss": 3.3609, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0024089944528268e-05, + "loss": 3.3437, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0015703997017747e-05, + "loss": 3.3432, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.870269298553467, + "eval_runtime": 305.9313, + "eval_samples_per_second": 1247.31, + "eval_steps_per_second": 38.979, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0007318049507228e-05, + "loss": 3.3386, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 9.998932101996708e-06, + "loss": 3.3439, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.990562533289919e-06, + "loss": 3.3652, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.982176585779399e-06, + "loss": 3.3635, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.973790638268879e-06, + "loss": 3.3499, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.965404690758359e-06, + "loss": 3.3511, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.957018743247839e-06, + "loss": 3.3474, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.948632795737319e-06, + "loss": 3.3412, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.94026322703053e-06, + "loss": 3.3578, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.93187727952001e-06, + "loss": 3.3512, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.92349133200949e-06, + "loss": 3.354, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.91510538449897e-06, + "loss": 3.3512, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.90671943698845e-06, + "loss": 3.3471, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.89834986828166e-06, + "loss": 3.3377, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.88996392077114e-06, + "loss": 3.3347, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.88157797326062e-06, + "loss": 3.3456, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.873192025750102e-06, + "loss": 3.3466, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.86480607823958e-06, + "loss": 3.3454, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.85642013072906e-06, + "loss": 3.3453, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.84803418321854e-06, + "loss": 3.3665, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.83964823570802e-06, + "loss": 3.3505, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.83127866700123e-06, + "loss": 3.3496, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.822892719490712e-06, + "loss": 3.3483, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.814506771980192e-06, + "loss": 3.3621, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.80612082446967e-06, + "loss": 3.3352, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.797767634566614e-06, + "loss": 3.3499, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.789381687056094e-06, + "loss": 3.3423, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.780995739545574e-06, + "loss": 3.3435, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.772609792035054e-06, + "loss": 3.3436, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.764223844524534e-06, + "loss": 3.3445, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.755837897014014e-06, + "loss": 3.3424, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.747451949503494e-06, + "loss": 3.3509, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.739066001992974e-06, + "loss": 3.3464, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.730696433286184e-06, + "loss": 3.3507, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.722310485775664e-06, + "loss": 3.3458, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.713924538265144e-06, + "loss": 3.3552, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.705538590754624e-06, + "loss": 3.3353, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.697169022047837e-06, + "loss": 3.3554, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.688799453341046e-06, + "loss": 3.3262, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.680413505830528e-06, + "loss": 3.3473, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.672027558320007e-06, + "loss": 3.3428, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.663641610809487e-06, + "loss": 3.3561, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.655255663298966e-06, + "loss": 3.3431, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.646869715788447e-06, + "loss": 3.3532, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.638483768277927e-06, + "loss": 3.352, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.630097820767406e-06, + "loss": 3.3538, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.621728252060618e-06, + "loss": 3.3454, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.613342304550098e-06, + "loss": 3.3243, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.604956357039578e-06, + "loss": 3.3468, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.596570409529056e-06, + "loss": 3.3528, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.588200840822269e-06, + "loss": 3.3482, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.579814893311749e-06, + "loss": 3.3475, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.571428945801229e-06, + "loss": 3.3376, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.563042998290709e-06, + "loss": 3.3402, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.55467342958392e-06, + "loss": 3.3256, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.546287482073401e-06, + "loss": 3.3543, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.53790153456288e-06, + "loss": 3.3284, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.52951558705236e-06, + "loss": 3.3518, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.521146018345572e-06, + "loss": 3.3442, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.512760070835052e-06, + "loss": 3.3328, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.50437412332453e-06, + "loss": 3.3422, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.496004554617742e-06, + "loss": 3.3364, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.487618607107222e-06, + "loss": 3.3391, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.4792326595967e-06, + "loss": 3.33, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.470846712086182e-06, + "loss": 3.3503, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.462477143379393e-06, + "loss": 3.3355, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.454091195868873e-06, + "loss": 3.335, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.445705248358353e-06, + "loss": 3.3328, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.437319300847833e-06, + "loss": 3.34, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.428949732141044e-06, + "loss": 3.3486, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.420580163434256e-06, + "loss": 3.3465, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.412194215923734e-06, + "loss": 3.3356, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.403808268413216e-06, + "loss": 3.351, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.395422320902696e-06, + "loss": 3.3532, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.387036373392174e-06, + "loss": 3.331, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.378650425881654e-06, + "loss": 3.3494, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.370264478371136e-06, + "loss": 3.3406, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.361878530860616e-06, + "loss": 3.3409, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.353508962153825e-06, + "loss": 3.3392, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.345123014643307e-06, + "loss": 3.3432, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.336737067132787e-06, + "loss": 3.3487, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.328351119622265e-06, + "loss": 3.3547, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.319981550915477e-06, + "loss": 3.3318, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.311595603404957e-06, + "loss": 3.3172, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.303209655894437e-06, + "loss": 3.3356, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.294823708383917e-06, + "loss": 3.3433, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.286454139677128e-06, + "loss": 3.3446, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.278068192166608e-06, + "loss": 3.3335, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.26968224465609e-06, + "loss": 3.3456, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.261296297145568e-06, + "loss": 3.3422, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.252926728438779e-06, + "loss": 3.34, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.24454078092826e-06, + "loss": 3.3333, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.236154833417739e-06, + "loss": 3.3486, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.227768885907219e-06, + "loss": 3.3391, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.219399317200431e-06, + "loss": 3.3472, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.211013369689911e-06, + "loss": 3.3421, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.20262742217939e-06, + "loss": 3.3288, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.194257853472602e-06, + "loss": 3.3443, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.185871905962082e-06, + "loss": 3.3414, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.177485958451562e-06, + "loss": 3.3465, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.169100010941042e-06, + "loss": 3.3412, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.160730442234252e-06, + "loss": 3.3359, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.152344494723732e-06, + "loss": 3.3356, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.143974926016945e-06, + "loss": 3.3465, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.135588978506423e-06, + "loss": 3.3285, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.127203030995905e-06, + "loss": 3.3387, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.118817083485385e-06, + "loss": 3.3435, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.110431135974863e-06, + "loss": 3.3401, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.102045188464343e-06, + "loss": 3.3291, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.093659240953825e-06, + "loss": 3.3414, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.085273293443303e-06, + "loss": 3.3331, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.076903724736514e-06, + "loss": 3.3428, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.068517777225995e-06, + "loss": 3.3383, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.060131829715475e-06, + "loss": 3.3383, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.051745882204953e-06, + "loss": 3.3463, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.043376313498166e-06, + "loss": 3.3481, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.034990365987646e-06, + "loss": 3.3447, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.026604418477124e-06, + "loss": 3.3354, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.018218470966606e-06, + "loss": 3.3453, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.009848902259817e-06, + "loss": 3.336, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 9.001462954749297e-06, + "loss": 3.3338, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.993077007238777e-06, + "loss": 3.3465, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.984691059728256e-06, + "loss": 3.3333, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.976321491021467e-06, + "loss": 3.3451, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.967935543510949e-06, + "loss": 3.3328, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.959549596000427e-06, + "loss": 3.3366, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.951163648489907e-06, + "loss": 3.342, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.94279407978312e-06, + "loss": 3.3354, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.934408132272598e-06, + "loss": 3.3335, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.926022184762078e-06, + "loss": 3.3574, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.91763623725156e-06, + "loss": 3.3479, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.90926666854477e-06, + "loss": 3.3393, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.900880721034249e-06, + "loss": 3.3372, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.89249477352373e-06, + "loss": 3.3406, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.88410882601321e-06, + "loss": 3.3438, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.875739257306421e-06, + "loss": 3.3407, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.867353309795901e-06, + "loss": 3.3378, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.858967362285381e-06, + "loss": 3.3514, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.85058141477486e-06, + "loss": 3.3466, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.842211846068072e-06, + "loss": 3.347, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.833825898557552e-06, + "loss": 3.3385, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.825439951047032e-06, + "loss": 3.3453, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.817070382340244e-06, + "loss": 3.3408, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.808684434829722e-06, + "loss": 3.3453, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.800298487319202e-06, + "loss": 3.3437, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.791912539808684e-06, + "loss": 3.3421, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.783526592298162e-06, + "loss": 3.3489, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.775140644787642e-06, + "loss": 3.3318, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.766754697277122e-06, + "loss": 3.3338, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.871385335922241, + "eval_runtime": 306.2668, + "eval_samples_per_second": 1245.943, + "eval_steps_per_second": 38.937, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.758368749766604e-06, + "loss": 3.3289, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.749999181059813e-06, + "loss": 3.3373, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.741613233549294e-06, + "loss": 3.356, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.733227286038774e-06, + "loss": 3.3494, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.724841338528253e-06, + "loss": 3.3459, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.716471769821465e-06, + "loss": 3.3367, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.708085822310945e-06, + "loss": 3.3391, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.699699874800425e-06, + "loss": 3.3302, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.691330306093636e-06, + "loss": 3.3476, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.682944358583116e-06, + "loss": 3.3453, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.674558411072596e-06, + "loss": 3.3413, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.666172463562076e-06, + "loss": 3.3437, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.657786516051556e-06, + "loss": 3.3348, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.649400568541036e-06, + "loss": 3.3324, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.641030999834248e-06, + "loss": 3.3287, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.632645052323726e-06, + "loss": 3.3292, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.624259104813206e-06, + "loss": 3.3383, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.615873157302686e-06, + "loss": 3.3342, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.607487209792168e-06, + "loss": 3.3394, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.599101262281646e-06, + "loss": 3.3571, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.590715314771126e-06, + "loss": 3.3402, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.582329367260606e-06, + "loss": 3.3425, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.573959798553817e-06, + "loss": 3.3384, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.565573851043297e-06, + "loss": 3.3484, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.557187903532777e-06, + "loss": 3.3302, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.548801956022258e-06, + "loss": 3.34, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.540432387315468e-06, + "loss": 3.3323, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.53204643980495e-06, + "loss": 3.3358, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.523660492294429e-06, + "loss": 3.3335, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.515274544783907e-06, + "loss": 3.333, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.50690497607712e-06, + "loss": 3.3361, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.4985190285666e-06, + "loss": 3.3453, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.49013308105608e-06, + "loss": 3.3383, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.48174713354556e-06, + "loss": 3.3402, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.47337756483877e-06, + "loss": 3.3343, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.46499161732825e-06, + "loss": 3.3441, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.45660566981773e-06, + "loss": 3.3283, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.44821972230721e-06, + "loss": 3.3431, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.439866532404154e-06, + "loss": 3.3189, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.431480584893634e-06, + "loss": 3.3428, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.423094637383112e-06, + "loss": 3.3306, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.414708689872592e-06, + "loss": 3.3477, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.406322742362074e-06, + "loss": 3.3315, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.397936794851554e-06, + "loss": 3.3426, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.389550847341032e-06, + "loss": 3.3439, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.381164899830512e-06, + "loss": 3.3443, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.372795331123724e-06, + "loss": 3.3418, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.364409383613202e-06, + "loss": 3.3177, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.356023436102684e-06, + "loss": 3.3315, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.347637488592164e-06, + "loss": 3.3442, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.339267919885375e-06, + "loss": 3.3412, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.330881972374855e-06, + "loss": 3.3353, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.322496024864335e-06, + "loss": 3.3316, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.314110077353815e-06, + "loss": 3.3286, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.305740508647027e-06, + "loss": 3.3247, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.297354561136505e-06, + "loss": 3.3392, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.288968613625985e-06, + "loss": 3.3234, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.280582666115465e-06, + "loss": 3.3382, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.272213097408676e-06, + "loss": 3.3387, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.263827149898156e-06, + "loss": 3.3264, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.255441202387638e-06, + "loss": 3.3298, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.247055254877118e-06, + "loss": 3.3311, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.238685686170327e-06, + "loss": 3.3254, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.230299738659808e-06, + "loss": 3.3218, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.221913791149288e-06, + "loss": 3.3422, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.213527843638767e-06, + "loss": 3.3287, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.20515827493198e-06, + "loss": 3.3255, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.196772327421459e-06, + "loss": 3.3279, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.188386379910939e-06, + "loss": 3.3282, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.18001681120415e-06, + "loss": 3.3388, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.17164724249736e-06, + "loss": 3.3341, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.163261294986842e-06, + "loss": 3.3286, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.154875347476322e-06, + "loss": 3.339, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.1464893999658e-06, + "loss": 3.3415, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.13810345245528e-06, + "loss": 3.3271, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.129717504944762e-06, + "loss": 3.3377, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.12133155743424e-06, + "loss": 3.3334, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.11294560992372e-06, + "loss": 3.3337, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.104576041216933e-06, + "loss": 3.3306, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.096190093706413e-06, + "loss": 3.3322, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.087804146195891e-06, + "loss": 3.3414, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.079418198685373e-06, + "loss": 3.3389, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.071048629978584e-06, + "loss": 3.3288, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.062662682468063e-06, + "loss": 3.3089, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.054276734957543e-06, + "loss": 3.3271, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.045890787447023e-06, + "loss": 3.3352, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.037521218740234e-06, + "loss": 3.3356, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.029135271229714e-06, + "loss": 3.3283, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.020749323719194e-06, + "loss": 3.3319, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.012363376208674e-06, + "loss": 3.3347, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.003993807501887e-06, + "loss": 3.329, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.995607859991365e-06, + "loss": 3.3216, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.987221912480845e-06, + "loss": 3.343, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.978835964970326e-06, + "loss": 3.3238, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.970466396263537e-06, + "loss": 3.3406, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.962080448753015e-06, + "loss": 3.3362, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.953694501242497e-06, + "loss": 3.3178, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.945308553731977e-06, + "loss": 3.3359, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.936938985025188e-06, + "loss": 3.326, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.928553037514668e-06, + "loss": 3.339, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.920167090004148e-06, + "loss": 3.3317, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.911781142493628e-06, + "loss": 3.3272, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.903411573786839e-06, + "loss": 3.3254, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.895025626276318e-06, + "loss": 3.3379, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.886656057569531e-06, + "loss": 3.3196, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.878270110059011e-06, + "loss": 3.3282, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.86988416254849e-06, + "loss": 3.3362, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.861498215037969e-06, + "loss": 3.3287, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.85311226752745e-06, + "loss": 3.3174, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.844726320016929e-06, + "loss": 3.3366, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.836340372506409e-06, + "loss": 3.3232, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.827970803799621e-06, + "loss": 3.3304, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.8195848562891e-06, + "loss": 3.332, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.81119890877858e-06, + "loss": 3.3261, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.802812961268061e-06, + "loss": 3.3458, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.794443392561272e-06, + "loss": 3.3378, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.786073823854483e-06, + "loss": 3.3324, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.777687876343963e-06, + "loss": 3.3275, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.769301928833443e-06, + "loss": 3.3353, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.760915981322923e-06, + "loss": 3.3283, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.752530033812403e-06, + "loss": 3.3222, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.744144086301883e-06, + "loss": 3.3385, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.735758138791363e-06, + "loss": 3.3295, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.727372191280843e-06, + "loss": 3.3314, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.719002622574053e-06, + "loss": 3.3294, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.710616675063533e-06, + "loss": 3.3282, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.702230727553015e-06, + "loss": 3.331, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.693844780042493e-06, + "loss": 3.3275, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.685475211335704e-06, + "loss": 3.3218, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.677089263825186e-06, + "loss": 3.3476, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.668703316314664e-06, + "loss": 3.3409, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.660317368804144e-06, + "loss": 3.3305, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.651947800097356e-06, + "loss": 3.3285, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.643561852586836e-06, + "loss": 3.328, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.635175905076315e-06, + "loss": 3.3366, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.626789957565795e-06, + "loss": 3.3348, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.618420388859007e-06, + "loss": 3.3264, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.610034441348488e-06, + "loss": 3.3447, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.601648493837966e-06, + "loss": 3.333, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.593262546327447e-06, + "loss": 3.3406, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.5848929776206586e-06, + "loss": 3.3277, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.576507030110138e-06, + "loss": 3.3381, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.568121082599618e-06, + "loss": 3.3313, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.559735135089098e-06, + "loss": 3.3327, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.551365566382309e-06, + "loss": 3.3346, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.542979618871788e-06, + "loss": 3.3351, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.534593671361269e-06, + "loss": 3.3389, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.526207723850749e-06, + "loss": 3.3233, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.517821776340228e-06, + "loss": 3.3265, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.871657609939575, + "eval_runtime": 304.844, + "eval_samples_per_second": 1251.758, + "eval_steps_per_second": 39.118, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.509435828829708e-06, + "loss": 3.3177, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.501049881319189e-06, + "loss": 3.3287, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.492663933808669e-06, + "loss": 3.3472, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.484277986298148e-06, + "loss": 3.3412, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.47590841759136e-06, + "loss": 3.3355, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.46752247008084e-06, + "loss": 3.3293, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.459136522570319e-06, + "loss": 3.3314, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.45076695386353e-06, + "loss": 3.3202, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.442397385156742e-06, + "loss": 3.3401, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.434011437646223e-06, + "loss": 3.3344, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.425625490135701e-06, + "loss": 3.332, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.417239542625182e-06, + "loss": 3.333, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.408853595114662e-06, + "loss": 3.3252, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.400467647604143e-06, + "loss": 3.324, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.3920980788973526e-06, + "loss": 3.3237, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.3837121313868325e-06, + "loss": 3.3225, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.375326183876313e-06, + "loss": 3.3274, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.3669402363657924e-06, + "loss": 3.3255, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.358554288855272e-06, + "loss": 3.3279, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.350168341344753e-06, + "loss": 3.3533, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.341782393834233e-06, + "loss": 3.3313, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.333396446323712e-06, + "loss": 3.3303, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.325026877616924e-06, + "loss": 3.3329, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.316640930106404e-06, + "loss": 3.3369, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.308254982595883e-06, + "loss": 3.3202, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.299869035085363e-06, + "loss": 3.3341, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.2914994663785746e-06, + "loss": 3.3231, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.283113518868055e-06, + "loss": 3.3255, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.2747275713575345e-06, + "loss": 3.3213, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.266341623847014e-06, + "loss": 3.3253, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.257972055140226e-06, + "loss": 3.3268, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.249586107629706e-06, + "loss": 3.3332, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.241200160119185e-06, + "loss": 3.3308, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.232814212608666e-06, + "loss": 3.3342, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.2244446439018776e-06, + "loss": 3.3216, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.216058696391356e-06, + "loss": 3.3391, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.207672748880837e-06, + "loss": 3.3164, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.199286801370317e-06, + "loss": 3.3352, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.19093361146726e-06, + "loss": 3.3119, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.182547663956739e-06, + "loss": 3.3321, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.174161716446219e-06, + "loss": 3.3195, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.1657757689357e-06, + "loss": 3.3407, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.157389821425178e-06, + "loss": 3.3251, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.149003873914659e-06, + "loss": 3.3314, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.140617926404139e-06, + "loss": 3.3349, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.13223197889362e-06, + "loss": 3.3382, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.1238624101868295e-06, + "loss": 3.3299, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.1154764626763095e-06, + "loss": 3.3139, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.10709051516579e-06, + "loss": 3.3176, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.098704567655269e-06, + "loss": 3.3375, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.090334998948481e-06, + "loss": 3.3298, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.081949051437961e-06, + "loss": 3.3265, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.073563103927441e-06, + "loss": 3.3223, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.06517715641692e-06, + "loss": 3.3229, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.056807587710132e-06, + "loss": 3.3124, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.0484216401996125e-06, + "loss": 3.3251, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.0400356926890925e-06, + "loss": 3.3168, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.0316497451785716e-06, + "loss": 3.3281, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.023280176471783e-06, + "loss": 3.3311, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.014894228961263e-06, + "loss": 3.3152, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.006508281450742e-06, + "loss": 3.3191, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.998122333940223e-06, + "loss": 3.3225, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.989752765233435e-06, + "loss": 3.3172, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.981366817722915e-06, + "loss": 3.3091, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.972980870212394e-06, + "loss": 3.3316, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.964594922701874e-06, + "loss": 3.3207, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.956225353995085e-06, + "loss": 3.3171, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.947839406484566e-06, + "loss": 3.3183, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.9394534589740444e-06, + "loss": 3.3214, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.931083890267256e-06, + "loss": 3.3272, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.922714321560468e-06, + "loss": 3.327, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.9143283740499485e-06, + "loss": 3.3181, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.905942426539428e-06, + "loss": 3.3314, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.8975564790289076e-06, + "loss": 3.3299, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.889170531518388e-06, + "loss": 3.3185, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.880784584007867e-06, + "loss": 3.3255, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.8723986364973474e-06, + "loss": 3.3247, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.864012688986827e-06, + "loss": 3.3242, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.855643120280039e-06, + "loss": 3.3232, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.847257172769518e-06, + "loss": 3.3233, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.838871225258998e-06, + "loss": 3.3308, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.830485277748479e-06, + "loss": 3.3322, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.822115709041689e-06, + "loss": 3.318, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.81372976153117e-06, + "loss": 3.3095, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.80534381402065e-06, + "loss": 3.315, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.7969578665101296e-06, + "loss": 3.3258, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.78858829780334e-06, + "loss": 3.3287, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.78020235029282e-06, + "loss": 3.3196, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.771816402782301e-06, + "loss": 3.3214, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.763430455271779e-06, + "loss": 3.3285, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.755060886564991e-06, + "loss": 3.3176, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.746674939054472e-06, + "loss": 3.316, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.738288991543952e-06, + "loss": 3.3307, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.729903044033431e-06, + "loss": 3.3219, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.7215334753266425e-06, + "loss": 3.3303, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.713147527816123e-06, + "loss": 3.3258, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.704761580305603e-06, + "loss": 3.3104, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.696375632795082e-06, + "loss": 3.328, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.688006064088294e-06, + "loss": 3.318, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.679620116577774e-06, + "loss": 3.3323, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.671234169067253e-06, + "loss": 3.325, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.662848221556733e-06, + "loss": 3.3182, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.654478652849945e-06, + "loss": 3.3118, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.646109084143156e-06, + "loss": 3.3309, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.637723136632635e-06, + "loss": 3.3124, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.629337189122116e-06, + "loss": 3.3232, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.620951241611596e-06, + "loss": 3.3254, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.612565294101077e-06, + "loss": 3.3181, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.604179346590555e-06, + "loss": 3.3081, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.595809777883767e-06, + "loss": 3.3318, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.587423830373248e-06, + "loss": 3.3149, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.579037882862727e-06, + "loss": 3.3197, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.570651935352207e-06, + "loss": 3.3263, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.562265987841687e-06, + "loss": 3.3181, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.5538800403311675e-06, + "loss": 3.3355, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.545494092820647e-06, + "loss": 3.3275, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.5371081453101266e-06, + "loss": 3.3275, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.528738576603338e-06, + "loss": 3.3155, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.520352629092817e-06, + "loss": 3.3243, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.511966681582297e-06, + "loss": 3.3243, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.503580734071778e-06, + "loss": 3.3108, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.49521116536499e-06, + "loss": 3.3255, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.486825217854468e-06, + "loss": 3.3242, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.478439270343949e-06, + "loss": 3.3215, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.470053322833429e-06, + "loss": 3.3233, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.4616837541266395e-06, + "loss": 3.3216, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.4532978066161195e-06, + "loss": 3.3153, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.4449118591056e-06, + "loss": 3.3223, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.43652591159508e-06, + "loss": 3.3142, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.42815634288829e-06, + "loss": 3.3358, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.419770395377771e-06, + "loss": 3.3361, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.411384447867251e-06, + "loss": 3.3196, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.40299850035673e-06, + "loss": 3.3179, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.394628931649942e-06, + "loss": 3.3206, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.386242984139422e-06, + "loss": 3.327, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.3778570366289024e-06, + "loss": 3.3253, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.3694710891183815e-06, + "loss": 3.3185, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.361101520411593e-06, + "loss": 3.3317, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.352715572901073e-06, + "loss": 3.3253, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.344329625390553e-06, + "loss": 3.3341, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.335960056683764e-06, + "loss": 3.3182, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.327574109173244e-06, + "loss": 3.3319, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.319188161662725e-06, + "loss": 3.3235, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.310802214152203e-06, + "loss": 3.3176, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.3024326454454145e-06, + "loss": 3.3273, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.294046697934895e-06, + "loss": 3.3272, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.285660750424375e-06, + "loss": 3.3275, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.277274802913854e-06, + "loss": 3.3111, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.268888855403335e-06, + "loss": 3.3135, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.8721344470977783, + "eval_runtime": 304.4148, + "eval_samples_per_second": 1253.523, + "eval_steps_per_second": 39.174, + "step": 2671200 + }, + { + "epoch": 1.0, + "learning_rate": 6.260502907892815e-06, + "loss": 3.3183, + "step": 2671616 + }, + { + "epoch": 1.0, + "learning_rate": 6.252116960382294e-06, + "loss": 3.3194, + "step": 2672128 + }, + { + "epoch": 1.0, + "learning_rate": 6.243731012871774e-06, + "loss": 3.3342, + "step": 2672640 + }, + { + "epoch": 1.0, + "learning_rate": 6.235361444164986e-06, + "loss": 3.3342, + "step": 2673152 + }, + { + "epoch": 1.0, + "learning_rate": 6.226975496654466e-06, + "loss": 3.3301, + "step": 2673664 + }, + { + "epoch": 1.0, + "learning_rate": 6.218589549143946e-06, + "loss": 3.3146, + "step": 2674176 + }, + { + "epoch": 1.0, + "learning_rate": 6.2102199804371566e-06, + "loss": 3.3251, + "step": 2674688 + }, + { + "epoch": 1.0, + "learning_rate": 6.201834032926637e-06, + "loss": 3.3085, + "step": 2675200 + }, + { + "epoch": 1.0, + "learning_rate": 6.193464464219848e-06, + "loss": 3.3317, + "step": 2675712 + }, + { + "epoch": 1.0, + "learning_rate": 6.185078516709328e-06, + "loss": 3.3281, + "step": 2676224 + }, + { + "epoch": 1.0, + "learning_rate": 6.176692569198808e-06, + "loss": 3.3191, + "step": 2676736 + }, + { + "epoch": 1.0, + "learning_rate": 6.168306621688288e-06, + "loss": 3.3291, + "step": 2677248 + }, + { + "epoch": 1.0, + "learning_rate": 6.159920674177768e-06, + "loss": 3.3161, + "step": 2677760 + }, + { + "epoch": 1.0, + "learning_rate": 6.151534726667248e-06, + "loss": 3.3174, + "step": 2678272 + }, + { + "epoch": 1.0, + "learning_rate": 6.14316515796046e-06, + "loss": 3.3104, + "step": 2678784 + }, + { + "epoch": 1.0, + "learning_rate": 6.134779210449939e-06, + "loss": 3.3187, + "step": 2679296 + }, + { + "epoch": 1.0, + "learning_rate": 6.1263932629394195e-06, + "loss": 3.317, + "step": 2679808 + }, + { + "epoch": 1.0, + "learning_rate": 6.118007315428899e-06, + "loss": 3.3158, + "step": 2680320 + }, + { + "epoch": 1.0, + "learning_rate": 6.1096213679183786e-06, + "loss": 3.3198, + "step": 2680832 + }, + { + "epoch": 1.0, + "learning_rate": 6.1012354204078585e-06, + "loss": 3.3416, + "step": 2681344 + }, + { + "epoch": 1.0, + "learning_rate": 6.0928494728973385e-06, + "loss": 3.3223, + "step": 2681856 + }, + { + "epoch": 1.0, + "learning_rate": 6.0844635253868184e-06, + "loss": 3.3232, + "step": 2682368 + }, + { + "epoch": 1.0, + "learning_rate": 6.07609395668003e-06, + "loss": 3.3224, + "step": 2682880 + }, + { + "epoch": 1.0, + "learning_rate": 6.06770800916951e-06, + "loss": 3.3287, + "step": 2683392 + }, + { + "epoch": 1.0, + "learning_rate": 6.05932206165899e-06, + "loss": 3.316, + "step": 2683904 + }, + { + "epoch": 1.0, + "learning_rate": 6.050936114148469e-06, + "loss": 3.3225, + "step": 2684416 + }, + { + "epoch": 1.0, + "learning_rate": 6.042566545441681e-06, + "loss": 3.3143, + "step": 2684928 + }, + { + "epoch": 1.0, + "learning_rate": 6.034180597931161e-06, + "loss": 3.3138, + "step": 2685440 + }, + { + "epoch": 1.0, + "learning_rate": 6.025794650420641e-06, + "loss": 3.3121, + "step": 2685952 + }, + { + "epoch": 1.01, + "learning_rate": 6.017408702910121e-06, + "loss": 3.3214, + "step": 2686464 + }, + { + "epoch": 1.01, + "learning_rate": 6.009039134203332e-06, + "loss": 3.3159, + "step": 2686976 + }, + { + "epoch": 1.01, + "learning_rate": 6.000653186692811e-06, + "loss": 3.3255, + "step": 2687488 + }, + { + "epoch": 1.01, + "learning_rate": 5.992267239182292e-06, + "loss": 3.3219, + "step": 2688000 + }, + { + "epoch": 1.01, + "learning_rate": 5.983881291671771e-06, + "loss": 3.3218, + "step": 2688512 + }, + { + "epoch": 1.01, + "learning_rate": 5.975511722964984e-06, + "loss": 3.3128, + "step": 2689024 + }, + { + "epoch": 1.01, + "learning_rate": 5.967125775454463e-06, + "loss": 3.3266, + "step": 2689536 + }, + { + "epoch": 1.01, + "learning_rate": 5.958739827943943e-06, + "loss": 3.3137, + "step": 2690048 + }, + { + "epoch": 1.01, + "learning_rate": 5.950353880433423e-06, + "loss": 3.3253, + "step": 2690560 + }, + { + "epoch": 1.01, + "learning_rate": 5.942000690530366e-06, + "loss": 3.3015, + "step": 2691072 + }, + { + "epoch": 1.01, + "learning_rate": 5.933614743019845e-06, + "loss": 3.319, + "step": 2691584 + }, + { + "epoch": 1.01, + "learning_rate": 5.925228795509325e-06, + "loss": 3.3172, + "step": 2692096 + }, + { + "epoch": 1.01, + "learning_rate": 5.916842847998805e-06, + "loss": 3.3321, + "step": 2692608 + }, + { + "epoch": 1.01, + "learning_rate": 5.908456900488285e-06, + "loss": 3.3173, + "step": 2693120 + }, + { + "epoch": 1.01, + "learning_rate": 5.900070952977765e-06, + "loss": 3.3209, + "step": 2693632 + }, + { + "epoch": 1.01, + "learning_rate": 5.891685005467245e-06, + "loss": 3.3243, + "step": 2694144 + }, + { + "epoch": 1.01, + "learning_rate": 5.883299057956725e-06, + "loss": 3.3294, + "step": 2694656 + }, + { + "epoch": 1.01, + "learning_rate": 5.8749294892499366e-06, + "loss": 3.3194, + "step": 2695168 + }, + { + "epoch": 1.01, + "learning_rate": 5.866543541739416e-06, + "loss": 3.3101, + "step": 2695680 + }, + { + "epoch": 1.01, + "learning_rate": 5.8581575942288965e-06, + "loss": 3.3048, + "step": 2696192 + }, + { + "epoch": 1.01, + "learning_rate": 5.8497716467183756e-06, + "loss": 3.3278, + "step": 2696704 + }, + { + "epoch": 1.01, + "learning_rate": 5.841402078011587e-06, + "loss": 3.3242, + "step": 2697216 + }, + { + "epoch": 1.01, + "learning_rate": 5.833016130501067e-06, + "loss": 3.3185, + "step": 2697728 + }, + { + "epoch": 1.01, + "learning_rate": 5.824630182990547e-06, + "loss": 3.309, + "step": 2698240 + }, + { + "epoch": 1.01, + "learning_rate": 5.816244235480027e-06, + "loss": 3.3148, + "step": 2698752 + }, + { + "epoch": 1.01, + "learning_rate": 5.807874666773239e-06, + "loss": 3.3025, + "step": 2699264 + }, + { + "epoch": 1.01, + "learning_rate": 5.799488719262719e-06, + "loss": 3.319, + "step": 2699776 + }, + { + "epoch": 1.01, + "learning_rate": 5.791102771752198e-06, + "loss": 3.3064, + "step": 2700288 + }, + { + "epoch": 1.01, + "learning_rate": 5.782716824241679e-06, + "loss": 3.319, + "step": 2700800 + }, + { + "epoch": 1.01, + "learning_rate": 5.774347255534889e-06, + "loss": 3.3223, + "step": 2701312 + }, + { + "epoch": 1.01, + "learning_rate": 5.765961308024369e-06, + "loss": 3.3131, + "step": 2701824 + }, + { + "epoch": 1.01, + "learning_rate": 5.757575360513849e-06, + "loss": 3.3068, + "step": 2702336 + }, + { + "epoch": 1.01, + "learning_rate": 5.749189413003329e-06, + "loss": 3.3148, + "step": 2702848 + }, + { + "epoch": 1.01, + "learning_rate": 5.74081984429654e-06, + "loss": 3.3064, + "step": 2703360 + }, + { + "epoch": 1.01, + "learning_rate": 5.732433896786021e-06, + "loss": 3.3054, + "step": 2703872 + }, + { + "epoch": 1.01, + "learning_rate": 5.7240479492755e-06, + "loss": 3.3196, + "step": 2704384 + }, + { + "epoch": 1.01, + "learning_rate": 5.71566200176498e-06, + "loss": 3.3127, + "step": 2704896 + }, + { + "epoch": 1.01, + "learning_rate": 5.7072924330581915e-06, + "loss": 3.3073, + "step": 2705408 + }, + { + "epoch": 1.01, + "learning_rate": 5.6989064855476715e-06, + "loss": 3.3069, + "step": 2705920 + }, + { + "epoch": 1.01, + "learning_rate": 5.6905205380371514e-06, + "loss": 3.3137, + "step": 2706432 + }, + { + "epoch": 1.01, + "learning_rate": 5.682134590526631e-06, + "loss": 3.3137, + "step": 2706944 + }, + { + "epoch": 1.01, + "learning_rate": 5.673781400623574e-06, + "loss": 3.3179, + "step": 2707456 + }, + { + "epoch": 1.01, + "learning_rate": 5.665395453113054e-06, + "loss": 3.3119, + "step": 2707968 + }, + { + "epoch": 1.01, + "learning_rate": 5.657009505602534e-06, + "loss": 3.3227, + "step": 2708480 + }, + { + "epoch": 1.01, + "learning_rate": 5.648623558092014e-06, + "loss": 3.3237, + "step": 2708992 + }, + { + "epoch": 1.01, + "learning_rate": 5.640237610581494e-06, + "loss": 3.3121, + "step": 2709504 + }, + { + "epoch": 1.01, + "learning_rate": 5.631851663070974e-06, + "loss": 3.3158, + "step": 2710016 + }, + { + "epoch": 1.01, + "learning_rate": 5.623465715560454e-06, + "loss": 3.3173, + "step": 2710528 + }, + { + "epoch": 1.01, + "learning_rate": 5.6150797680499336e-06, + "loss": 3.3176, + "step": 2711040 + }, + { + "epoch": 1.01, + "learning_rate": 5.606710199343144e-06, + "loss": 3.3143, + "step": 2711552 + }, + { + "epoch": 1.01, + "learning_rate": 5.598324251832625e-06, + "loss": 3.3147, + "step": 2712064 + }, + { + "epoch": 1.01, + "learning_rate": 5.589938304322104e-06, + "loss": 3.3197, + "step": 2712576 + }, + { + "epoch": 1.01, + "learning_rate": 5.581552356811584e-06, + "loss": 3.324, + "step": 2713088 + }, + { + "epoch": 1.01, + "learning_rate": 5.573182788104796e-06, + "loss": 3.3128, + "step": 2713600 + }, + { + "epoch": 1.01, + "learning_rate": 5.564796840594275e-06, + "loss": 3.3028, + "step": 2714112 + }, + { + "epoch": 1.01, + "learning_rate": 5.556410893083756e-06, + "loss": 3.2996, + "step": 2714624 + }, + { + "epoch": 1.01, + "learning_rate": 5.548024945573235e-06, + "loss": 3.314, + "step": 2715136 + }, + { + "epoch": 1.01, + "learning_rate": 5.5396553768664465e-06, + "loss": 3.323, + "step": 2715648 + }, + { + "epoch": 1.01, + "learning_rate": 5.5312694293559265e-06, + "loss": 3.3147, + "step": 2716160 + }, + { + "epoch": 1.01, + "learning_rate": 5.522883481845407e-06, + "loss": 3.3061, + "step": 2716672 + }, + { + "epoch": 1.02, + "learning_rate": 5.514497534334886e-06, + "loss": 3.3219, + "step": 2717184 + }, + { + "epoch": 1.02, + "learning_rate": 5.506127965628098e-06, + "loss": 3.3124, + "step": 2717696 + }, + { + "epoch": 1.02, + "learning_rate": 5.497742018117578e-06, + "loss": 3.3093, + "step": 2718208 + }, + { + "epoch": 1.02, + "learning_rate": 5.489356070607057e-06, + "loss": 3.317, + "step": 2718720 + }, + { + "epoch": 1.02, + "learning_rate": 5.480970123096538e-06, + "loss": 3.3193, + "step": 2719232 + }, + { + "epoch": 1.02, + "learning_rate": 5.472600554389749e-06, + "loss": 3.3249, + "step": 2719744 + }, + { + "epoch": 1.02, + "learning_rate": 5.464214606879229e-06, + "loss": 3.3112, + "step": 2720256 + }, + { + "epoch": 1.02, + "learning_rate": 5.455828659368709e-06, + "loss": 3.3013, + "step": 2720768 + }, + { + "epoch": 1.02, + "learning_rate": 5.4474427118581885e-06, + "loss": 3.3198, + "step": 2721280 + }, + { + "epoch": 1.02, + "learning_rate": 5.4390731431514e-06, + "loss": 3.3088, + "step": 2721792 + }, + { + "epoch": 1.02, + "learning_rate": 5.43068719564088e-06, + "loss": 3.3215, + "step": 2722304 + }, + { + "epoch": 1.02, + "learning_rate": 5.42230124813036e-06, + "loss": 3.3184, + "step": 2722816 + }, + { + "epoch": 1.02, + "learning_rate": 5.413915300619839e-06, + "loss": 3.3089, + "step": 2723328 + }, + { + "epoch": 1.02, + "learning_rate": 5.405545731913051e-06, + "loss": 3.3059, + "step": 2723840 + }, + { + "epoch": 1.02, + "learning_rate": 5.397159784402531e-06, + "loss": 3.3201, + "step": 2724352 + }, + { + "epoch": 1.02, + "learning_rate": 5.388773836892011e-06, + "loss": 3.3048, + "step": 2724864 + }, + { + "epoch": 1.02, + "learning_rate": 5.380387889381491e-06, + "loss": 3.316, + "step": 2725376 + }, + { + "epoch": 1.02, + "learning_rate": 5.372018320674702e-06, + "loss": 3.3099, + "step": 2725888 + }, + { + "epoch": 1.02, + "learning_rate": 5.363632373164182e-06, + "loss": 3.3161, + "step": 2726400 + }, + { + "epoch": 1.02, + "learning_rate": 5.355246425653662e-06, + "loss": 3.2983, + "step": 2726912 + }, + { + "epoch": 1.02, + "learning_rate": 5.346876856946873e-06, + "loss": 3.3215, + "step": 2727424 + }, + { + "epoch": 1.02, + "learning_rate": 5.338490909436354e-06, + "loss": 3.3054, + "step": 2727936 + }, + { + "epoch": 1.02, + "learning_rate": 5.330104961925833e-06, + "loss": 3.3101, + "step": 2728448 + }, + { + "epoch": 1.02, + "learning_rate": 5.321719014415313e-06, + "loss": 3.3181, + "step": 2728960 + }, + { + "epoch": 1.02, + "learning_rate": 5.3133494457085246e-06, + "loss": 3.3081, + "step": 2729472 + }, + { + "epoch": 1.02, + "learning_rate": 5.304963498198004e-06, + "loss": 3.3263, + "step": 2729984 + }, + { + "epoch": 1.02, + "learning_rate": 5.2965775506874845e-06, + "loss": 3.3224, + "step": 2730496 + }, + { + "epoch": 1.02, + "learning_rate": 5.2881916031769636e-06, + "loss": 3.3153, + "step": 2731008 + }, + { + "epoch": 1.02, + "learning_rate": 5.279822034470175e-06, + "loss": 3.3094, + "step": 2731520 + }, + { + "epoch": 1.02, + "learning_rate": 5.271436086959655e-06, + "loss": 3.3189, + "step": 2732032 + }, + { + "epoch": 1.02, + "learning_rate": 5.263050139449135e-06, + "loss": 3.3111, + "step": 2732544 + }, + { + "epoch": 1.02, + "learning_rate": 5.254664191938615e-06, + "loss": 3.3035, + "step": 2733056 + }, + { + "epoch": 1.02, + "learning_rate": 5.246294623231827e-06, + "loss": 3.3161, + "step": 2733568 + }, + { + "epoch": 1.02, + "learning_rate": 5.237908675721307e-06, + "loss": 3.3125, + "step": 2734080 + }, + { + "epoch": 1.02, + "learning_rate": 5.229522728210786e-06, + "loss": 3.3144, + "step": 2734592 + }, + { + "epoch": 1.02, + "learning_rate": 5.221136780700267e-06, + "loss": 3.3133, + "step": 2735104 + }, + { + "epoch": 1.02, + "learning_rate": 5.212767211993477e-06, + "loss": 3.3138, + "step": 2735616 + }, + { + "epoch": 1.02, + "learning_rate": 5.204381264482957e-06, + "loss": 3.3078, + "step": 2736128 + }, + { + "epoch": 1.02, + "learning_rate": 5.195995316972437e-06, + "loss": 3.3139, + "step": 2736640 + }, + { + "epoch": 1.02, + "learning_rate": 5.187609369461917e-06, + "loss": 3.3075, + "step": 2737152 + }, + { + "epoch": 1.02, + "learning_rate": 5.179239800755129e-06, + "loss": 3.3234, + "step": 2737664 + }, + { + "epoch": 1.02, + "learning_rate": 5.170853853244609e-06, + "loss": 3.3243, + "step": 2738176 + }, + { + "epoch": 1.02, + "learning_rate": 5.162467905734089e-06, + "loss": 3.3168, + "step": 2738688 + }, + { + "epoch": 1.02, + "learning_rate": 5.154081958223568e-06, + "loss": 3.3092, + "step": 2739200 + }, + { + "epoch": 1.02, + "learning_rate": 5.1457123895167795e-06, + "loss": 3.312, + "step": 2739712 + }, + { + "epoch": 1.02, + "learning_rate": 5.1373264420062595e-06, + "loss": 3.3175, + "step": 2740224 + }, + { + "epoch": 1.02, + "learning_rate": 5.1289404944957394e-06, + "loss": 3.3195, + "step": 2740736 + }, + { + "epoch": 1.02, + "learning_rate": 5.120554546985219e-06, + "loss": 3.3092, + "step": 2741248 + }, + { + "epoch": 1.02, + "learning_rate": 5.112184978278431e-06, + "loss": 3.3178, + "step": 2741760 + }, + { + "epoch": 1.02, + "learning_rate": 5.10379903076791e-06, + "loss": 3.3139, + "step": 2742272 + }, + { + "epoch": 1.02, + "learning_rate": 5.095413083257391e-06, + "loss": 3.3257, + "step": 2742784 + }, + { + "epoch": 1.02, + "learning_rate": 5.08702713574687e-06, + "loss": 3.3123, + "step": 2743296 + }, + { + "epoch": 1.02, + "learning_rate": 5.078657567040082e-06, + "loss": 3.3218, + "step": 2743808 + }, + { + "epoch": 1.02, + "learning_rate": 5.070271619529562e-06, + "loss": 3.3162, + "step": 2744320 + }, + { + "epoch": 1.02, + "learning_rate": 5.061902050822773e-06, + "loss": 3.3128, + "step": 2744832 + }, + { + "epoch": 1.02, + "learning_rate": 5.053516103312253e-06, + "loss": 3.3157, + "step": 2745344 + }, + { + "epoch": 1.02, + "learning_rate": 5.045130155801732e-06, + "loss": 3.324, + "step": 2745856 + }, + { + "epoch": 1.02, + "learning_rate": 5.036744208291213e-06, + "loss": 3.3154, + "step": 2746368 + }, + { + "epoch": 1.02, + "learning_rate": 5.028358260780692e-06, + "loss": 3.3003, + "step": 2746880 + }, + { + "epoch": 1.02, + "learning_rate": 5.019972313270173e-06, + "loss": 3.3111, + "step": 2747392 + }, + { + "epoch": 1.03, + "eval_loss": 3.8720781803131104, + "eval_runtime": 304.7256, + "eval_samples_per_second": 1252.245, + "eval_steps_per_second": 39.134, + "step": 2747520 + }, + { + "epoch": 0.0, + "learning_rate": 5.011586365759652e-06, + "loss": 3.3013, + "step": 2747904 + }, + { + "epoch": 0.0, + "learning_rate": 5.003200418249132e-06, + "loss": 3.3103, + "step": 2748416 + }, + { + "epoch": 0.0, + "learning_rate": 4.994814470738612e-06, + "loss": 3.3222, + "step": 2748928 + }, + { + "epoch": 0.0, + "learning_rate": 4.986428523228092e-06, + "loss": 3.3245, + "step": 2749440 + }, + { + "epoch": 0.0, + "learning_rate": 4.978058954521304e-06, + "loss": 3.3233, + "step": 2749952 + }, + { + "epoch": 0.0, + "learning_rate": 4.969673007010784e-06, + "loss": 3.3146, + "step": 2750464 + }, + { + "epoch": 0.0, + "learning_rate": 4.961287059500264e-06, + "loss": 3.3145, + "step": 2750976 + }, + { + "epoch": 0.0, + "learning_rate": 4.9529011119897435e-06, + "loss": 3.2975, + "step": 2751488 + }, + { + "epoch": 0.0, + "learning_rate": 4.944547922086686e-06, + "loss": 3.3229, + "step": 2752000 + }, + { + "epoch": 0.0, + "learning_rate": 4.936161974576166e-06, + "loss": 3.3194, + "step": 2752512 + }, + { + "epoch": 0.0, + "learning_rate": 4.927776027065646e-06, + "loss": 3.311, + "step": 2753024 + }, + { + "epoch": 0.0, + "learning_rate": 4.919390079555126e-06, + "loss": 3.3194, + "step": 2753536 + }, + { + "epoch": 0.0, + "learning_rate": 4.911004132044605e-06, + "loss": 3.3072, + "step": 2754048 + }, + { + "epoch": 0.0, + "learning_rate": 4.902618184534086e-06, + "loss": 3.3106, + "step": 2754560 + }, + { + "epoch": 0.0, + "learning_rate": 4.894248615827297e-06, + "loss": 3.3032, + "step": 2755072 + }, + { + "epoch": 0.0, + "learning_rate": 4.885862668316777e-06, + "loss": 3.3056, + "step": 2755584 + }, + { + "epoch": 0.0, + "learning_rate": 4.8774767208062565e-06, + "loss": 3.3101, + "step": 2756096 + }, + { + "epoch": 0.0, + "learning_rate": 4.8690907732957365e-06, + "loss": 3.3077, + "step": 2756608 + }, + { + "epoch": 0.0, + "learning_rate": 4.860704825785216e-06, + "loss": 3.3132, + "step": 2757120 + }, + { + "epoch": 0.0, + "learning_rate": 4.852318878274696e-06, + "loss": 3.3304, + "step": 2757632 + }, + { + "epoch": 0.0, + "learning_rate": 4.843932930764176e-06, + "loss": 3.3149, + "step": 2758144 + }, + { + "epoch": 0.0, + "learning_rate": 4.835546983253656e-06, + "loss": 3.3169, + "step": 2758656 + }, + { + "epoch": 0.0, + "learning_rate": 4.827177414546868e-06, + "loss": 3.3131, + "step": 2759168 + }, + { + "epoch": 0.0, + "learning_rate": 4.818791467036347e-06, + "loss": 3.3183, + "step": 2759680 + }, + { + "epoch": 0.0, + "learning_rate": 4.810405519525827e-06, + "loss": 3.3083, + "step": 2760192 + }, + { + "epoch": 0.0, + "learning_rate": 4.802019572015307e-06, + "loss": 3.3163, + "step": 2760704 + }, + { + "epoch": 0.0, + "learning_rate": 4.7936500033085186e-06, + "loss": 3.3105, + "step": 2761216 + }, + { + "epoch": 0.0, + "learning_rate": 4.7852640557979985e-06, + "loss": 3.3046, + "step": 2761728 + }, + { + "epoch": 0.0, + "learning_rate": 4.7768781082874785e-06, + "loss": 3.3022, + "step": 2762240 + }, + { + "epoch": 0.0, + "learning_rate": 4.7684921607769584e-06, + "loss": 3.3133, + "step": 2762752 + }, + { + "epoch": 0.01, + "learning_rate": 4.760122592070169e-06, + "loss": 3.3089, + "step": 2763264 + }, + { + "epoch": 0.01, + "learning_rate": 4.75173664455965e-06, + "loss": 3.3166, + "step": 2763776 + }, + { + "epoch": 0.01, + "learning_rate": 4.743350697049129e-06, + "loss": 3.3149, + "step": 2764288 + }, + { + "epoch": 0.01, + "learning_rate": 4.734964749538609e-06, + "loss": 3.3133, + "step": 2764800 + }, + { + "epoch": 0.01, + "learning_rate": 4.726595180831821e-06, + "loss": 3.3041, + "step": 2765312 + }, + { + "epoch": 0.01, + "learning_rate": 4.718209233321301e-06, + "loss": 3.3194, + "step": 2765824 + }, + { + "epoch": 0.01, + "learning_rate": 4.709823285810781e-06, + "loss": 3.3072, + "step": 2766336 + }, + { + "epoch": 0.01, + "learning_rate": 4.701437338300261e-06, + "loss": 3.3154, + "step": 2766848 + }, + { + "epoch": 0.01, + "learning_rate": 4.693084148397203e-06, + "loss": 3.2952, + "step": 2767360 + }, + { + "epoch": 0.01, + "learning_rate": 4.684698200886683e-06, + "loss": 3.3089, + "step": 2767872 + }, + { + "epoch": 0.01, + "learning_rate": 4.676312253376163e-06, + "loss": 3.3095, + "step": 2768384 + }, + { + "epoch": 0.01, + "learning_rate": 4.667926305865643e-06, + "loss": 3.3243, + "step": 2768896 + }, + { + "epoch": 0.01, + "learning_rate": 4.659540358355123e-06, + "loss": 3.309, + "step": 2769408 + }, + { + "epoch": 0.01, + "learning_rate": 4.651154410844603e-06, + "loss": 3.3142, + "step": 2769920 + }, + { + "epoch": 0.01, + "learning_rate": 4.642768463334082e-06, + "loss": 3.3195, + "step": 2770432 + }, + { + "epoch": 0.01, + "learning_rate": 4.634382515823563e-06, + "loss": 3.3196, + "step": 2770944 + }, + { + "epoch": 0.01, + "learning_rate": 4.6260129471167736e-06, + "loss": 3.3117, + "step": 2771456 + }, + { + "epoch": 0.01, + "learning_rate": 4.6176269996062535e-06, + "loss": 3.2993, + "step": 2771968 + }, + { + "epoch": 0.01, + "learning_rate": 4.6092410520957335e-06, + "loss": 3.2937, + "step": 2772480 + }, + { + "epoch": 0.01, + "learning_rate": 4.600855104585214e-06, + "loss": 3.3241, + "step": 2772992 + }, + { + "epoch": 0.01, + "learning_rate": 4.592485535878425e-06, + "loss": 3.3136, + "step": 2773504 + }, + { + "epoch": 0.01, + "learning_rate": 4.584099588367905e-06, + "loss": 3.3106, + "step": 2774016 + }, + { + "epoch": 0.01, + "learning_rate": 4.575713640857385e-06, + "loss": 3.3055, + "step": 2774528 + }, + { + "epoch": 0.01, + "learning_rate": 4.567327693346864e-06, + "loss": 3.3067, + "step": 2775040 + }, + { + "epoch": 0.01, + "learning_rate": 4.558958124640076e-06, + "loss": 3.2927, + "step": 2775552 + }, + { + "epoch": 0.01, + "learning_rate": 4.550572177129556e-06, + "loss": 3.3057, + "step": 2776064 + }, + { + "epoch": 0.01, + "learning_rate": 4.542186229619036e-06, + "loss": 3.3008, + "step": 2776576 + }, + { + "epoch": 0.01, + "learning_rate": 4.533800282108516e-06, + "loss": 3.3071, + "step": 2777088 + }, + { + "epoch": 0.01, + "learning_rate": 4.525430713401727e-06, + "loss": 3.3177, + "step": 2777600 + }, + { + "epoch": 0.01, + "learning_rate": 4.517044765891207e-06, + "loss": 3.3032, + "step": 2778112 + }, + { + "epoch": 0.01, + "learning_rate": 4.508658818380687e-06, + "loss": 3.2968, + "step": 2778624 + }, + { + "epoch": 0.01, + "learning_rate": 4.500272870870167e-06, + "loss": 3.3134, + "step": 2779136 + }, + { + "epoch": 0.01, + "learning_rate": 4.491903302163379e-06, + "loss": 3.2958, + "step": 2779648 + }, + { + "epoch": 0.01, + "learning_rate": 4.483517354652858e-06, + "loss": 3.3004, + "step": 2780160 + }, + { + "epoch": 0.01, + "learning_rate": 4.475131407142338e-06, + "loss": 3.3101, + "step": 2780672 + }, + { + "epoch": 0.01, + "learning_rate": 4.466745459631818e-06, + "loss": 3.307, + "step": 2781184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4583758909250285e-06, + "loss": 3.2997, + "step": 2781696 + }, + { + "epoch": 0.01, + "learning_rate": 4.449989943414509e-06, + "loss": 3.3007, + "step": 2782208 + }, + { + "epoch": 0.01, + "learning_rate": 4.441603995903989e-06, + "loss": 3.3007, + "step": 2782720 + }, + { + "epoch": 0.01, + "learning_rate": 4.433218048393469e-06, + "loss": 3.3074, + "step": 2783232 + }, + { + "epoch": 0.01, + "learning_rate": 4.42484847968668e-06, + "loss": 3.3086, + "step": 2783744 + }, + { + "epoch": 0.01, + "learning_rate": 4.416462532176161e-06, + "loss": 3.3039, + "step": 2784256 + }, + { + "epoch": 0.01, + "learning_rate": 4.40807658466564e-06, + "loss": 3.3162, + "step": 2784768 + }, + { + "epoch": 0.01, + "learning_rate": 4.39969063715512e-06, + "loss": 3.3137, + "step": 2785280 + }, + { + "epoch": 0.01, + "learning_rate": 4.3913210684483315e-06, + "loss": 3.3069, + "step": 2785792 + }, + { + "epoch": 0.01, + "learning_rate": 4.382935120937811e-06, + "loss": 3.3005, + "step": 2786304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3745491734272915e-06, + "loss": 3.316, + "step": 2786816 + }, + { + "epoch": 0.01, + "learning_rate": 4.3661632259167706e-06, + "loss": 3.3086, + "step": 2787328 + }, + { + "epoch": 0.01, + "learning_rate": 4.357793657209982e-06, + "loss": 3.3029, + "step": 2787840 + }, + { + "epoch": 0.01, + "learning_rate": 4.349407709699462e-06, + "loss": 3.3091, + "step": 2788352 + }, + { + "epoch": 0.01, + "learning_rate": 4.341021762188942e-06, + "loss": 3.3115, + "step": 2788864 + }, + { + "epoch": 0.01, + "learning_rate": 4.332652193482154e-06, + "loss": 3.3185, + "step": 2789376 + }, + { + "epoch": 0.01, + "learning_rate": 4.324266245971634e-06, + "loss": 3.3012, + "step": 2789888 + }, + { + "epoch": 0.01, + "learning_rate": 4.315880298461114e-06, + "loss": 3.2918, + "step": 2790400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307494350950593e-06, + "loss": 3.2993, + "step": 2790912 + }, + { + "epoch": 0.01, + "learning_rate": 4.299124782243804e-06, + "loss": 3.3015, + "step": 2791424 + }, + { + "epoch": 0.01, + "learning_rate": 4.290738834733284e-06, + "loss": 3.3135, + "step": 2791936 + }, + { + "epoch": 0.01, + "learning_rate": 4.282352887222764e-06, + "loss": 3.3073, + "step": 2792448 + }, + { + "epoch": 0.01, + "learning_rate": 4.273966939712244e-06, + "loss": 3.2975, + "step": 2792960 + }, + { + "epoch": 0.02, + "learning_rate": 4.265597371005456e-06, + "loss": 3.3122, + "step": 2793472 + }, + { + "epoch": 0.02, + "learning_rate": 4.257211423494936e-06, + "loss": 3.3004, + "step": 2793984 + }, + { + "epoch": 0.02, + "learning_rate": 4.248825475984415e-06, + "loss": 3.3059, + "step": 2794496 + }, + { + "epoch": 0.02, + "learning_rate": 4.240439528473896e-06, + "loss": 3.3028, + "step": 2795008 + }, + { + "epoch": 0.02, + "learning_rate": 4.2320699597671066e-06, + "loss": 3.3102, + "step": 2795520 + }, + { + "epoch": 0.02, + "learning_rate": 4.2236840122565865e-06, + "loss": 3.3175, + "step": 2796032 + }, + { + "epoch": 0.02, + "learning_rate": 4.2152980647460665e-06, + "loss": 3.3074, + "step": 2796544 + }, + { + "epoch": 0.02, + "learning_rate": 4.2069121172355464e-06, + "loss": 3.2881, + "step": 2797056 + }, + { + "epoch": 0.02, + "learning_rate": 4.198542548528757e-06, + "loss": 3.3121, + "step": 2797568 + }, + { + "epoch": 0.02, + "learning_rate": 4.190156601018238e-06, + "loss": 3.2991, + "step": 2798080 + }, + { + "epoch": 0.02, + "learning_rate": 4.181770653507717e-06, + "loss": 3.3082, + "step": 2798592 + }, + { + "epoch": 0.02, + "learning_rate": 4.173384705997197e-06, + "loss": 3.3133, + "step": 2799104 + }, + { + "epoch": 0.02, + "learning_rate": 4.165015137290409e-06, + "loss": 3.3024, + "step": 2799616 + }, + { + "epoch": 0.02, + "learning_rate": 4.156629189779889e-06, + "loss": 3.3003, + "step": 2800128 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482596210731e-06, + "loss": 3.3094, + "step": 2800640 + }, + { + "epoch": 0.02, + "learning_rate": 4.1398736735625794e-06, + "loss": 3.2921, + "step": 2801152 + }, + { + "epoch": 0.02, + "learning_rate": 4.13148772605206e-06, + "loss": 3.3105, + "step": 2801664 + }, + { + "epoch": 0.02, + "learning_rate": 4.123101778541539e-06, + "loss": 3.2979, + "step": 2802176 + }, + { + "epoch": 0.02, + "learning_rate": 4.11471583103102e-06, + "loss": 3.3097, + "step": 2802688 + }, + { + "epoch": 0.02, + "learning_rate": 4.106329883520499e-06, + "loss": 3.2928, + "step": 2803200 + }, + { + "epoch": 0.02, + "learning_rate": 4.097943936009979e-06, + "loss": 3.3127, + "step": 2803712 + }, + { + "epoch": 0.02, + "learning_rate": 4.089557988499459e-06, + "loss": 3.2964, + "step": 2804224 + }, + { + "epoch": 0.02, + "learning_rate": 4.081188419792671e-06, + "loss": 3.3022, + "step": 2804736 + }, + { + "epoch": 0.02, + "learning_rate": 4.072802472282151e-06, + "loss": 3.3111, + "step": 2805248 + }, + { + "epoch": 0.02, + "learning_rate": 4.064416524771631e-06, + "loss": 3.3048, + "step": 2805760 + }, + { + "epoch": 0.02, + "learning_rate": 4.056030577261111e-06, + "loss": 3.3154, + "step": 2806272 + }, + { + "epoch": 0.02, + "learning_rate": 4.0476610085543215e-06, + "loss": 3.312, + "step": 2806784 + }, + { + "epoch": 0.02, + "learning_rate": 4.039275061043802e-06, + "loss": 3.3022, + "step": 2807296 + }, + { + "epoch": 0.02, + "learning_rate": 4.030889113533281e-06, + "loss": 3.309, + "step": 2807808 + }, + { + "epoch": 0.02, + "learning_rate": 4.022519544826493e-06, + "loss": 3.3038, + "step": 2808320 + }, + { + "epoch": 0.02, + "learning_rate": 4.014133597315973e-06, + "loss": 3.3067, + "step": 2808832 + }, + { + "epoch": 0.02, + "learning_rate": 4.005747649805452e-06, + "loss": 3.2956, + "step": 2809344 + }, + { + "epoch": 0.02, + "learning_rate": 3.997361702294933e-06, + "loss": 3.3103, + "step": 2809856 + }, + { + "epoch": 0.02, + "learning_rate": 3.988992133588144e-06, + "loss": 3.3012, + "step": 2810368 + }, + { + "epoch": 0.02, + "learning_rate": 3.9806061860776245e-06, + "loss": 3.3035, + "step": 2810880 + }, + { + "epoch": 0.02, + "learning_rate": 3.972220238567104e-06, + "loss": 3.3015, + "step": 2811392 + }, + { + "epoch": 0.02, + "learning_rate": 3.963834291056584e-06, + "loss": 3.3102, + "step": 2811904 + }, + { + "epoch": 0.02, + "learning_rate": 3.955464722349795e-06, + "loss": 3.3015, + "step": 2812416 + }, + { + "epoch": 0.02, + "learning_rate": 3.947078774839275e-06, + "loss": 3.306, + "step": 2812928 + }, + { + "epoch": 0.02, + "learning_rate": 3.938692827328755e-06, + "loss": 3.3002, + "step": 2813440 + }, + { + "epoch": 0.02, + "learning_rate": 3.930323258621967e-06, + "loss": 3.3146, + "step": 2813952 + }, + { + "epoch": 0.02, + "learning_rate": 3.921937311111446e-06, + "loss": 3.3112, + "step": 2814464 + }, + { + "epoch": 0.02, + "learning_rate": 3.913551363600926e-06, + "loss": 3.3097, + "step": 2814976 + }, + { + "epoch": 0.02, + "learning_rate": 3.905165416090406e-06, + "loss": 3.3036, + "step": 2815488 + }, + { + "epoch": 0.02, + "learning_rate": 3.896779468579886e-06, + "loss": 3.3027, + "step": 2816000 + }, + { + "epoch": 0.02, + "learning_rate": 3.888393521069366e-06, + "loss": 3.313, + "step": 2816512 + }, + { + "epoch": 0.02, + "learning_rate": 3.880007573558846e-06, + "loss": 3.3079, + "step": 2817024 + }, + { + "epoch": 0.02, + "learning_rate": 3.8716216260483256e-06, + "loss": 3.299, + "step": 2817536 + }, + { + "epoch": 0.02, + "learning_rate": 3.863252057341537e-06, + "loss": 3.312, + "step": 2818048 + }, + { + "epoch": 0.02, + "learning_rate": 3.854866109831016e-06, + "loss": 3.3094, + "step": 2818560 + }, + { + "epoch": 0.02, + "learning_rate": 3.846480162320497e-06, + "loss": 3.3196, + "step": 2819072 + }, + { + "epoch": 0.02, + "learning_rate": 3.838110593613708e-06, + "loss": 3.3055, + "step": 2819584 + }, + { + "epoch": 0.02, + "learning_rate": 3.829724646103188e-06, + "loss": 3.3123, + "step": 2820096 + }, + { + "epoch": 0.02, + "learning_rate": 3.821338698592668e-06, + "loss": 3.3083, + "step": 2820608 + }, + { + "epoch": 0.02, + "learning_rate": 3.812952751082148e-06, + "loss": 3.3014, + "step": 2821120 + }, + { + "epoch": 0.02, + "learning_rate": 3.804583182375359e-06, + "loss": 3.3108, + "step": 2821632 + }, + { + "epoch": 0.02, + "learning_rate": 3.7961972348648394e-06, + "loss": 3.3109, + "step": 2822144 + }, + { + "epoch": 0.02, + "learning_rate": 3.787811287354319e-06, + "loss": 3.3095, + "step": 2822656 + }, + { + "epoch": 0.02, + "learning_rate": 3.7794253398437984e-06, + "loss": 3.2898, + "step": 2823168 + }, + { + "epoch": 0.02, + "learning_rate": 3.771039392333279e-06, + "loss": 3.3045, + "step": 2823680 + }, + { + "epoch": 0.03, + "eval_loss": 3.8724441528320312, + "eval_runtime": 302.2674, + "eval_samples_per_second": 1262.429, + "eval_steps_per_second": 39.452, + "step": 2823840 + }, + { + "epoch": 1.0, + "learning_rate": 3.7626534448227583e-06, + "loss": 3.2996, + "step": 2824192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7542674973122387e-06, + "loss": 3.3012, + "step": 2824704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7458815498017183e-06, + "loss": 3.3136, + "step": 2825216 + }, + { + "epoch": 1.0, + "learning_rate": 3.73751198109493e-06, + "loss": 3.3177, + "step": 2825728 + }, + { + "epoch": 1.0, + "learning_rate": 3.72912603358441e-06, + "loss": 3.3129, + "step": 2826240 + }, + { + "epoch": 1.0, + "learning_rate": 3.7207400860738894e-06, + "loss": 3.3037, + "step": 2826752 + }, + { + "epoch": 1.0, + "learning_rate": 3.7123541385633698e-06, + "loss": 3.3047, + "step": 2827264 + }, + { + "epoch": 1.0, + "learning_rate": 3.7039845698565806e-06, + "loss": 3.2934, + "step": 2827776 + }, + { + "epoch": 1.0, + "learning_rate": 3.695615001149792e-06, + "loss": 3.3118, + "step": 2828288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6872290536392717e-06, + "loss": 3.3132, + "step": 2828800 + }, + { + "epoch": 1.0, + "learning_rate": 3.678843106128752e-06, + "loss": 3.3037, + "step": 2829312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6704571586182316e-06, + "loss": 3.3075, + "step": 2829824 + }, + { + "epoch": 1.0, + "learning_rate": 3.662071211107712e-06, + "loss": 3.3014, + "step": 2830336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6536852635971915e-06, + "loss": 3.3036, + "step": 2830848 + }, + { + "epoch": 1.0, + "learning_rate": 3.645315694890403e-06, + "loss": 3.2947, + "step": 2831360 + }, + { + "epoch": 1.0, + "learning_rate": 3.636929747379883e-06, + "loss": 3.2984, + "step": 2831872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6285437998693627e-06, + "loss": 3.3001, + "step": 2832384 + }, + { + "epoch": 1.0, + "learning_rate": 3.620157852358843e-06, + "loss": 3.3004, + "step": 2832896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6117719048483226e-06, + "loss": 3.3055, + "step": 2833408 + }, + { + "epoch": 1.0, + "learning_rate": 3.603385957337802e-06, + "loss": 3.3176, + "step": 2833920 + }, + { + "epoch": 1.0, + "learning_rate": 3.5950000098272825e-06, + "loss": 3.3137, + "step": 2834432 + }, + { + "epoch": 1.0, + "learning_rate": 3.586614062316762e-06, + "loss": 3.3078, + "step": 2834944 + }, + { + "epoch": 1.0, + "learning_rate": 3.5782444936099737e-06, + "loss": 3.3053, + "step": 2835456 + }, + { + "epoch": 1.0, + "learning_rate": 3.569858546099453e-06, + "loss": 3.3121, + "step": 2835968 + }, + { + "epoch": 1.0, + "learning_rate": 3.5614725985889336e-06, + "loss": 3.2964, + "step": 2836480 + }, + { + "epoch": 1.0, + "learning_rate": 3.5530866510784135e-06, + "loss": 3.3104, + "step": 2836992 + }, + { + "epoch": 1.0, + "learning_rate": 3.544717082371625e-06, + "loss": 3.3001, + "step": 2837504 + }, + { + "epoch": 1.0, + "learning_rate": 3.5363311348611047e-06, + "loss": 3.2941, + "step": 2838016 + }, + { + "epoch": 1.0, + "learning_rate": 3.5279451873505842e-06, + "loss": 3.2977, + "step": 2838528 + }, + { + "epoch": 1.0, + "learning_rate": 3.5195592398400646e-06, + "loss": 3.3023, + "step": 2839040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5111896711332754e-06, + "loss": 3.3044, + "step": 2839552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5028037236227558e-06, + "loss": 3.3052, + "step": 2840064 + }, + { + "epoch": 1.01, + "learning_rate": 3.4944177761122353e-06, + "loss": 3.3086, + "step": 2840576 + }, + { + "epoch": 1.01, + "learning_rate": 3.4860318286017157e-06, + "loss": 3.3073, + "step": 2841088 + }, + { + "epoch": 1.01, + "learning_rate": 3.477662259894927e-06, + "loss": 3.2978, + "step": 2841600 + }, + { + "epoch": 1.01, + "learning_rate": 3.469276312384407e-06, + "loss": 3.309, + "step": 2842112 + }, + { + "epoch": 1.01, + "learning_rate": 3.460890364873887e-06, + "loss": 3.3015, + "step": 2842624 + }, + { + "epoch": 1.01, + "learning_rate": 3.4525044173633663e-06, + "loss": 3.3016, + "step": 2843136 + }, + { + "epoch": 1.01, + "learning_rate": 3.444134848656578e-06, + "loss": 3.295, + "step": 2843648 + }, + { + "epoch": 1.01, + "learning_rate": 3.4357489011460575e-06, + "loss": 3.2982, + "step": 2844160 + }, + { + "epoch": 1.01, + "learning_rate": 3.427362953635538e-06, + "loss": 3.3044, + "step": 2844672 + }, + { + "epoch": 1.01, + "learning_rate": 3.4189770061250174e-06, + "loss": 3.3129, + "step": 2845184 + }, + { + "epoch": 1.01, + "learning_rate": 3.410607437418229e-06, + "loss": 3.3018, + "step": 2845696 + }, + { + "epoch": 1.01, + "learning_rate": 3.4022214899077086e-06, + "loss": 3.3017, + "step": 2846208 + }, + { + "epoch": 1.01, + "learning_rate": 3.393835542397189e-06, + "loss": 3.311, + "step": 2846720 + }, + { + "epoch": 1.01, + "learning_rate": 3.3854495948866685e-06, + "loss": 3.3112, + "step": 2847232 + }, + { + "epoch": 1.01, + "learning_rate": 3.37708002617988e-06, + "loss": 3.3061, + "step": 2847744 + }, + { + "epoch": 1.01, + "learning_rate": 3.36869407866936e-06, + "loss": 3.2923, + "step": 2848256 + }, + { + "epoch": 1.01, + "learning_rate": 3.3603081311588396e-06, + "loss": 3.2811, + "step": 2848768 + }, + { + "epoch": 1.01, + "learning_rate": 3.35192218364832e-06, + "loss": 3.3153, + "step": 2849280 + }, + { + "epoch": 1.01, + "learning_rate": 3.343552614941531e-06, + "loss": 3.3067, + "step": 2849792 + }, + { + "epoch": 1.01, + "learning_rate": 3.335166667431011e-06, + "loss": 3.3031, + "step": 2850304 + }, + { + "epoch": 1.01, + "learning_rate": 3.3267807199204907e-06, + "loss": 3.2984, + "step": 2850816 + }, + { + "epoch": 1.01, + "learning_rate": 3.318394772409971e-06, + "loss": 3.2942, + "step": 2851328 + }, + { + "epoch": 1.01, + "learning_rate": 3.310025203703182e-06, + "loss": 3.2888, + "step": 2851840 + }, + { + "epoch": 1.01, + "learning_rate": 3.3016392561926623e-06, + "loss": 3.2961, + "step": 2852352 + }, + { + "epoch": 1.01, + "learning_rate": 3.293253308682142e-06, + "loss": 3.2938, + "step": 2852864 + }, + { + "epoch": 1.01, + "learning_rate": 3.2848673611716218e-06, + "loss": 3.3017, + "step": 2853376 + }, + { + "epoch": 1.01, + "learning_rate": 3.2764977924648334e-06, + "loss": 3.3075, + "step": 2853888 + }, + { + "epoch": 1.01, + "learning_rate": 3.268111844954313e-06, + "loss": 3.2951, + "step": 2854400 + }, + { + "epoch": 1.01, + "learning_rate": 3.2597258974437933e-06, + "loss": 3.2882, + "step": 2854912 + }, + { + "epoch": 1.01, + "learning_rate": 3.251339949933273e-06, + "loss": 3.3064, + "step": 2855424 + }, + { + "epoch": 1.01, + "learning_rate": 3.2429703812264845e-06, + "loss": 3.2881, + "step": 2855936 + }, + { + "epoch": 1.01, + "learning_rate": 3.234584433715964e-06, + "loss": 3.2904, + "step": 2856448 + }, + { + "epoch": 1.01, + "learning_rate": 3.2261984862054444e-06, + "loss": 3.3034, + "step": 2856960 + }, + { + "epoch": 1.01, + "learning_rate": 3.217828917498655e-06, + "loss": 3.3014, + "step": 2857472 + }, + { + "epoch": 1.01, + "learning_rate": 3.2094429699881356e-06, + "loss": 3.2913, + "step": 2857984 + }, + { + "epoch": 1.01, + "learning_rate": 3.201057022477615e-06, + "loss": 3.2923, + "step": 2858496 + }, + { + "epoch": 1.01, + "learning_rate": 3.192671074967095e-06, + "loss": 3.2925, + "step": 2859008 + }, + { + "epoch": 1.01, + "learning_rate": 3.1843015062603067e-06, + "loss": 3.2973, + "step": 2859520 + }, + { + "epoch": 1.01, + "learning_rate": 3.1759319375535183e-06, + "loss": 3.303, + "step": 2860032 + }, + { + "epoch": 1.01, + "learning_rate": 3.167545990042998e-06, + "loss": 3.2924, + "step": 2860544 + }, + { + "epoch": 1.01, + "learning_rate": 3.1591600425324774e-06, + "loss": 3.3048, + "step": 2861056 + }, + { + "epoch": 1.01, + "learning_rate": 3.1507740950219578e-06, + "loss": 3.3066, + "step": 2861568 + }, + { + "epoch": 1.01, + "learning_rate": 3.1423881475114373e-06, + "loss": 3.3049, + "step": 2862080 + }, + { + "epoch": 1.01, + "learning_rate": 3.1340022000009177e-06, + "loss": 3.2904, + "step": 2862592 + }, + { + "epoch": 1.01, + "learning_rate": 3.125616252490397e-06, + "loss": 3.3047, + "step": 2863104 + }, + { + "epoch": 1.01, + "learning_rate": 3.117230304979877e-06, + "loss": 3.306, + "step": 2863616 + }, + { + "epoch": 1.01, + "learning_rate": 3.1088607362730884e-06, + "loss": 3.2903, + "step": 2864128 + }, + { + "epoch": 1.01, + "learning_rate": 3.1004747887625683e-06, + "loss": 3.3067, + "step": 2864640 + }, + { + "epoch": 1.01, + "learning_rate": 3.0920888412520483e-06, + "loss": 3.2997, + "step": 2865152 + }, + { + "epoch": 1.01, + "learning_rate": 3.0837028937415282e-06, + "loss": 3.3105, + "step": 2865664 + }, + { + "epoch": 1.01, + "learning_rate": 3.0753333250347395e-06, + "loss": 3.2954, + "step": 2866176 + }, + { + "epoch": 1.01, + "learning_rate": 3.0669473775242194e-06, + "loss": 3.2803, + "step": 2866688 + }, + { + "epoch": 1.01, + "learning_rate": 3.0585614300136994e-06, + "loss": 3.2936, + "step": 2867200 + }, + { + "epoch": 1.01, + "learning_rate": 3.0501754825031793e-06, + "loss": 3.294, + "step": 2867712 + }, + { + "epoch": 1.01, + "learning_rate": 3.0418059137963905e-06, + "loss": 3.3018, + "step": 2868224 + }, + { + "epoch": 1.01, + "learning_rate": 3.0334199662858705e-06, + "loss": 3.2973, + "step": 2868736 + }, + { + "epoch": 1.01, + "learning_rate": 3.0250340187753504e-06, + "loss": 3.2924, + "step": 2869248 + }, + { + "epoch": 1.02, + "learning_rate": 3.01664807126483e-06, + "loss": 3.3011, + "step": 2869760 + }, + { + "epoch": 1.02, + "learning_rate": 3.008278502558042e-06, + "loss": 3.2976, + "step": 2870272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9998925550475216e-06, + "loss": 3.2902, + "step": 2870784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9915066075370015e-06, + "loss": 3.2966, + "step": 2871296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9831206600264815e-06, + "loss": 3.3048, + "step": 2871808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9747510913196927e-06, + "loss": 3.3085, + "step": 2872320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9663651438091727e-06, + "loss": 3.2969, + "step": 2872832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9579791962986526e-06, + "loss": 3.2825, + "step": 2873344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9495932487881326e-06, + "loss": 3.3047, + "step": 2873856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9412236800813438e-06, + "loss": 3.292, + "step": 2874368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9328377325708237e-06, + "loss": 3.3016, + "step": 2874880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9244517850603037e-06, + "loss": 3.3038, + "step": 2875392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9160658375497836e-06, + "loss": 3.2898, + "step": 2875904 + }, + { + "epoch": 1.02, + "learning_rate": 2.907696268842995e-06, + "loss": 3.2937, + "step": 2876416 + }, + { + "epoch": 1.02, + "learning_rate": 2.8993267001362065e-06, + "loss": 3.303, + "step": 2876928 + }, + { + "epoch": 1.02, + "learning_rate": 2.890940752625686e-06, + "loss": 3.2867, + "step": 2877440 + }, + { + "epoch": 1.02, + "learning_rate": 2.882554805115166e-06, + "loss": 3.3013, + "step": 2877952 + }, + { + "epoch": 1.02, + "learning_rate": 2.874168857604646e-06, + "loss": 3.285, + "step": 2878464 + }, + { + "epoch": 1.02, + "learning_rate": 2.865782910094126e-06, + "loss": 3.3024, + "step": 2878976 + }, + { + "epoch": 1.02, + "learning_rate": 2.857396962583606e-06, + "loss": 3.2847, + "step": 2879488 + }, + { + "epoch": 1.02, + "learning_rate": 2.8490110150730854e-06, + "loss": 3.3031, + "step": 2880000 + }, + { + "epoch": 1.02, + "learning_rate": 2.840641446366297e-06, + "loss": 3.2912, + "step": 2880512 + }, + { + "epoch": 1.02, + "learning_rate": 2.832255498855777e-06, + "loss": 3.2902, + "step": 2881024 + }, + { + "epoch": 1.02, + "learning_rate": 2.823869551345257e-06, + "loss": 3.3022, + "step": 2881536 + }, + { + "epoch": 1.02, + "learning_rate": 2.815483603834737e-06, + "loss": 3.2947, + "step": 2882048 + }, + { + "epoch": 1.02, + "learning_rate": 2.807114035127948e-06, + "loss": 3.3073, + "step": 2882560 + }, + { + "epoch": 1.02, + "learning_rate": 2.798728087617428e-06, + "loss": 3.3083, + "step": 2883072 + }, + { + "epoch": 1.02, + "learning_rate": 2.790342140106908e-06, + "loss": 3.2934, + "step": 2883584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7819561925963875e-06, + "loss": 3.3018, + "step": 2884096 + }, + { + "epoch": 1.02, + "learning_rate": 2.773586623889599e-06, + "loss": 3.2933, + "step": 2884608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652006763790787e-06, + "loss": 3.299, + "step": 2885120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568147288685587e-06, + "loss": 3.2922, + "step": 2885632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7484287813580386e-06, + "loss": 3.2995, + "step": 2886144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7400592126512503e-06, + "loss": 3.2936, + "step": 2886656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7316732651407302e-06, + "loss": 3.2935, + "step": 2887168 + }, + { + "epoch": 1.02, + "learning_rate": 2.72328731763021e-06, + "loss": 3.2987, + "step": 2887680 + }, + { + "epoch": 1.02, + "learning_rate": 2.71490137011969e-06, + "loss": 3.3016, + "step": 2888192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7065318014129013e-06, + "loss": 3.2915, + "step": 2888704 + }, + { + "epoch": 1.02, + "learning_rate": 2.6981458539023813e-06, + "loss": 3.2974, + "step": 2889216 + }, + { + "epoch": 1.02, + "learning_rate": 2.689759906391861e-06, + "loss": 3.2887, + "step": 2889728 + }, + { + "epoch": 1.02, + "learning_rate": 2.6813903376850725e-06, + "loss": 3.3122, + "step": 2890240 + }, + { + "epoch": 1.02, + "learning_rate": 2.673004390174552e-06, + "loss": 3.2959, + "step": 2890752 + }, + { + "epoch": 1.02, + "learning_rate": 2.664618442664032e-06, + "loss": 3.3051, + "step": 2891264 + }, + { + "epoch": 1.02, + "learning_rate": 2.656232495153512e-06, + "loss": 3.2952, + "step": 2891776 + }, + { + "epoch": 1.02, + "learning_rate": 2.647846547642992e-06, + "loss": 3.2975, + "step": 2892288 + }, + { + "epoch": 1.02, + "learning_rate": 2.639460600132472e-06, + "loss": 3.3021, + "step": 2892800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6310746526219518e-06, + "loss": 3.2991, + "step": 2893312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6226887051114317e-06, + "loss": 3.2942, + "step": 2893824 + }, + { + "epoch": 1.02, + "learning_rate": 2.614319136404643e-06, + "loss": 3.3054, + "step": 2894336 + }, + { + "epoch": 1.02, + "learning_rate": 2.605933188894123e-06, + "loss": 3.3005, + "step": 2894848 + }, + { + "epoch": 1.02, + "learning_rate": 2.597547241383603e-06, + "loss": 3.3124, + "step": 2895360 + }, + { + "epoch": 1.02, + "learning_rate": 2.589177672676814e-06, + "loss": 3.2941, + "step": 2895872 + }, + { + "epoch": 1.02, + "learning_rate": 2.580791725166294e-06, + "loss": 3.3043, + "step": 2896384 + }, + { + "epoch": 1.02, + "learning_rate": 2.572405777655774e-06, + "loss": 3.2998, + "step": 2896896 + }, + { + "epoch": 1.02, + "learning_rate": 2.564019830145254e-06, + "loss": 3.2967, + "step": 2897408 + }, + { + "epoch": 1.02, + "learning_rate": 2.5556502614384656e-06, + "loss": 3.3012, + "step": 2897920 + }, + { + "epoch": 1.02, + "learning_rate": 2.5472643139279455e-06, + "loss": 3.3027, + "step": 2898432 + }, + { + "epoch": 1.02, + "learning_rate": 2.538878366417425e-06, + "loss": 3.3079, + "step": 2898944 + }, + { + "epoch": 1.02, + "learning_rate": 2.530492418906905e-06, + "loss": 3.2776, + "step": 2899456 + }, + { + "epoch": 1.02, + "learning_rate": 2.522106471396385e-06, + "loss": 3.3015, + "step": 2899968 + }, + { + "epoch": 1.03, + "eval_loss": 3.871725082397461, + "eval_runtime": 302.0261, + "eval_samples_per_second": 1263.437, + "eval_steps_per_second": 39.483, + "step": 2900160 + }, + { + "epoch": 0.0, + "learning_rate": 2.513720523885865e-06, + "loss": 3.2905, + "step": 2900480 + }, + { + "epoch": 0.0, + "learning_rate": 2.5053345763753445e-06, + "loss": 3.2932, + "step": 2900992 + }, + { + "epoch": 0.0, + "learning_rate": 2.4969486288648244e-06, + "loss": 3.3047, + "step": 2901504 + }, + { + "epoch": 0.0, + "learning_rate": 2.4885626813543044e-06, + "loss": 3.314, + "step": 2902016 + }, + { + "epoch": 0.0, + "learning_rate": 2.4801931126475156e-06, + "loss": 3.3047, + "step": 2902528 + }, + { + "epoch": 0.0, + "learning_rate": 2.4718071651369956e-06, + "loss": 3.2937, + "step": 2903040 + }, + { + "epoch": 0.0, + "learning_rate": 2.4634212176264755e-06, + "loss": 3.2975, + "step": 2903552 + }, + { + "epoch": 0.0, + "learning_rate": 2.4550352701159555e-06, + "loss": 3.288, + "step": 2904064 + }, + { + "epoch": 0.0, + "learning_rate": 2.4466820802128984e-06, + "loss": 3.3002, + "step": 2904576 + }, + { + "epoch": 0.0, + "learning_rate": 2.4382961327023783e-06, + "loss": 3.3049, + "step": 2905088 + }, + { + "epoch": 0.0, + "learning_rate": 2.4299101851918583e-06, + "loss": 3.3038, + "step": 2905600 + }, + { + "epoch": 0.0, + "learning_rate": 2.4215242376813382e-06, + "loss": 3.2964, + "step": 2906112 + }, + { + "epoch": 0.0, + "learning_rate": 2.4131382901708178e-06, + "loss": 3.295, + "step": 2906624 + }, + { + "epoch": 0.0, + "learning_rate": 2.4047523426602977e-06, + "loss": 3.2925, + "step": 2907136 + }, + { + "epoch": 0.0, + "learning_rate": 2.3963663951497777e-06, + "loss": 3.2874, + "step": 2907648 + }, + { + "epoch": 0.0, + "learning_rate": 2.3879804476392576e-06, + "loss": 3.2869, + "step": 2908160 + }, + { + "epoch": 0.0, + "learning_rate": 2.379610878932469e-06, + "loss": 3.2922, + "step": 2908672 + }, + { + "epoch": 0.0, + "learning_rate": 2.371224931421949e-06, + "loss": 3.2927, + "step": 2909184 + }, + { + "epoch": 0.0, + "learning_rate": 2.3628389839114288e-06, + "loss": 3.2987, + "step": 2909696 + }, + { + "epoch": 0.0, + "learning_rate": 2.3544530364009087e-06, + "loss": 3.3085, + "step": 2910208 + }, + { + "epoch": 0.0, + "learning_rate": 2.3460834676941203e-06, + "loss": 3.3079, + "step": 2910720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3376975201836e-06, + "loss": 3.2989, + "step": 2911232 + }, + { + "epoch": 0.0, + "learning_rate": 2.32931157267308e-06, + "loss": 3.2962, + "step": 2911744 + }, + { + "epoch": 0.0, + "learning_rate": 2.3209256251625598e-06, + "loss": 3.3023, + "step": 2912256 + }, + { + "epoch": 0.0, + "learning_rate": 2.312556056455771e-06, + "loss": 3.2891, + "step": 2912768 + }, + { + "epoch": 0.0, + "learning_rate": 2.304170108945251e-06, + "loss": 3.3061, + "step": 2913280 + }, + { + "epoch": 0.0, + "learning_rate": 2.295784161434731e-06, + "loss": 3.2923, + "step": 2913792 + }, + { + "epoch": 0.0, + "learning_rate": 2.287398213924211e-06, + "loss": 3.2836, + "step": 2914304 + }, + { + "epoch": 0.0, + "learning_rate": 2.279028645217422e-06, + "loss": 3.2909, + "step": 2914816 + }, + { + "epoch": 0.0, + "learning_rate": 2.270642697706902e-06, + "loss": 3.2936, + "step": 2915328 + }, + { + "epoch": 0.01, + "learning_rate": 2.262256750196382e-06, + "loss": 3.2948, + "step": 2915840 + }, + { + "epoch": 0.01, + "learning_rate": 2.253870802685862e-06, + "loss": 3.2966, + "step": 2916352 + }, + { + "epoch": 0.01, + "learning_rate": 2.245501233979073e-06, + "loss": 3.3015, + "step": 2916864 + }, + { + "epoch": 0.01, + "learning_rate": 2.237115286468553e-06, + "loss": 3.2992, + "step": 2917376 + }, + { + "epoch": 0.01, + "learning_rate": 2.228729338958033e-06, + "loss": 3.2858, + "step": 2917888 + }, + { + "epoch": 0.01, + "learning_rate": 2.220343391447513e-06, + "loss": 3.3059, + "step": 2918400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2119738227407242e-06, + "loss": 3.2918, + "step": 2918912 + }, + { + "epoch": 0.01, + "learning_rate": 2.203587875230204e-06, + "loss": 3.2899, + "step": 2919424 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952019277196837e-06, + "loss": 3.2899, + "step": 2919936 + }, + { + "epoch": 0.01, + "learning_rate": 2.1868159802091637e-06, + "loss": 3.2848, + "step": 2920448 + }, + { + "epoch": 0.01, + "learning_rate": 2.1784464115023753e-06, + "loss": 3.2976, + "step": 2920960 + }, + { + "epoch": 0.01, + "learning_rate": 2.1700604639918553e-06, + "loss": 3.3048, + "step": 2921472 + }, + { + "epoch": 0.01, + "learning_rate": 2.1616745164813352e-06, + "loss": 3.2922, + "step": 2921984 + }, + { + "epoch": 0.01, + "learning_rate": 2.153288568970815e-06, + "loss": 3.2949, + "step": 2922496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1449190002640264e-06, + "loss": 3.3016, + "step": 2923008 + }, + { + "epoch": 0.01, + "learning_rate": 2.1365330527535064e-06, + "loss": 3.3057, + "step": 2923520 + }, + { + "epoch": 0.01, + "learning_rate": 2.1281471052429863e-06, + "loss": 3.3013, + "step": 2924032 + }, + { + "epoch": 0.01, + "learning_rate": 2.119761157732466e-06, + "loss": 3.2878, + "step": 2924544 + }, + { + "epoch": 0.01, + "learning_rate": 2.1113915890256775e-06, + "loss": 3.267, + "step": 2925056 + }, + { + "epoch": 0.01, + "learning_rate": 2.103005641515157e-06, + "loss": 3.3108, + "step": 2925568 + }, + { + "epoch": 0.01, + "learning_rate": 2.094619694004637e-06, + "loss": 3.2989, + "step": 2926080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0862337464941174e-06, + "loss": 3.2976, + "step": 2926592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0778641777873286e-06, + "loss": 3.2892, + "step": 2927104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0694782302768085e-06, + "loss": 3.2865, + "step": 2927616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0610922827662885e-06, + "loss": 3.2815, + "step": 2928128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0527063352557684e-06, + "loss": 3.2862, + "step": 2928640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0443367665489797e-06, + "loss": 3.2875, + "step": 2929152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0359508190384596e-06, + "loss": 3.2934, + "step": 2929664 + }, + { + "epoch": 0.01, + "learning_rate": 2.027564871527939e-06, + "loss": 3.3008, + "step": 2930176 + }, + { + "epoch": 0.01, + "learning_rate": 2.019178924017419e-06, + "loss": 3.2848, + "step": 2930688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0108093553106307e-06, + "loss": 3.2816, + "step": 2931200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0024234078001107e-06, + "loss": 3.2988, + "step": 2931712 + }, + { + "epoch": 0.01, + "learning_rate": 1.9940374602895906e-06, + "loss": 3.2853, + "step": 2932224 + }, + { + "epoch": 0.01, + "learning_rate": 1.985667891582802e-06, + "loss": 3.2824, + "step": 2932736 + }, + { + "epoch": 0.01, + "learning_rate": 1.977281944072282e-06, + "loss": 3.294, + "step": 2933248 + }, + { + "epoch": 0.01, + "learning_rate": 1.9688959965617618e-06, + "loss": 3.2894, + "step": 2933760 + }, + { + "epoch": 0.01, + "learning_rate": 1.9605100490512417e-06, + "loss": 3.2832, + "step": 2934272 + }, + { + "epoch": 0.01, + "learning_rate": 1.9521241015407213e-06, + "loss": 3.2836, + "step": 2934784 + }, + { + "epoch": 0.01, + "learning_rate": 1.943754532833933e-06, + "loss": 3.2823, + "step": 2935296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9353685853234124e-06, + "loss": 3.2924, + "step": 2935808 + }, + { + "epoch": 0.01, + "learning_rate": 1.926999016616624e-06, + "loss": 3.2923, + "step": 2936320 + }, + { + "epoch": 0.01, + "learning_rate": 1.918613069106104e-06, + "loss": 3.2891, + "step": 2936832 + }, + { + "epoch": 0.01, + "learning_rate": 1.910227121595584e-06, + "loss": 3.2947, + "step": 2937344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9018411740850637e-06, + "loss": 3.2992, + "step": 2937856 + }, + { + "epoch": 0.01, + "learning_rate": 1.8934552265745437e-06, + "loss": 3.2998, + "step": 2938368 + }, + { + "epoch": 0.01, + "learning_rate": 1.8850692790640236e-06, + "loss": 3.2819, + "step": 2938880 + }, + { + "epoch": 0.01, + "learning_rate": 1.8766833315535034e-06, + "loss": 3.2957, + "step": 2939392 + }, + { + "epoch": 0.01, + "learning_rate": 1.8682973840429833e-06, + "loss": 3.2982, + "step": 2939904 + }, + { + "epoch": 0.01, + "learning_rate": 1.8599278153361945e-06, + "loss": 3.282, + "step": 2940416 + }, + { + "epoch": 0.01, + "learning_rate": 1.8515418678256745e-06, + "loss": 3.2986, + "step": 2940928 + }, + { + "epoch": 0.01, + "learning_rate": 1.8431559203151545e-06, + "loss": 3.295, + "step": 2941440 + }, + { + "epoch": 0.01, + "learning_rate": 1.8347699728046344e-06, + "loss": 3.2982, + "step": 2941952 + }, + { + "epoch": 0.01, + "learning_rate": 1.8264004040978458e-06, + "loss": 3.2889, + "step": 2942464 + }, + { + "epoch": 0.01, + "learning_rate": 1.8180144565873258e-06, + "loss": 3.2738, + "step": 2942976 + }, + { + "epoch": 0.01, + "learning_rate": 1.8096285090768053e-06, + "loss": 3.2851, + "step": 2943488 + }, + { + "epoch": 0.01, + "learning_rate": 1.8012425615662853e-06, + "loss": 3.2855, + "step": 2944000 + }, + { + "epoch": 0.01, + "learning_rate": 1.7928729928594967e-06, + "loss": 3.2964, + "step": 2944512 + }, + { + "epoch": 0.01, + "learning_rate": 1.7844870453489767e-06, + "loss": 3.2888, + "step": 2945024 + }, + { + "epoch": 0.01, + "learning_rate": 1.7761010978384566e-06, + "loss": 3.2852, + "step": 2945536 + }, + { + "epoch": 0.02, + "learning_rate": 1.7677151503279366e-06, + "loss": 3.2907, + "step": 2946048 + }, + { + "epoch": 0.02, + "learning_rate": 1.7593455816211478e-06, + "loss": 3.2954, + "step": 2946560 + }, + { + "epoch": 0.02, + "learning_rate": 1.7509596341106277e-06, + "loss": 3.2811, + "step": 2947072 + }, + { + "epoch": 0.02, + "learning_rate": 1.7425736866001077e-06, + "loss": 3.289, + "step": 2947584 + }, + { + "epoch": 0.02, + "learning_rate": 1.7341877390895874e-06, + "loss": 3.3007, + "step": 2948096 + }, + { + "epoch": 0.02, + "learning_rate": 1.725818170382799e-06, + "loss": 3.3005, + "step": 2948608 + }, + { + "epoch": 0.02, + "learning_rate": 1.7174322228722786e-06, + "loss": 3.2916, + "step": 2949120 + }, + { + "epoch": 0.02, + "learning_rate": 1.7090462753617586e-06, + "loss": 3.277, + "step": 2949632 + }, + { + "epoch": 0.02, + "learning_rate": 1.7006603278512385e-06, + "loss": 3.2943, + "step": 2950144 + }, + { + "epoch": 0.02, + "learning_rate": 1.69229075914445e-06, + "loss": 3.2829, + "step": 2950656 + }, + { + "epoch": 0.02, + "learning_rate": 1.68390481163393e-06, + "loss": 3.2956, + "step": 2951168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6755188641234099e-06, + "loss": 3.2973, + "step": 2951680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6671329166128898e-06, + "loss": 3.286, + "step": 2952192 + }, + { + "epoch": 0.02, + "learning_rate": 1.658763347906101e-06, + "loss": 3.2864, + "step": 2952704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6503937791993125e-06, + "loss": 3.2905, + "step": 2953216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420078316887924e-06, + "loss": 3.2795, + "step": 2953728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6336218841782724e-06, + "loss": 3.2966, + "step": 2954240 + }, + { + "epoch": 0.02, + "learning_rate": 1.625235936667752e-06, + "loss": 3.276, + "step": 2954752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6168499891572319e-06, + "loss": 3.2966, + "step": 2955264 + }, + { + "epoch": 0.02, + "learning_rate": 1.608464041646712e-06, + "loss": 3.2792, + "step": 2955776 + }, + { + "epoch": 0.02, + "learning_rate": 1.600078094136192e-06, + "loss": 3.2915, + "step": 2956288 + }, + { + "epoch": 0.02, + "learning_rate": 1.591692146625672e-06, + "loss": 3.2858, + "step": 2956800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5833225779188831e-06, + "loss": 3.2862, + "step": 2957312 + }, + { + "epoch": 0.02, + "learning_rate": 1.574936630408363e-06, + "loss": 3.2927, + "step": 2957824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5665506828978428e-06, + "loss": 3.2872, + "step": 2958336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5581647353873228e-06, + "loss": 3.3024, + "step": 2958848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5497951666805342e-06, + "loss": 3.2979, + "step": 2959360 + }, + { + "epoch": 0.02, + "learning_rate": 1.541409219170014e-06, + "loss": 3.2901, + "step": 2959872 + }, + { + "epoch": 0.02, + "learning_rate": 1.533023271659494e-06, + "loss": 3.2927, + "step": 2960384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5246373241489737e-06, + "loss": 3.2881, + "step": 2960896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5162677554421853e-06, + "loss": 3.2898, + "step": 2961408 + }, + { + "epoch": 0.02, + "learning_rate": 1.507881807931665e-06, + "loss": 3.2859, + "step": 2961920 + }, + { + "epoch": 0.02, + "learning_rate": 1.499495860421145e-06, + "loss": 3.2885, + "step": 2962432 + }, + { + "epoch": 0.02, + "learning_rate": 1.491109912910625e-06, + "loss": 3.2857, + "step": 2962944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4827403442038362e-06, + "loss": 3.2904, + "step": 2963456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4743543966933161e-06, + "loss": 3.2914, + "step": 2963968 + }, + { + "epoch": 0.02, + "learning_rate": 1.465968449182796e-06, + "loss": 3.2905, + "step": 2964480 + }, + { + "epoch": 0.02, + "learning_rate": 1.457582501672276e-06, + "loss": 3.2882, + "step": 2964992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4492129329654873e-06, + "loss": 3.2901, + "step": 2965504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4408269854549672e-06, + "loss": 3.2798, + "step": 2966016 + }, + { + "epoch": 0.02, + "learning_rate": 1.432441037944447e-06, + "loss": 3.3026, + "step": 2966528 + }, + { + "epoch": 0.02, + "learning_rate": 1.424055090433927e-06, + "loss": 3.2918, + "step": 2967040 + }, + { + "epoch": 0.02, + "learning_rate": 1.4156855217271383e-06, + "loss": 3.3007, + "step": 2967552 + }, + { + "epoch": 0.02, + "learning_rate": 1.4072995742166183e-06, + "loss": 3.2816, + "step": 2968064 + }, + { + "epoch": 0.02, + "learning_rate": 1.398913626706098e-06, + "loss": 3.2931, + "step": 2968576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3905440579993095e-06, + "loss": 3.2939, + "step": 2969088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3821581104887894e-06, + "loss": 3.2952, + "step": 2969600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3737721629782694e-06, + "loss": 3.2807, + "step": 2970112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3653862154677493e-06, + "loss": 3.2988, + "step": 2970624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3570166467609606e-06, + "loss": 3.2906, + "step": 2971136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3486306992504405e-06, + "loss": 3.3077, + "step": 2971648 + }, + { + "epoch": 0.02, + "learning_rate": 1.340261130543652e-06, + "loss": 3.2832, + "step": 2972160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3318751830331319e-06, + "loss": 3.2992, + "step": 2972672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3234892355226116e-06, + "loss": 3.2923, + "step": 2973184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3151032880120916e-06, + "loss": 3.289, + "step": 2973696 + }, + { + "epoch": 0.02, + "learning_rate": 1.306733719305303e-06, + "loss": 3.2941, + "step": 2974208 + }, + { + "epoch": 0.02, + "learning_rate": 1.298347771794783e-06, + "loss": 3.2937, + "step": 2974720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2899618242842627e-06, + "loss": 3.2984, + "step": 2975232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2815758767737427e-06, + "loss": 3.2735, + "step": 2975744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2731899292632224e-06, + "loss": 3.2961, + "step": 2976256 + }, + { + "epoch": 0.03, + "eval_loss": 3.8712921142578125, + "eval_runtime": 308.0583, + "eval_samples_per_second": 1238.697, + "eval_steps_per_second": 38.71, + "step": 2976480 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 2.071853443103109e+18, + "trial_name": null, + "trial_params": null +}