diff --git "a/checkpoint-1373749/trainer_state.json" "b/checkpoint-1373749/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1373749/trainer_state.json" @@ -0,0 +1,16267 @@ +{ + "best_metric": 3.8440616130828857, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/transformer/2/checkpoints/checkpoint-915829", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1373749, + "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": 10.9748, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8335, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1931, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9727, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8231, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7041, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6016, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5361, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4785, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4027, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3692, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3265, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2678, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.218, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.1917, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.1596, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1264, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0807, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0634, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0329, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0061, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9914, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9694, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.943, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9239, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.9086, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8847, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8743, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8388, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8435, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8097, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.8009, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.8019, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7844, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7601, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7462, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7482, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7292, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7189, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.7026, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6858, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6757, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964790485618428e-05, + "loss": 4.6629, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 4.6644, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6533, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6474, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6327, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.9605991497435414e-05, + "loss": 4.6294, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.6336, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.6089, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6038, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5928, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.6029, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5665, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.586, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5609, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5566, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5588, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5506, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5343, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949702331620985e-05, + "loss": 4.5269, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5172, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5281, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.5142, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5029, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.5038, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4942, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4746, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4968, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.475, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4703, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4823, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.46, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4737, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4683, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4587, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4621, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.436, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4327, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4363, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4363, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4316, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4156, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.406, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4098, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928747290126923e-05, + "loss": 4.4097, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927908695375871e-05, + "loss": 4.4103, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927070100624819e-05, + "loss": 4.4131, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.4071, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3936, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3799, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3803, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3867, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3824, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3645, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3697, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.37, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3722, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3687, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3638, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3654, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3557, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914496093000158e-05, + "loss": 4.3526, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3604, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912820541378427e-05, + "loss": 4.3435, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911981946627375e-05, + "loss": 4.3519, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3299, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3253, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3249, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3355, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.9077906107524886e-05, + "loss": 4.3297, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.9069520160014366e-05, + "loss": 4.3067, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.9061134212503846e-05, + "loss": 4.3096, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3205, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3266, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3129, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.3187, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.311, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.3126, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.3018, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.3001, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.2924, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.3002, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2838, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2938, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2868, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2966, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2701, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2823, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2914, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2696, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2881, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2756, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2764, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2686, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.2626, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2618, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2698, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.8843197850052706e-05, + "loss": 4.2741, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.8834811902542186e-05, + "loss": 4.2628, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826425955031666e-05, + "loss": 4.2681, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818040007521146e-05, + "loss": 4.2596, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2473, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2546, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2431, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87845125962828e-05, + "loss": 4.2456, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877612664877228e-05, + "loss": 4.2451, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2405, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2369, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2371, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.200362205505371, + "eval_runtime": 608.2164, + "eval_samples_per_second": 627.393, + "eval_steps_per_second": 19.607, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.874259923753393e-05, + "loss": 4.2423, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.238, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2301, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.2275, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.2279, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2038, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2201, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.219, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2098, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2178, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.22, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2048, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.2033, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.2042, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.2046, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1923, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1931, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.196, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1929, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.197, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.195, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1953, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1899, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1902, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1878, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1821, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1875, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1686, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1817, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.166, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1705, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1808, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1779, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1653, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1602, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1722, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.165, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1654, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1591, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.1445, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1454, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1457, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1544, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.8382134525011416e-05, + "loss": 4.1438, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1486, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1451, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1474, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834860711377307e-05, + "loss": 4.1558, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.1358, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1389, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1301, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.831507970253472e-05, + "loss": 4.1523, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.1226, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.1426, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1235, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.1306, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1336, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1312, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1202, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1232, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1081, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1266, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.1214, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.1146, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1128, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.1157, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.0966, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.1189, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.817258411007081e-05, + "loss": 4.1041, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816419816256029e-05, + "loss": 4.108, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.815581221504977e-05, + "loss": 4.1165, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.1026, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.813905669883246e-05, + "loss": 4.1143, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813067075132194e-05, + "loss": 4.1194, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812228480381141e-05, + "loss": 4.1118, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.1143, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810552928759411e-05, + "loss": 4.0969, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809714334008359e-05, + "loss": 4.0922, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808875739257306e-05, + "loss": 4.1002, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.1069, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.1005, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.8063615928845243e-05, + "loss": 4.0915, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.8055229981334717e-05, + "loss": 4.0801, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.8046844033824197e-05, + "loss": 4.0844, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803847446511741e-05, + "loss": 4.0877, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.8030088517606886e-05, + "loss": 4.0906, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.8021702570096366e-05, + "loss": 4.1005, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.8013316622585846e-05, + "loss": 4.0974, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800494705387906e-05, + "loss": 4.0852, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.799657748517227e-05, + "loss": 4.0801, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.798819153766175e-05, + "loss": 4.0757, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.083, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797141964264071e-05, + "loss": 4.0825, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796303369513019e-05, + "loss": 4.0777, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.074, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.7946278178912886e-05, + "loss": 4.0807, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793789223140236e-05, + "loss": 4.0849, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792950628389184e-05, + "loss": 4.0799, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792112033638132e-05, + "loss": 4.08, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.79127343888708e-05, + "loss": 4.0852, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790434844136028e-05, + "loss": 4.0754, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789596249384976e-05, + "loss": 4.0736, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788759292514297e-05, + "loss": 4.088, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.7879223356436184e-05, + "loss": 4.0704, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870837408925664e-05, + "loss": 4.0828, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.7862451461415144e-05, + "loss": 4.0661, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7854065513904624e-05, + "loss": 4.0564, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.0651, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.072, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.782892405017679e-05, + "loss": 4.0652, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.782053810266627e-05, + "loss": 4.0527, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781215215515575e-05, + "loss": 4.0499, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780376620764523e-05, + "loss": 4.0634, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779538026013471e-05, + "loss": 4.0729, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778699431262419e-05, + "loss": 4.0601, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.77786247439174e-05, + "loss": 4.0732, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777023879640689e-05, + "loss": 4.0602, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.062, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.0607, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.774508095387533e-05, + "loss": 4.0542, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773671138516854e-05, + "loss": 4.0475, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772832543765802e-05, + "loss": 4.0611, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.77199394901475e-05, + "loss": 4.0477, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771155354263698e-05, + "loss": 4.0496, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0524, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0615, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0392, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.7678026131398626e-05, + "loss": 4.0441, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.7669640183888106e-05, + "loss": 4.0641, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.7661254236377586e-05, + "loss": 4.0422, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.765286828886707e-05, + "loss": 4.062, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0452, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.7636096393846026e-05, + "loss": 4.0542, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.7627710446335506e-05, + "loss": 4.042, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.7619324498824986e-05, + "loss": 4.0371, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.0418, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.0476, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.0581, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.0495, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.7577427518879844e-05, + "loss": 4.0492, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.7569041571369324e-05, + "loss": 4.0435, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756065562385881e-05, + "loss": 4.0301, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755226967634829e-05, + "loss": 4.0441, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.75439001076415e-05, + "loss": 4.0312, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.0346, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0387, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.751874226510994e-05, + "loss": 4.0264, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751035631759942e-05, + "loss": 4.0335, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.75019703700889e-05, + "loss": 4.0294, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.031442642211914, + "eval_runtime": 575.8524, + "eval_samples_per_second": 662.654, + "eval_steps_per_second": 20.708, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.749360080138211e-05, + "loss": 4.0398, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748521485387159e-05, + "loss": 4.0362, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747682890636107e-05, + "loss": 4.03, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746844295885055e-05, + "loss": 4.0269, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746005701134003e-05, + "loss": 4.0301, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745167106382951e-05, + "loss": 4.0118, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744328511631899e-05, + "loss": 4.0276, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434899168808475e-05, + "loss": 4.0213, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0126, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418143652591164e-05, + "loss": 4.0265, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409757705080644e-05, + "loss": 4.0314, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401371757570124e-05, + "loss": 4.0126, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739300218886333e-05, + "loss": 4.0112, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738461624135281e-05, + "loss": 4.0155, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737623029384229e-05, + "loss": 4.0168, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736784434633177e-05, + "loss": 4.008, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735945839882125e-05, + "loss": 4.0077, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735107245131073e-05, + "loss": 4.0094, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 4.0119, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733431693509343e-05, + "loss": 4.0168, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732593098758291e-05, + "loss": 4.0117, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731754504007238e-05, + "loss": 4.0176, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 4.0135, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 4.0085, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729240357634456e-05, + "loss": 4.0116, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728401762883403e-05, + "loss": 4.0082, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727563168132351e-05, + "loss": 4.013, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726724573381299e-05, + "loss": 3.996, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725887616510621e-05, + "loss": 4.0076, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725049021759568e-05, + "loss": 3.9948, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724210427008517e-05, + "loss": 3.9992, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233718322574647e-05, + "loss": 4.0122, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225348753867856e-05, + "loss": 4.0069, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.9986, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9928, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 4.0095, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191821342629505e-05, + "loss": 3.9936, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.9999, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175049447608465e-05, + "loss": 3.9953, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166663500097945e-05, + "loss": 3.9797, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158277552587424e-05, + "loss": 3.9833, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 3.9812, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714152203637012e-05, + "loss": 3.9985, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71331360888596e-05, + "loss": 3.9863, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712475014134908e-05, + "loss": 3.9881, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711636419383856e-05, + "loss": 3.9854, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9856, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709960867762125e-05, + "loss": 4.0006, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9796, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708283678260021e-05, + "loss": 3.9789, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707446721389342e-05, + "loss": 3.9779, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9984, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9708, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9898, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040939802655074e-05, + "loss": 3.9693, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9821, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9853, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.973, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700741239141672e-05, + "loss": 3.9799, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9751, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.9561, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.9771, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697388498017837e-05, + "loss": 3.9765, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9693, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9662, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9721, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9545, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.9762, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9576, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9659, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9738, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9634, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.9733, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.9838, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.9699, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9782, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9602, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848144903931765e-05, + "loss": 3.9518, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9608, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.9745, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.964, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681461749269342e-05, + "loss": 3.9541, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.68062315451829e-05, + "loss": 3.9491, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.9516, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9493, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678109008145507e-05, + "loss": 3.958, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677270413394455e-05, + "loss": 3.9665, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676433456523776e-05, + "loss": 3.9645, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.9548, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9509, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.9458, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730807153999415e-05, + "loss": 3.9533, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.9496, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9521, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9451, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697279742761064e-05, + "loss": 3.9548, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688893795250544e-05, + "loss": 3.9552, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680507847740024e-05, + "loss": 3.9563, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672121900229504e-05, + "loss": 3.9547, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666375233152271e-05, + "loss": 3.9583, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665536638401219e-05, + "loss": 3.9521, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664698043650167e-05, + "loss": 3.9466, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663859448899115e-05, + "loss": 3.9645, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663022492028437e-05, + "loss": 3.9411, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662183897277385e-05, + "loss": 3.9634, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661345302526333e-05, + "loss": 3.9396, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660506707775281e-05, + "loss": 3.935, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659669750904602e-05, + "loss": 3.9424, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65883115615355e-05, + "loss": 3.9519, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657992561402498e-05, + "loss": 3.9455, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9324, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6563170097807667e-05, + "loss": 3.9317, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554784150297146e-05, + "loss": 3.9399, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546398202786626e-05, + "loss": 3.9539, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538012255276106e-05, + "loss": 3.9392, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652964268656932e-05, + "loss": 3.9534, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212567390588e-05, + "loss": 3.9419, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651287079154828e-05, + "loss": 3.9429, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650448484403776e-05, + "loss": 3.9464, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649611527533097e-05, + "loss": 3.9335, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648772932782045e-05, + "loss": 3.9335, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647934338030993e-05, + "loss": 3.9399, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470957432799404e-05, + "loss": 3.9299, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646258786409262e-05, + "loss": 3.9364, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.64542019165821e-05, + "loss": 3.9368, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644581596907158e-05, + "loss": 3.9435, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643743002156106e-05, + "loss": 3.9267, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429060452854276e-05, + "loss": 3.9256, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420674505343756e-05, + "loss": 3.9516, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412288557833236e-05, + "loss": 3.9291, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640390261032271e-05, + "loss": 3.943, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395533041615925e-05, + "loss": 3.9359, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387147094105405e-05, + "loss": 3.9389, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637876114659488e-05, + "loss": 3.9306, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637037519908436e-05, + "loss": 3.9284, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6362005630377574e-05, + "loss": 3.9334, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353619682867054e-05, + "loss": 3.9332, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634523373535653e-05, + "loss": 3.9462, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336847787846014e-05, + "loss": 3.9401, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632847821913923e-05, + "loss": 3.9384, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632009227162871e-05, + "loss": 3.9318, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631170632411818e-05, + "loss": 3.9229, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630332037660766e-05, + "loss": 3.9331, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629495080790088e-05, + "loss": 3.9243, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628656486039035e-05, + "loss": 3.9271, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627817891287983e-05, + "loss": 3.9279, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626979296536931e-05, + "loss": 3.9191, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626142339666253e-05, + "loss": 3.9267, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6253037449152e-05, + "loss": 3.9211, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9574191570281982, + "eval_runtime": 569.6837, + "eval_samples_per_second": 669.83, + "eval_steps_per_second": 20.933, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624465150164148e-05, + "loss": 3.9284, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623626555413097e-05, + "loss": 3.9338, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622787960662045e-05, + "loss": 3.922, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621949365910993e-05, + "loss": 3.9224, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621110771159941e-05, + "loss": 3.9264, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620272176408889e-05, + "loss": 3.9065, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619433581657837e-05, + "loss": 3.9218, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618594986906785e-05, + "loss": 3.9193, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6177580300361056e-05, + "loss": 3.9113, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.6169194352850536e-05, + "loss": 3.9205, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.6160808405340016e-05, + "loss": 3.9275, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.6152438836633225e-05, + "loss": 3.9077, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.6144052889122705e-05, + "loss": 3.9105, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.6135666941612185e-05, + "loss": 3.9152, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.6127280994101665e-05, + "loss": 3.9149, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611891142539488e-05, + "loss": 3.9048, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611052547788436e-05, + "loss": 3.9052, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610213953037384e-05, + "loss": 3.907, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609375358286332e-05, + "loss": 3.9106, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.608538401415653e-05, + "loss": 3.9176, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607699806664601e-05, + "loss": 3.9081, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.606861211913549e-05, + "loss": 3.9199, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.606022617162497e-05, + "loss": 3.9148, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605185660291818e-05, + "loss": 3.9109, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604347065540766e-05, + "loss": 3.9086, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603508470789714e-05, + "loss": 3.9067, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602669876038662e-05, + "loss": 3.9156, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018329191679835e-05, + "loss": 3.9026, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009959622973044e-05, + "loss": 3.9102, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.6001573675462524e-05, + "loss": 3.8984, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.5993187727952004e-05, + "loss": 3.9013, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.5984801780441484e-05, + "loss": 3.915, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.5976415832930964e-05, + "loss": 3.9101, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.5968029885420443e-05, + "loss": 3.9047, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959643937909923e-05, + "loss": 3.8996, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.5951257990399403e-05, + "loss": 3.9091, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594288842169261e-05, + "loss": 3.8991, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593450247418209e-05, + "loss": 3.9079, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592611652667157e-05, + "loss": 3.8997, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591773057916105e-05, + "loss": 3.8856, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590936101045427e-05, + "loss": 3.8923, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590097506294375e-05, + "loss": 3.8897, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589258911543323e-05, + "loss": 3.9022, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588420316792271e-05, + "loss": 3.8926, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587583359921592e-05, + "loss": 3.895, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.58674476517054e-05, + "loss": 3.8925, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585906170419488e-05, + "loss": 3.8964, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585067575668436e-05, + "loss": 3.9082, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.5842306187977566e-05, + "loss": 3.8873, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.5833920240467046e-05, + "loss": 3.887, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.5825534292956526e-05, + "loss": 3.8925, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581716472424974e-05, + "loss": 3.9032, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580877877673922e-05, + "loss": 3.8826, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.58003928292287e-05, + "loss": 3.8962, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579200688171818e-05, + "loss": 3.8796, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.578362093420766e-05, + "loss": 3.8867, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.5775234986697135e-05, + "loss": 3.8978, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.5766849039186615e-05, + "loss": 3.8797, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.5758463091676095e-05, + "loss": 3.8978, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.575009352296931e-05, + "loss": 3.889, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.5741707575458784e-05, + "loss": 3.868, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.5733321627948264e-05, + "loss": 3.8844, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.5724935680437744e-05, + "loss": 3.8869, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571656611173096e-05, + "loss": 3.885, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570818016422044e-05, + "loss": 3.8784, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569979421670992e-05, + "loss": 3.8841, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.56914082691994e-05, + "loss": 3.868, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568303870049261e-05, + "loss": 3.8894, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567465275298209e-05, + "loss": 3.8704, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566626680547157e-05, + "loss": 3.8804, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565788085796105e-05, + "loss": 3.8867, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564951128925426e-05, + "loss": 3.8786, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564112534174374e-05, + "loss": 3.8857, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563273939423322e-05, + "loss": 3.8933, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.56243534467227e-05, + "loss": 3.887, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561598387801591e-05, + "loss": 3.8934, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560759793050539e-05, + "loss": 3.874, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559921198299487e-05, + "loss": 3.8699, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559082603548435e-05, + "loss": 3.873, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558245646677756e-05, + "loss": 3.8929, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557407051926704e-05, + "loss": 3.88, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556568457175652e-05, + "loss": 3.8679, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557298624246e-05, + "loss": 3.8639, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.554892905553921e-05, + "loss": 3.8711, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554054310802869e-05, + "loss": 3.868, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553215716051817e-05, + "loss": 3.8708, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552377121300765e-05, + "loss": 3.8805, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551540164430087e-05, + "loss": 3.8843, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550701569679035e-05, + "loss": 3.8711, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549862974927983e-05, + "loss": 3.8728, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549024380176931e-05, + "loss": 3.8612, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.5481874233062516e-05, + "loss": 3.8703, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.5473488285551996e-05, + "loss": 3.873, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.5465102338041476e-05, + "loss": 3.8703, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.5456716390530956e-05, + "loss": 3.8634, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.5448346821824165e-05, + "loss": 3.8758, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.5439960874313645e-05, + "loss": 3.8703, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.5431574926803125e-05, + "loss": 3.8829, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.5423188979292605e-05, + "loss": 3.8718, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541481941058582e-05, + "loss": 3.878, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.54064334630753e-05, + "loss": 3.8718, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539804751556478e-05, + "loss": 3.8667, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.538966156805426e-05, + "loss": 3.8837, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538129199934747e-05, + "loss": 3.8636, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.537290605183695e-05, + "loss": 3.8852, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536452010432643e-05, + "loss": 3.8589, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535613415681591e-05, + "loss": 3.8591, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.534776458810912e-05, + "loss": 3.8619, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.53393786405986e-05, + "loss": 3.8756, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.5331009071891814e-05, + "loss": 3.8666, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.5322623124381294e-05, + "loss": 3.8518, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.5314237176870774e-05, + "loss": 3.8502, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.5305851229360254e-05, + "loss": 3.8613, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.5297465281849734e-05, + "loss": 3.8788, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.5289079334339214e-05, + "loss": 3.8619, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.5280693386828694e-05, + "loss": 3.8774, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.5272307439318174e-05, + "loss": 3.8641, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526393787061138e-05, + "loss": 3.8675, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.525555192310086e-05, + "loss": 3.867, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.524716597559034e-05, + "loss": 3.8578, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.523879640688355e-05, + "loss": 3.8562, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523041045937303e-05, + "loss": 3.861, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522202451186251e-05, + "loss": 3.8554, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.5213638564352e-05, + "loss": 3.859, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520525261684148e-05, + "loss": 3.8629, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519686666933096e-05, + "loss": 3.8624, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518848072182044e-05, + "loss": 3.8527, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.518011115311365e-05, + "loss": 3.8511, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.517172520560313e-05, + "loss": 3.8732, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516333925809261e-05, + "loss": 3.8536, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515495331058209e-05, + "loss": 3.8677, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514656736307156e-05, + "loss": 3.8605, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513818141556104e-05, + "loss": 3.863, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.512979546805052e-05, + "loss": 3.8543, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512140952054e-05, + "loss": 3.8583, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511303995183322e-05, + "loss": 3.8575, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.5104654004322697e-05, + "loss": 3.8614, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.5096268056812177e-05, + "loss": 3.8746, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.5087882109301657e-05, + "loss": 3.8609, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.5079512540594866e-05, + "loss": 3.8671, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.5071126593084346e-05, + "loss": 3.8634, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.5062740645573826e-05, + "loss": 3.8491, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.5054354698063305e-05, + "loss": 3.8581, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.5045968750552785e-05, + "loss": 3.8502, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.5037582803042265e-05, + "loss": 3.8533, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.5029196855531745e-05, + "loss": 3.8538, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.5020827286824954e-05, + "loss": 3.8508, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.5012441339314434e-05, + "loss": 3.8488, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.5004055391803914e-05, + "loss": 3.8523, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9163527488708496, + "eval_runtime": 553.4248, + "eval_samples_per_second": 689.508, + "eval_steps_per_second": 21.548, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.499568582309713e-05, + "loss": 3.8584, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498729987558661e-05, + "loss": 3.8584, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497891392807609e-05, + "loss": 3.853, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497052798056557e-05, + "loss": 3.8496, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496214203305505e-05, + "loss": 3.8596, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495375608554453e-05, + "loss": 3.8357, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494538651683774e-05, + "loss": 3.8525, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493700056932722e-05, + "loss": 3.844, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.49286146218167e-05, + "loss": 3.8429, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492022867430618e-05, + "loss": 3.8501, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491184272679566e-05, + "loss": 3.8533, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490345677928514e-05, + "loss": 3.8379, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489507083177462e-05, + "loss": 3.8427, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.48866848842641e-05, + "loss": 3.8429, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878315315557315e-05, + "loss": 3.848, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869929368046795e-05, + "loss": 3.8314, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861559799340004e-05, + "loss": 3.8365, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853173851829484e-05, + "loss": 3.8372, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844787904318964e-05, + "loss": 3.8407, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836401956808444e-05, + "loss": 3.8525, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4828016009297924e-05, + "loss": 3.8405, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.48196300617874e-05, + "loss": 3.853, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481124411427688e-05, + "loss": 3.8469, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480285816676636e-05, + "loss": 3.8448, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479448859805957e-05, + "loss": 3.8389, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478610265054905e-05, + "loss": 3.8393, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477771670303853e-05, + "loss": 3.8484, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476933075552801e-05, + "loss": 3.8377, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476096118682122e-05, + "loss": 3.839, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.47525752393107e-05, + "loss": 3.8375, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474418929180018e-05, + "loss": 3.8285, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473580334428966e-05, + "loss": 3.8445, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472743377558287e-05, + "loss": 3.8482, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471904782807235e-05, + "loss": 3.8386, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471066188056183e-05, + "loss": 3.8331, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470227593305131e-05, + "loss": 3.841, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469388998554079e-05, + "loss": 3.8386, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468550403803028e-05, + "loss": 3.8367, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467711809051976e-05, + "loss": 3.8332, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466873214300924e-05, + "loss": 3.821, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660362574302446e-05, + "loss": 3.828, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651976626791926e-05, + "loss": 3.8218, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643590679281406e-05, + "loss": 3.8386, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635204731770886e-05, + "loss": 3.828, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626835163064095e-05, + "loss": 3.8286, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618449215553575e-05, + "loss": 3.8285, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610063268043055e-05, + "loss": 3.8303, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601677320532535e-05, + "loss": 3.8446, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593307751825744e-05, + "loss": 3.8245, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584921804315224e-05, + "loss": 3.8214, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457653585680471e-05, + "loss": 3.8316, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456816628809792e-05, + "loss": 3.8338, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.45597803405874e-05, + "loss": 3.8243, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455139439307688e-05, + "loss": 3.8271, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454300844556636e-05, + "loss": 3.8209, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453463887685957e-05, + "loss": 3.8242, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452625292934905e-05, + "loss": 3.833, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451786698183853e-05, + "loss": 3.8148, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450948103432801e-05, + "loss": 3.8361, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450111146562122e-05, + "loss": 3.8238, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44927255181107e-05, + "loss": 3.8085, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448433957060018e-05, + "loss": 3.8199, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475953623089664e-05, + "loss": 3.8239, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446758405438287e-05, + "loss": 3.8292, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445919810687235e-05, + "loss": 3.815, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445081215936183e-05, + "loss": 3.8226, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444242621185131e-05, + "loss": 3.8018, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443405664314452e-05, + "loss": 3.8277, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425670695634e-05, + "loss": 3.8114, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441728474812348e-05, + "loss": 3.8177, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440889880061296e-05, + "loss": 3.8244, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440051285310244e-05, + "loss": 3.8161, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439212690559192e-05, + "loss": 3.8213, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.43837409580814e-05, + "loss": 3.8313, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437535501057088e-05, + "loss": 3.8262, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669854418641e-05, + "loss": 3.8306, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435859949435358e-05, + "loss": 3.8154, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435021354684306e-05, + "loss": 3.8079, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434182759933253e-05, + "loss": 3.8163, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433345803062575e-05, + "loss": 3.8301, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325088461918956e-05, + "loss": 3.8191, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316702514408436e-05, + "loss": 3.8113, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308316566897916e-05, + "loss": 3.8019, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299930619387396e-05, + "loss": 3.811, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291544671876876e-05, + "loss": 3.8048, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283158724366356e-05, + "loss": 3.8156, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274772776855836e-05, + "loss": 3.8163, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266386829345316e-05, + "loss": 3.8265, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425801726063853e-05, + "loss": 3.8124, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249631313128005e-05, + "loss": 3.8144, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241245365617485e-05, + "loss": 3.8021, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.42328757969107e-05, + "loss": 3.8115, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422448984940018e-05, + "loss": 3.8146, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216103901889654e-05, + "loss": 3.8088, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207717954379134e-05, + "loss": 3.8041, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199332006868614e-05, + "loss": 3.8186, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190946059358094e-05, + "loss": 3.8081, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182560111847573e-05, + "loss": 3.8302, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417419054314079e-05, + "loss": 3.8091, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416580459563027e-05, + "loss": 3.8189, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415741864811975e-05, + "loss": 3.8107, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414903270060923e-05, + "loss": 3.8092, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414064675309871e-05, + "loss": 3.8263, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413226080558819e-05, + "loss": 3.806, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412387485807767e-05, + "loss": 3.8229, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411548891056715e-05, + "loss": 3.8043, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410711934186036e-05, + "loss": 3.8032, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409873339434984e-05, + "loss": 3.8017, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409034744683932e-05, + "loss": 3.8137, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408197787813253e-05, + "loss": 3.8113, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407359193062201e-05, + "loss": 3.8003, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065205983111494e-05, + "loss": 3.7903, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056820035600974e-05, + "loss": 3.8049, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404845046689418e-05, + "loss": 3.8206, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404006451938366e-05, + "loss": 3.8023, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403167857187314e-05, + "loss": 3.8213, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402329262436262e-05, + "loss": 3.8081, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149066768521e-05, + "loss": 3.8107, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400652072934158e-05, + "loss": 3.812, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399815116063479e-05, + "loss": 3.8016, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398976521312427e-05, + "loss": 3.7984, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398137926561375e-05, + "loss": 3.8031, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397299331810323e-05, + "loss": 3.8029, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396460737059271e-05, + "loss": 3.8045, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395622142308219e-05, + "loss": 3.8056, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394785185437541e-05, + "loss": 3.8061, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393946590686489e-05, + "loss": 3.7964, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393107995935437e-05, + "loss": 3.7982, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392269401184384e-05, + "loss": 3.8138, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914324443137056e-05, + "loss": 3.7992, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905938495626536e-05, + "loss": 3.8135, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897552548116016e-05, + "loss": 3.8081, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388916660060549e-05, + "loss": 3.8055, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388078065309497e-05, + "loss": 3.8015, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387239470558445e-05, + "loss": 3.803, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386400875807393e-05, + "loss": 3.8037, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855639189367145e-05, + "loss": 3.8037, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847253241856625e-05, + "loss": 3.819, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838867294346105e-05, + "loss": 3.8097, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830481346835585e-05, + "loss": 3.8117, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822111778128794e-05, + "loss": 3.8092, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813725830618274e-05, + "loss": 3.7981, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805339883107754e-05, + "loss": 3.8029, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796953935597234e-05, + "loss": 3.7952, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788567988086714e-05, + "loss": 3.799, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780182040576194e-05, + "loss": 3.8019, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.37718124718694e-05, + "loss": 3.7944, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376342652435888e-05, + "loss": 3.7909, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375504057684836e-05, + "loss": 3.8001, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.89127779006958, + "eval_runtime": 565.2585, + "eval_samples_per_second": 675.073, + "eval_steps_per_second": 21.097, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.374665462933785e-05, + "loss": 3.8091, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373826868182733e-05, + "loss": 3.8003, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372988273431681e-05, + "loss": 3.8, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372149678680629e-05, + "loss": 3.7992, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.37131272180995e-05, + "loss": 3.8003, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370474127058898e-05, + "loss": 3.787, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369635532307846e-05, + "loss": 3.7983, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368796937556794e-05, + "loss": 3.7879, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367959980686115e-05, + "loss": 3.7951, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367121385935063e-05, + "loss": 3.7968, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366282791184011e-05, + "loss": 3.7984, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365444196432959e-05, + "loss": 3.7833, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364605601681907e-05, + "loss": 3.7915, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363768644811228e-05, + "loss": 3.7897, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362930050060176e-05, + "loss": 3.7944, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362091455309124e-05, + "loss": 3.7805, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361252860558072e-05, + "loss": 3.7817, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.36041426580702e-05, + "loss": 3.7863, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359577308936341e-05, + "loss": 3.7897, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358738714185289e-05, + "loss": 3.8009, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357900119434237e-05, + "loss": 3.7863, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.3570615246831845e-05, + "loss": 3.8038, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562229299321325e-05, + "loss": 3.793, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553843351810805e-05, + "loss": 3.7956, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354547378310402e-05, + "loss": 3.7864, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.35370878355935e-05, + "loss": 3.7886, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352870188808298e-05, + "loss": 3.7983, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.352031594057246e-05, + "loss": 3.7853, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351192999306194e-05, + "loss": 3.79, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350356042435515e-05, + "loss": 3.7852, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349517447684463e-05, + "loss": 3.7764, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348678852933411e-05, + "loss": 3.7969, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347840258182359e-05, + "loss": 3.7948, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347001663431307e-05, + "loss": 3.792, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346164706560628e-05, + "loss": 3.7797, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345326111809576e-05, + "loss": 3.7934, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344487517058524e-05, + "loss": 3.7831, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436489223074726e-05, + "loss": 3.7908, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3428103275564206e-05, + "loss": 3.784, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.3419733706857415e-05, + "loss": 3.7708, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411347759346895e-05, + "loss": 3.7792, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402961811836375e-05, + "loss": 3.769, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394575864325854e-05, + "loss": 3.7931, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3386189916815334e-05, + "loss": 3.7781, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377803969304814e-05, + "loss": 3.7754, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369434400598024e-05, + "loss": 3.7823, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361048453087503e-05, + "loss": 3.7818, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352662505576983e-05, + "loss": 3.7932, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334427655806646e-05, + "loss": 3.7715, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333590698935968e-05, + "loss": 3.774, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332752104184916e-05, + "loss": 3.7832, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331913509433864e-05, + "loss": 3.7806, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331074914682812e-05, + "loss": 3.7757, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7747, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329399363061081e-05, + "loss": 3.7716, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328560768310029e-05, + "loss": 3.7766, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327722173558977e-05, + "loss": 3.7787, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.7731, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.7867, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325206389305821e-05, + "loss": 3.7737, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324367794554768e-05, + "loss": 3.7649, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323529199803716e-05, + "loss": 3.7709, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322692242933038e-05, + "loss": 3.7703, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321855286062359e-05, + "loss": 3.7891, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321016691311307e-05, + "loss": 3.7655, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320178096560255e-05, + "loss": 3.774, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319339501809203e-05, + "loss": 3.7582, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318502544938524e-05, + "loss": 3.775, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317663950187472e-05, + "loss": 3.765, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.31682535543642e-05, + "loss": 3.7671, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.7781, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315149803814689e-05, + "loss": 3.7712, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314311209063637e-05, + "loss": 3.7736, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313472614312585e-05, + "loss": 3.7836, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.7771, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311795424810481e-05, + "loss": 3.7859, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310956830059429e-05, + "loss": 3.7679, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.7617, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7669, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308442683686646e-05, + "loss": 3.7833, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307604088935594e-05, + "loss": 3.7708, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306765494184542e-05, + "loss": 3.7653, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.30592689943349e-05, + "loss": 3.7558, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305088304682438e-05, + "loss": 3.7671, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304251347811759e-05, + "loss": 3.7552, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303412753060707e-05, + "loss": 3.7692, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302574158309655e-05, + "loss": 3.7709, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3017372014389764e-05, + "loss": 3.7762, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3008986066879244e-05, + "loss": 3.7672, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.3000600119368724e-05, + "loss": 3.768, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.2992214171858204e-05, + "loss": 3.7552, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298384460315141e-05, + "loss": 3.7645, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297545865564089e-05, + "loss": 3.7664, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296707270813037e-05, + "loss": 3.7636, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295868676061985e-05, + "loss": 3.7574, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295030081310933e-05, + "loss": 3.7737, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294193124440254e-05, + "loss": 3.7601, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293354529689202e-05, + "loss": 3.7852, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.29251593493815e-05, + "loss": 3.7583, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291677340187099e-05, + "loss": 3.775, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290838745436047e-05, + "loss": 3.7635, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290001788565368e-05, + "loss": 3.7642, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289163193814316e-05, + "loss": 3.7826, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288324599063264e-05, + "loss": 3.7575, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287486004312212e-05, + "loss": 3.7784, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.28664740956116e-05, + "loss": 3.7588, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285810452690481e-05, + "loss": 3.7586, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284971857939429e-05, + "loss": 3.756, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284133263188377e-05, + "loss": 3.7692, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.2832946684373247e-05, + "loss": 3.7682, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.2824560736862727e-05, + "loss": 3.7595, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281619116815594e-05, + "loss": 3.7414, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280780522064542e-05, + "loss": 3.7607, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.27994192731349e-05, + "loss": 3.7744, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279103332562438e-05, + "loss": 3.7657, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278264737811386e-05, + "loss": 3.7709, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277426143060334e-05, + "loss": 3.7642, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276589186189655e-05, + "loss": 3.7655, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275750591438603e-05, + "loss": 3.7692, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274911996687551e-05, + "loss": 3.7606, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274073401936499e-05, + "loss": 3.752, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.27323644506582e-05, + "loss": 3.7574, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272397850314768e-05, + "loss": 3.7562, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.271559255563716e-05, + "loss": 3.7604, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270720660812664e-05, + "loss": 3.7588, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269882066061612e-05, + "loss": 3.7613, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690451091909336e-05, + "loss": 3.7545, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.2682065144398816e-05, + "loss": 3.7522, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267367919688829e-05, + "loss": 3.7671, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266529324937777e-05, + "loss": 3.7565, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265690730186725e-05, + "loss": 3.768, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.2648537733160465e-05, + "loss": 3.7677, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264015178564994e-05, + "loss": 3.7608, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263176583813942e-05, + "loss": 3.7598, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.26233798906289e-05, + "loss": 3.7594, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261499394311838e-05, + "loss": 3.757, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.2606624374411594e-05, + "loss": 3.758, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.2598238426901074e-05, + "loss": 3.7742, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.2589852479390554e-05, + "loss": 3.7703, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.2581466531880034e-05, + "loss": 3.7627, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257309696317324e-05, + "loss": 3.7647, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256471101566272e-05, + "loss": 3.7567, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.25563250681522e-05, + "loss": 3.7611, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254793912064168e-05, + "loss": 3.7551, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253956955193489e-05, + "loss": 3.7484, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253118360442437e-05, + "loss": 3.7619, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252279765691385e-05, + "loss": 3.753, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251441170940333e-05, + "loss": 3.7476, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250604214069655e-05, + "loss": 3.7553, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8747153282165527, + "eval_runtime": 566.4256, + "eval_samples_per_second": 673.683, + "eval_steps_per_second": 21.053, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249765619318603e-05, + "loss": 3.7664, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248927024567551e-05, + "loss": 3.7575, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248088429816499e-05, + "loss": 3.7565, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247249835065447e-05, + "loss": 3.7585, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464128781947676e-05, + "loss": 3.7576, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455742834437156e-05, + "loss": 3.7472, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447356886926636e-05, + "loss": 3.7551, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438970939416116e-05, + "loss": 3.7452, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430584991905596e-05, + "loss": 3.7504, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422215423198805e-05, + "loss": 3.7544, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413829475688285e-05, + "loss": 3.7601, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405443528177765e-05, + "loss": 3.7382, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239705758066725e-05, + "loss": 3.7535, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238868801196046e-05, + "loss": 3.7483, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238030206444994e-05, + "loss": 3.7565, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237191611693942e-05, + "loss": 3.7365, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.23635301694289e-05, + "loss": 3.741, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235516060072211e-05, + "loss": 3.7475, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234677465321159e-05, + "loss": 3.7442, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233838870570107e-05, + "loss": 3.7564, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233000275819055e-05, + "loss": 3.747, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232161681068003e-05, + "loss": 3.7597, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231323086316951e-05, + "loss": 3.7516, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230486129446272e-05, + "loss": 3.7529, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296475346952206e-05, + "loss": 3.7445, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288089399441686e-05, + "loss": 3.7484, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279719830734895e-05, + "loss": 3.7564, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271333883224375e-05, + "loss": 3.7487, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262947935713855e-05, + "loss": 3.7446, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254561988203335e-05, + "loss": 3.7478, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246176040692814e-05, + "loss": 3.737, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237790093182294e-05, + "loss": 3.7521, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229420524475504e-05, + "loss": 3.7547, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221034576964983e-05, + "loss": 3.7501, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212648629454463e-05, + "loss": 3.7394, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204262681943943e-05, + "loss": 3.7529, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219589311323716e-05, + "loss": 3.7412, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218750716572664e-05, + "loss": 3.7491, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217912121821612e-05, + "loss": 3.7463, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.21707352707056e-05, + "loss": 3.7326, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216234932319507e-05, + "loss": 3.7339, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215396337568455e-05, + "loss": 3.7271, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214559380697777e-05, + "loss": 3.7568, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213720785946725e-05, + "loss": 3.7359, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212882191195672e-05, + "loss": 3.7327, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.21204359644462e-05, + "loss": 3.7458, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211206639573942e-05, + "loss": 3.7397, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.21036804482289e-05, + "loss": 3.7492, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209529450071838e-05, + "loss": 3.736, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208690855320786e-05, + "loss": 3.7381, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207852260569734e-05, + "loss": 3.7394, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070153036990546e-05, + "loss": 3.742, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061767089480026e-05, + "loss": 3.7381, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053381141969506e-05, + "loss": 3.7292, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2044995194458986e-05, + "loss": 3.7342, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036609246948466e-05, + "loss": 3.742, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028239678241675e-05, + "loss": 3.7376, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019853730731155e-05, + "loss": 3.7323, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011467783220635e-05, + "loss": 3.7459, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003081835710115e-05, + "loss": 3.7352, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994695888199595e-05, + "loss": 3.7245, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986309940689075e-05, + "loss": 3.7296, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197794037198229e-05, + "loss": 3.7314, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196955442447177e-05, + "loss": 3.7507, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196116847696125e-05, + "loss": 3.7279, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195278252945073e-05, + "loss": 3.7325, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194441296074394e-05, + "loss": 3.7191, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193602701323342e-05, + "loss": 3.7363, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.19276410657229e-05, + "loss": 3.7275, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191925511821238e-05, + "loss": 3.7288, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191086917070186e-05, + "loss": 3.7374, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190249960199507e-05, + "loss": 3.732, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189411365448455e-05, + "loss": 3.7379, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188572770697403e-05, + "loss": 3.743, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877341759463515e-05, + "loss": 3.7384, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868955811952995e-05, + "loss": 3.7453, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860586243246204e-05, + "loss": 3.736, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1852200295735684e-05, + "loss": 3.7218, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843814348225164e-05, + "loss": 3.7288, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835428400714644e-05, + "loss": 3.7389, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182705883200785e-05, + "loss": 3.7378, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181867288449733e-05, + "loss": 3.7294, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181028693698681e-05, + "loss": 3.7127, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180190098947629e-05, + "loss": 3.7319, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179351504196577e-05, + "loss": 3.717, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178514547325898e-05, + "loss": 3.7328, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177675952574847e-05, + "loss": 3.7302, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176837357823795e-05, + "loss": 3.7382, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175998763072743e-05, + "loss": 3.7288, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175161806202064e-05, + "loss": 3.729, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174323211451012e-05, + "loss": 3.7202, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.17348461669996e-05, + "loss": 3.7313, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172646021948908e-05, + "loss": 3.7243, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171809065078229e-05, + "loss": 3.7284, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170970470327177e-05, + "loss": 3.7197, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170131875576125e-05, + "loss": 3.732, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169293280825073e-05, + "loss": 3.7252, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684563239543936e-05, + "loss": 3.7507, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167617729203342e-05, + "loss": 3.7224, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.16677913445229e-05, + "loss": 3.7387, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165940539701238e-05, + "loss": 3.7276, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165103582830559e-05, + "loss": 3.7249, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164264988079507e-05, + "loss": 3.7443, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163426393328455e-05, + "loss": 3.7241, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625877985774025e-05, + "loss": 3.7386, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161750841706724e-05, + "loss": 3.7252, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160912246955672e-05, + "loss": 3.7166, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.16007365220462e-05, + "loss": 3.7183, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592350574535674e-05, + "loss": 3.7312, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158396462702516e-05, + "loss": 3.73, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575595058318376e-05, + "loss": 3.7264, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567209110807856e-05, + "loss": 3.7012, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155882316329733e-05, + "loss": 3.7236, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155043721578681e-05, + "loss": 3.7375, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154205126827629e-05, + "loss": 3.7261, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.15336816995695e-05, + "loss": 3.734, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152529575205898e-05, + "loss": 3.7288, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151690980454846e-05, + "loss": 3.7291, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150852385703794e-05, + "loss": 3.7308, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150013790952742e-05, + "loss": 3.7239, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149176834082063e-05, + "loss": 3.7143, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483382393310114e-05, + "loss": 3.7199, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474996445799594e-05, + "loss": 3.7219, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466610498289074e-05, + "loss": 3.7223, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145824092958228e-05, + "loss": 3.7235, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144985498207176e-05, + "loss": 3.7263, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144146903456124e-05, + "loss": 3.7186, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143308308705072e-05, + "loss": 3.7168, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.14246971395402e-05, + "loss": 3.7304, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141632757083341e-05, + "loss": 3.7184, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140794162332289e-05, + "loss": 3.7323, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139955567581237e-05, + "loss": 3.7295, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139116972830185e-05, + "loss": 3.7248, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138280015959507e-05, + "loss": 3.7239, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137441421208455e-05, + "loss": 3.7256, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136602826457403e-05, + "loss": 3.7196, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135764231706351e-05, + "loss": 3.7219, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349272748356717e-05, + "loss": 3.7387, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340886800846197e-05, + "loss": 3.7318, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332500853335676e-05, + "loss": 3.7301, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324114905825156e-05, + "loss": 3.7294, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315745337118366e-05, + "loss": 3.7178, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307359389607845e-05, + "loss": 3.7233, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298973442097325e-05, + "loss": 3.7204, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290587494586805e-05, + "loss": 3.7116, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128221792588002e-05, + "loss": 3.7299, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.12738319783695e-05, + "loss": 3.7159, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126544603085898e-05, + "loss": 3.711, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125706008334846e-05, + "loss": 3.7228, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.864755153656006, + "eval_runtime": 566.8215, + "eval_samples_per_second": 673.212, + "eval_steps_per_second": 21.038, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.124869051464167e-05, + "loss": 3.7301, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.124030456713115e-05, + "loss": 3.7198, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123191861962063e-05, + "loss": 3.7272, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122353267211011e-05, + "loss": 3.7218, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121516310340332e-05, + "loss": 3.7206, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.12067771558928e-05, + "loss": 3.7153, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119839120838228e-05, + "loss": 3.7187, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119000526087176e-05, + "loss": 3.7106, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118163569216497e-05, + "loss": 3.7164, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.1173249744654455e-05, + "loss": 3.7132, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.1164863797143935e-05, + "loss": 3.7262, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156477849633415e-05, + "loss": 3.7071, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.1148108280926624e-05, + "loss": 3.7161, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.1139722333416104e-05, + "loss": 3.7089, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.1131336385905584e-05, + "loss": 3.7231, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.1122950438395064e-05, + "loss": 3.7033, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111458086968827e-05, + "loss": 3.7057, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110619492217775e-05, + "loss": 3.7125, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109780897466723e-05, + "loss": 3.7087, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108942302715671e-05, + "loss": 3.7216, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108105345844992e-05, + "loss": 3.7118, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107266751093941e-05, + "loss": 3.7276, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106428156342889e-05, + "loss": 3.7151, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105589561591837e-05, + "loss": 3.7199, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104750966840785e-05, + "loss": 3.7134, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103914009970106e-05, + "loss": 3.7114, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103075415219054e-05, + "loss": 3.7185, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102236820468002e-05, + "loss": 3.7152, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.10139822571695e-05, + "loss": 3.7136, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005612688462706e-05, + "loss": 3.7123, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997226740952186e-05, + "loss": 3.7009, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0988840793441666e-05, + "loss": 3.7141, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.0980454845931146e-05, + "loss": 3.7227, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097208527722436e-05, + "loss": 3.7147, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096369932971384e-05, + "loss": 3.7051, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095531338220332e-05, + "loss": 3.7161, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.09469274346928e-05, + "loss": 3.7104, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093855786598601e-05, + "loss": 3.7135, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093017191847549e-05, + "loss": 3.7106, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092178597096497e-05, + "loss": 3.7022, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091340002345445e-05, + "loss": 3.7007, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090501407594393e-05, + "loss": 3.6939, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089664450723714e-05, + "loss": 3.7195, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088825855972662e-05, + "loss": 3.7054, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.08798726122161e-05, + "loss": 3.701, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087148666470558e-05, + "loss": 3.7134, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0863117095998796e-05, + "loss": 3.7063, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.0854731148488276e-05, + "loss": 3.7152, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.0846345200977756e-05, + "loss": 3.7025, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083795925346723e-05, + "loss": 3.7068, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082957330595671e-05, + "loss": 3.7039, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.0821203737249925e-05, + "loss": 3.7079, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.0812817789739405e-05, + "loss": 3.7071, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080443184222888e-05, + "loss": 3.6939, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079604589471836e-05, + "loss": 3.7047, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078765994720784e-05, + "loss": 3.7061, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.0779290378501054e-05, + "loss": 3.7034, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0770904430990534e-05, + "loss": 3.7009, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.0762518483480014e-05, + "loss": 3.7151, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.0754132535969494e-05, + "loss": 3.6946, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.0745746588458974e-05, + "loss": 3.6953, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.0737360640948453e-05, + "loss": 3.6949, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072899107224166e-05, + "loss": 3.7016, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072060512473114e-05, + "loss": 3.713, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071221917722062e-05, + "loss": 3.6954, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.07038332297101e-05, + "loss": 3.6988, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069546366100331e-05, + "loss": 3.6894, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068707771349279e-05, + "loss": 3.702, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067869176598227e-05, + "loss": 3.6933, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067030581847175e-05, + "loss": 3.6973, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066193624976497e-05, + "loss": 3.7035, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065355030225445e-05, + "loss": 3.6988, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064516435474393e-05, + "loss": 3.7024, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063677840723341e-05, + "loss": 3.7129, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062839245972289e-05, + "loss": 3.7037, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620022891016096e-05, + "loss": 3.7101, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.0611636943505576e-05, + "loss": 3.7041, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0603250995995056e-05, + "loss": 3.6909, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.0594865048484536e-05, + "loss": 3.6961, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0586495479777745e-05, + "loss": 3.7061, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578109532267225e-05, + "loss": 3.7071, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569723584756705e-05, + "loss": 3.6959, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056133763724619e-05, + "loss": 3.6836, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.05529680685394e-05, + "loss": 3.6951, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054458212102888e-05, + "loss": 3.687, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053619617351836e-05, + "loss": 3.7004, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052781022600784e-05, + "loss": 3.6979, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051944065730105e-05, + "loss": 3.7052, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051105470979053e-05, + "loss": 3.7022, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050266876228001e-05, + "loss": 3.6938, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049428281476949e-05, + "loss": 3.6914, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.04859132460627e-05, + "loss": 3.6976, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047752729855218e-05, + "loss": 3.6895, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046914135104166e-05, + "loss": 3.6966, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046075540353114e-05, + "loss": 3.6908, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0452369456020625e-05, + "loss": 3.6976, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.0443999887313835e-05, + "loss": 3.6951, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.0435613939803314e-05, + "loss": 3.7178, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.0427227992292794e-05, + "loss": 3.6879, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.0418842044782274e-05, + "loss": 3.7061, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.0410472476075483e-05, + "loss": 3.7011, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.0402086528564963e-05, + "loss": 3.6932, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039370058105444e-05, + "loss": 3.7059, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038531463354392e-05, + "loss": 3.6982, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037694506483713e-05, + "loss": 3.7041, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036855911732661e-05, + "loss": 3.6944, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036017316981609e-05, + "loss": 3.6859, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035178722230558e-05, + "loss": 3.6884, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034341765359879e-05, + "loss": 3.6991, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033503170608827e-05, + "loss": 3.6989, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032664575857775e-05, + "loss": 3.692, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031825981106723e-05, + "loss": 3.6699, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030987386355671e-05, + "loss": 3.6938, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030150429484992e-05, + "loss": 3.7055, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.02931183473394e-05, + "loss": 3.6932, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028473239982888e-05, + "loss": 3.7053, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027634645231836e-05, + "loss": 3.6987, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.0267976883611566e-05, + "loss": 3.6925, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.0259590936101046e-05, + "loss": 3.7027, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025120498859053e-05, + "loss": 3.6944, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024281904108001e-05, + "loss": 3.6863, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023444947237322e-05, + "loss": 3.6872, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.02260635248627e-05, + "loss": 3.6919, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021767757735218e-05, + "loss": 3.6907, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209291629841655e-05, + "loss": 3.688, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020092206113487e-05, + "loss": 3.699, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019253611362435e-05, + "loss": 3.6894, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018415016611383e-05, + "loss": 3.6828, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175764218603304e-05, + "loss": 3.7017, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016739464989652e-05, + "loss": 3.6846, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0159008702386e-05, + "loss": 3.7004, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.0150622754875486e-05, + "loss": 3.7029, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014223680736496e-05, + "loss": 3.6951, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013385085985444e-05, + "loss": 3.6915, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0125481291147655e-05, + "loss": 3.6923, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011709534363713e-05, + "loss": 3.6897, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010870939612661e-05, + "loss": 3.6924, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010032344861609e-05, + "loss": 3.7074, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091953879909304e-05, + "loss": 3.699, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008356793239878e-05, + "loss": 3.7017, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007518198488826e-05, + "loss": 3.6973, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006679603737774e-05, + "loss": 3.6875, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005842646867095e-05, + "loss": 3.6941, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.005004052116043e-05, + "loss": 3.6863, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004165457364991e-05, + "loss": 3.6842, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003326862613939e-05, + "loss": 3.6969, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002488267862887e-05, + "loss": 3.6882, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001651310992208e-05, + "loss": 3.6774, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000812716241156e-05, + "loss": 3.6953, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.8573412895202637, + "eval_runtime": 563.0454, + "eval_samples_per_second": 677.727, + "eval_steps_per_second": 21.179, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.999974121490104e-05, + "loss": 3.6974, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999135526739052e-05, + "loss": 3.696, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998296931988e-05, + "loss": 3.694, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997458337236948e-05, + "loss": 3.6904, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996621380366269e-05, + "loss": 3.6879, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995782785615218e-05, + "loss": 3.6846, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994944190864166e-05, + "loss": 3.6893, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994105596113114e-05, + "loss": 3.6801, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993268639242435e-05, + "loss": 3.6858, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992430044491383e-05, + "loss": 3.6857, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991591449740331e-05, + "loss": 3.6911, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990752854989279e-05, + "loss": 3.6781, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989914260238227e-05, + "loss": 3.6886, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890773033675476e-05, + "loss": 3.6759, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882387086164956e-05, + "loss": 3.6975, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874001138654436e-05, + "loss": 3.6693, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865615191143916e-05, + "loss": 3.6775, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985724562243713e-05, + "loss": 3.6835, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984885967492661e-05, + "loss": 3.6794, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984047372741609e-05, + "loss": 3.6915, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983208777990557e-05, + "loss": 3.6834, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982371821119878e-05, + "loss": 3.6978, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981533226368826e-05, + "loss": 3.6831, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980694631617774e-05, + "loss": 3.6889, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979856036866722e-05, + "loss": 3.6797, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.97901744211567e-05, + "loss": 3.6869, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978180485244991e-05, + "loss": 3.689, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977341890493939e-05, + "loss": 3.6856, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976503295742887e-05, + "loss": 3.6839, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975664700991835e-05, + "loss": 3.6825, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748277441211565e-05, + "loss": 3.671, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739891493701045e-05, + "loss": 3.6878, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731505546190525e-05, + "loss": 3.6945, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723119598680005e-05, + "loss": 3.6839, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714750029973214e-05, + "loss": 3.6765, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706364082462694e-05, + "loss": 3.6888, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9697978134952174e-05, + "loss": 3.6797, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689592187441654e-05, + "loss": 3.6839, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968122261873486e-05, + "loss": 3.682, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967283667122434e-05, + "loss": 3.6732, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966445072371382e-05, + "loss": 3.6735, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.96560647762033e-05, + "loss": 3.664, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964767882869278e-05, + "loss": 3.6911, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639309259986e-05, + "loss": 3.6768, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963092331247548e-05, + "loss": 3.672, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962253736496496e-05, + "loss": 3.6848, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961415141745444e-05, + "loss": 3.6728, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960578184874765e-05, + "loss": 3.687, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959739590123713e-05, + "loss": 3.676, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958900995372661e-05, + "loss": 3.6789, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958062400621609e-05, + "loss": 3.6736, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957223805870556e-05, + "loss": 3.6756, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956386848999878e-05, + "loss": 3.6817, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955548254248826e-05, + "loss": 3.6627, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547096594977737e-05, + "loss": 3.6753, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538710647467217e-05, + "loss": 3.6746, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953034107876043e-05, + "loss": 3.6758, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952195513124991e-05, + "loss": 3.6719, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513569183739386e-05, + "loss": 3.6858, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505183236228865e-05, + "loss": 3.6648, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949681366752208e-05, + "loss": 3.6717, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948842772001156e-05, + "loss": 3.6678, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480041772501035e-05, + "loss": 3.6735, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471655824990514e-05, + "loss": 3.6834, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946328625628373e-05, + "loss": 3.6688, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945490030877321e-05, + "loss": 3.6771, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944651436126269e-05, + "loss": 3.6533, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943812841375217e-05, + "loss": 3.6792, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429758845045386e-05, + "loss": 3.664, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942137289753486e-05, + "loss": 3.6699, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941298695002434e-05, + "loss": 3.6735, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940460100251382e-05, + "loss": 3.6724, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939623143380703e-05, + "loss": 3.6706, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938784548629651e-05, + "loss": 3.6873, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937945953878599e-05, + "loss": 3.6726, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937107359127547e-05, + "loss": 3.682, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936268764376495e-05, + "loss": 3.6787, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354318075058164e-05, + "loss": 3.6624, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345932127547644e-05, + "loss": 3.6646, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337546180037124e-05, + "loss": 3.6771, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329160232526604e-05, + "loss": 3.6835, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932079066381981e-05, + "loss": 3.6729, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931240471630929e-05, + "loss": 3.6521, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930401876879877e-05, + "loss": 3.6642, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929563282128825e-05, + "loss": 3.6607, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928724687377773e-05, + "loss": 3.6711, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927887730507094e-05, + "loss": 3.6707, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927049135756042e-05, + "loss": 3.6767, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621054100499e-05, + "loss": 3.6713, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925371946253938e-05, + "loss": 3.6672, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.92453498938326e-05, + "loss": 3.6679, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923696394632208e-05, + "loss": 3.6675, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922857799881156e-05, + "loss": 3.6592, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220208430104767e-05, + "loss": 3.6746, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211822482594247e-05, + "loss": 3.6648, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203436535083726e-05, + "loss": 3.6691, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195050587573206e-05, + "loss": 3.6669, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186681018866416e-05, + "loss": 3.6861, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178295071355896e-05, + "loss": 3.6611, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169909123845375e-05, + "loss": 3.6763, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161523176334855e-05, + "loss": 3.6768, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915315360762807e-05, + "loss": 3.6685, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914476766011755e-05, + "loss": 3.6755, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913638171260703e-05, + "loss": 3.6729, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912799576509651e-05, + "loss": 3.6771, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911962619638972e-05, + "loss": 3.6647, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.91112402488792e-05, + "loss": 3.6605, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910285430136868e-05, + "loss": 3.6631, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909446835385816e-05, + "loss": 3.6696, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908608240634764e-05, + "loss": 3.6691, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907771283764085e-05, + "loss": 3.6685, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906932689013033e-05, + "loss": 3.641, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906094094261981e-05, + "loss": 3.6695, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905255499510929e-05, + "loss": 3.6745, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044185426402505e-05, + "loss": 3.665, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035799478891985e-05, + "loss": 3.6775, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027413531381465e-05, + "loss": 3.6729, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019027583870945e-05, + "loss": 3.6626, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010658015164154e-05, + "loss": 3.6767, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002272067653634e-05, + "loss": 3.6691, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993886120143114e-05, + "loss": 3.6565, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985500172632594e-05, + "loss": 3.6621, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977114225122074e-05, + "loss": 3.667, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896874465641528e-05, + "loss": 3.6637, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896035870890476e-05, + "loss": 3.6617, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895197276139424e-05, + "loss": 3.668, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894358681388372e-05, + "loss": 3.6662, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893521724517694e-05, + "loss": 3.6551, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892683129766642e-05, + "loss": 3.6735, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.89184453501559e-05, + "loss": 3.6599, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891005940264538e-05, + "loss": 3.6727, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890168983393859e-05, + "loss": 3.6781, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889330388642807e-05, + "loss": 3.6625, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888491793891755e-05, + "loss": 3.665, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887653199140703e-05, + "loss": 3.6622, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868162422700236e-05, + "loss": 3.6629, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859776475189716e-05, + "loss": 3.6655, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851390527679196e-05, + "loss": 3.6805, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843004580168676e-05, + "loss": 3.6763, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883463501146189e-05, + "loss": 3.6692, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882624906395137e-05, + "loss": 3.6696, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881786311644085e-05, + "loss": 3.6655, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880947716893033e-05, + "loss": 3.6651, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880110760022354e-05, + "loss": 3.6632, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879272165271302e-05, + "loss": 3.6562, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.87843357052025e-05, + "loss": 3.6698, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877594975769198e-05, + "loss": 3.6652, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876758018898519e-05, + "loss": 3.6518, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875919424147467e-05, + "loss": 3.6645, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8536884784698486, + "eval_runtime": 575.8358, + "eval_samples_per_second": 662.673, + "eval_steps_per_second": 20.709, + "step": 686871 + }, + { + "epoch": 0.0, + "learning_rate": 3.875080829396415e-05, + "loss": 3.6717, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874242234645363e-05, + "loss": 3.6701, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873403639894311e-05, + "loss": 3.67, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872565045143259e-05, + "loss": 3.6617, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.8717280882725806e-05, + "loss": 3.6674, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.8708894935215286e-05, + "loss": 3.6603, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870050898770476e-05, + "loss": 3.658, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869212304019424e-05, + "loss": 3.6567, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683753471487455e-05, + "loss": 3.6561, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8675367523976935e-05, + "loss": 3.6637, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866698157646641e-05, + "loss": 3.6628, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865859562895589e-05, + "loss": 3.6517, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.8650226060249104e-05, + "loss": 3.6629, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8641840112738584e-05, + "loss": 3.6512, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8633454165228064e-05, + "loss": 3.6642, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8625068217717544e-05, + "loss": 3.643, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861669864901076e-05, + "loss": 3.6534, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860831270150023e-05, + "loss": 3.6587, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859992675398971e-05, + "loss": 3.6533, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859154080647919e-05, + "loss": 3.6674, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858317123777241e-05, + "loss": 3.6506, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857478529026188e-05, + "loss": 3.6768, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856639934275136e-05, + "loss": 3.6556, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855801339524084e-05, + "loss": 3.6633, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854962744773032e-05, + "loss": 3.6572, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854125787902354e-05, + "loss": 3.6632, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853287193151302e-05, + "loss": 3.6637, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.85244859840025e-05, + "loss": 3.6559, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851610003649198e-05, + "loss": 3.6582, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507730467785186e-05, + "loss": 3.6603, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.8499344520274666e-05, + "loss": 3.6388, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8490958572764146e-05, + "loss": 3.6633, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8482572625253626e-05, + "loss": 3.667, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8474203056546835e-05, + "loss": 3.6586, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.8465817109036315e-05, + "loss": 3.65, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8457431161525795e-05, + "loss": 3.6631, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.8449045214015275e-05, + "loss": 3.657, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.844067564530849e-05, + "loss": 3.6575, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843228969779797e-05, + "loss": 3.6564, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842390375028745e-05, + "loss": 3.646, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841551780277693e-05, + "loss": 3.6504, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840713185526641e-05, + "loss": 3.6376, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839874590775589e-05, + "loss": 3.6632, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.83903763390491e-05, + "loss": 3.6513, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838199039153858e-05, + "loss": 3.6435, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837360444402806e-05, + "loss": 3.6594, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836523487532127e-05, + "loss": 3.6477, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835684892781075e-05, + "loss": 3.6619, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834846298030023e-05, + "loss": 3.6552, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.834007703278971e-05, + "loss": 3.6505, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331691085279195e-05, + "loss": 3.651, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323305137768675e-05, + "loss": 3.6479, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8314935569061885e-05, + "loss": 3.6577, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8306549621551364e-05, + "loss": 3.6351, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.8298163674040844e-05, + "loss": 3.6536, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.8289777726530324e-05, + "loss": 3.6468, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.8281408157823533e-05, + "loss": 3.6522, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.8273022210313013e-05, + "loss": 3.6454, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8264636262802493e-05, + "loss": 3.6608, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825625031529197e-05, + "loss": 3.6459, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824786436778145e-05, + "loss": 3.6414, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823949479907466e-05, + "loss": 3.649, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823110885156415e-05, + "loss": 3.6416, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822272290405363e-05, + "loss": 3.6556, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821433695654311e-05, + "loss": 3.6509, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820596738783632e-05, + "loss": 3.6492, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.81975814403258e-05, + "loss": 3.631, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818919549281528e-05, + "loss": 3.6515, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818080954530476e-05, + "loss": 3.6408, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817243997659797e-05, + "loss": 3.6419, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816405402908745e-05, + "loss": 3.6485, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815566808157693e-05, + "loss": 3.6467, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8147298512870136e-05, + "loss": 3.6464, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.8138912565359616e-05, + "loss": 3.6633, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.8130526617849096e-05, + "loss": 3.6482, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812214067033858e-05, + "loss": 3.6573, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811377110163179e-05, + "loss": 3.6514, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810538515412127e-05, + "loss": 3.6424, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809699920661075e-05, + "loss": 3.638, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808861325910023e-05, + "loss": 3.6518, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808024369039344e-05, + "loss": 3.6539, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807185774288292e-05, + "loss": 3.6547, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.80634717953724e-05, + "loss": 3.6274, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805508584786188e-05, + "loss": 3.6375, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804671627915509e-05, + "loss": 3.6354, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803833033164457e-05, + "loss": 3.6461, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802994438413405e-05, + "loss": 3.6441, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8021558436623536e-05, + "loss": 3.6548, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.8013188867916746e-05, + "loss": 3.6468, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.8004802920406225e-05, + "loss": 3.6444, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.7996416972895705e-05, + "loss": 3.6404, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.7988031025385185e-05, + "loss": 3.6418, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797964507787466e-05, + "loss": 3.6331, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.7971275509167874e-05, + "loss": 3.6467, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.7962889561657354e-05, + "loss": 3.6426, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7954503614146834e-05, + "loss": 3.6418, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794611766663631e-05, + "loss": 3.6456, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.7937748097929523e-05, + "loss": 3.6584, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.7929362150419e-05, + "loss": 3.6394, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792097620290849e-05, + "loss": 3.652, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791259025539796e-05, + "loss": 3.6501, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790422068669118e-05, + "loss": 3.6465, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789583473918066e-05, + "loss": 3.6468, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788744879167013e-05, + "loss": 3.6514, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787906284415961e-05, + "loss": 3.6512, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787069327545283e-05, + "loss": 3.6395, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786230732794231e-05, + "loss": 3.6386, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785392138043178e-05, + "loss": 3.6368, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784553543292126e-05, + "loss": 3.6435, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783716586421448e-05, + "loss": 3.6483, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782877991670396e-05, + "loss": 3.6479, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782039396919344e-05, + "loss": 3.6208, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781200802168292e-05, + "loss": 3.6401, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780363845297613e-05, + "loss": 3.6475, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.7795252505465606e-05, + "loss": 3.6461, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.7786866557955086e-05, + "loss": 3.6552, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.7778480610444566e-05, + "loss": 3.6475, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777011104173778e-05, + "loss": 3.6406, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.7761725094227255e-05, + "loss": 3.6477, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.7753339146716735e-05, + "loss": 3.6441, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7744953199206215e-05, + "loss": 3.6386, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773658363049943e-05, + "loss": 3.6352, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772819768298891e-05, + "loss": 3.6451, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771981173547839e-05, + "loss": 3.6345, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771142578796787e-05, + "loss": 3.6409, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770305621926108e-05, + "loss": 3.6422, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769467027175056e-05, + "loss": 3.646, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768628432424004e-05, + "loss": 3.631, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767789837672952e-05, + "loss": 3.6471, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766952880802273e-05, + "loss": 3.635, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766114286051221e-05, + "loss": 3.6523, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765275691300169e-05, + "loss": 3.6551, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764437096549117e-05, + "loss": 3.6383, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.7636001396784384e-05, + "loss": 3.639, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7627615449273864e-05, + "loss": 3.6452, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7619229501763344e-05, + "loss": 3.6401, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7610843554252824e-05, + "loss": 3.6429, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760247398554603e-05, + "loss": 3.656, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759408803803551e-05, + "loss": 3.6469, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758570209052499e-05, + "loss": 3.6477, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757731614301447e-05, + "loss": 3.6484, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756894657430768e-05, + "loss": 3.6454, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756056062679716e-05, + "loss": 3.6384, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755217467928664e-05, + "loss": 3.638, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754378873177612e-05, + "loss": 3.6346, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753541916306934e-05, + "loss": 3.6476, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752703321555882e-05, + "loss": 3.6406, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.75186472680483e-05, + "loss": 3.6252, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751026132053778e-05, + "loss": 3.6436, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8506405353546143, + "eval_runtime": 320.4169, + "eval_samples_per_second": 1190.92, + "eval_steps_per_second": 37.217, + "step": 763190 + }, + { + "epoch": 1.0, + "learning_rate": 3.750189175183099e-05, + "loss": 3.6426, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749350580432047e-05, + "loss": 3.642, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748511985680995e-05, + "loss": 3.6462, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747673390929943e-05, + "loss": 3.6336, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.7468364340592636e-05, + "loss": 3.6455, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7459978393082116e-05, + "loss": 3.64, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.7451592445571596e-05, + "loss": 3.6345, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.7443206498061076e-05, + "loss": 3.6301, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743483692935429e-05, + "loss": 3.6326, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742645098184377e-05, + "loss": 3.6424, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741806503433325e-05, + "loss": 3.6372, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740967908682273e-05, + "loss": 3.6288, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740130951811594e-05, + "loss": 3.6395, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739292357060542e-05, + "loss": 3.6279, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.73845376230949e-05, + "loss": 3.6416, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737615167558438e-05, + "loss": 3.6189, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736776572807386e-05, + "loss": 3.6283, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735939615936707e-05, + "loss": 3.6383, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735101021185655e-05, + "loss": 3.6323, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734262426434603e-05, + "loss": 3.6413, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.7334254695639245e-05, + "loss": 3.6265, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.7325868748128725e-05, + "loss": 3.6538, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7317482800618205e-05, + "loss": 3.6315, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7309096853107685e-05, + "loss": 3.6451, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.7300727284400894e-05, + "loss": 3.6327, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.7292341336890374e-05, + "loss": 3.6435, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7283955389379854e-05, + "loss": 3.6394, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7275569441869334e-05, + "loss": 3.6332, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726719987316254e-05, + "loss": 3.6353, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725881392565202e-05, + "loss": 3.6356, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.72504279781415e-05, + "loss": 3.6189, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724204203063098e-05, + "loss": 3.6376, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723365608312046e-05, + "loss": 3.6431, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722528651441368e-05, + "loss": 3.6354, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721690056690316e-05, + "loss": 3.6271, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720851461939264e-05, + "loss": 3.6446, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.720012867188212e-05, + "loss": 3.6321, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719175910317533e-05, + "loss": 3.6389, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718337315566481e-05, + "loss": 3.6325, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.717498720815429e-05, + "loss": 3.6223, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716660126064377e-05, + "loss": 3.6294, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715823169193698e-05, + "loss": 3.6128, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714984574442646e-05, + "loss": 3.6389, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714145979691594e-05, + "loss": 3.6287, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713307384940542e-05, + "loss": 3.6221, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712470428069863e-05, + "loss": 3.6349, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711631833318811e-05, + "loss": 3.6264, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710793238567759e-05, + "loss": 3.6376, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709954643816707e-05, + "loss": 3.6318, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709117686946028e-05, + "loss": 3.6249, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708279092194976e-05, + "loss": 3.6306, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707440497443924e-05, + "loss": 3.6248, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706601902692872e-05, + "loss": 3.6303, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705764945822193e-05, + "loss": 3.6176, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704926351071141e-05, + "loss": 3.6284, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704087756320089e-05, + "loss": 3.625, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703249161569037e-05, + "loss": 3.6282, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.7024122046983586e-05, + "loss": 3.6242, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.7015736099473066e-05, + "loss": 3.6386, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.7007350151962546e-05, + "loss": 3.6228, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.6998964204452026e-05, + "loss": 3.6187, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.6990594635745235e-05, + "loss": 3.6263, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.6982208688234715e-05, + "loss": 3.6204, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.6973822740724195e-05, + "loss": 3.6337, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.6965436793213675e-05, + "loss": 3.6286, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.6957067224506884e-05, + "loss": 3.6248, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.6948681276996364e-05, + "loss": 3.6091, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.6940295329485844e-05, + "loss": 3.6289, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.6931909381975324e-05, + "loss": 3.6191, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692353981326854e-05, + "loss": 3.621, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691515386575802e-05, + "loss": 3.6209, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.69067679182475e-05, + "loss": 3.6277, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689838197073698e-05, + "loss": 3.6216, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.689001240203019e-05, + "loss": 3.6414, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688162645451967e-05, + "loss": 3.6297, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687324050700915e-05, + "loss": 3.6327, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686485455949863e-05, + "loss": 3.629, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685648499079184e-05, + "loss": 3.6191, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684809904328132e-05, + "loss": 3.6195, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.68397130957708e-05, + "loss": 3.6314, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683132714826028e-05, + "loss": 3.6292, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.6822957579553494e-05, + "loss": 3.6332, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814571632042974e-05, + "loss": 3.6058, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.6806185684532454e-05, + "loss": 3.6144, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679779973702193e-05, + "loss": 3.6116, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678943016831514e-05, + "loss": 3.6291, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678104422080462e-05, + "loss": 3.6208, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.67726582732941e-05, + "loss": 3.6314, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.6764272325783576e-05, + "loss": 3.6241, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675590275707679e-05, + "loss": 3.6244, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674751680956627e-05, + "loss": 3.6153, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673913086205575e-05, + "loss": 3.6203, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673074491454523e-05, + "loss": 3.6148, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672235896703471e-05, + "loss": 3.6217, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671398939832793e-05, + "loss": 3.6199, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.67056034508174e-05, + "loss": 3.6191, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669721750330688e-05, + "loss": 3.6259, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668883155579636e-05, + "loss": 3.635, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.6680461987089576e-05, + "loss": 3.6228, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667207603957905e-05, + "loss": 3.6299, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666369009206853e-05, + "loss": 3.6248, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665530414455801e-05, + "loss": 3.6268, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.6646934575851225e-05, + "loss": 3.6246, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.6638548628340705e-05, + "loss": 3.6315, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.6630162680830185e-05, + "loss": 3.6261, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.6621776733319665e-05, + "loss": 3.6193, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.6613407164612874e-05, + "loss": 3.6183, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.6605021217102354e-05, + "loss": 3.6126, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.6596635269591834e-05, + "loss": 3.6228, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6588249322081314e-05, + "loss": 3.6247, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657987975337452e-05, + "loss": 3.631, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.6571493805864e-05, + "loss": 3.5985, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656310785835348e-05, + "loss": 3.6125, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655472191084296e-05, + "loss": 3.6273, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654635234213617e-05, + "loss": 3.6257, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653796639462566e-05, + "loss": 3.6353, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652958044711514e-05, + "loss": 3.63, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652119449960462e-05, + "loss": 3.6126, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651282493089783e-05, + "loss": 3.6271, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650443898338731e-05, + "loss": 3.6228, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649605303587679e-05, + "loss": 3.6169, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648766708836627e-05, + "loss": 3.6129, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647929751965948e-05, + "loss": 3.6232, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.647091157214896e-05, + "loss": 3.618, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646252562463844e-05, + "loss": 3.6173, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645413967712792e-05, + "loss": 3.6151, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.6445770108421126e-05, + "loss": 3.6277, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643738416091061e-05, + "loss": 3.6089, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642899821340009e-05, + "loss": 3.6216, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642061226588957e-05, + "loss": 3.6189, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641224269718278e-05, + "loss": 3.6315, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640385674967226e-05, + "loss": 3.6313, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639547080216174e-05, + "loss": 3.618, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638708485465122e-05, + "loss": 3.6161, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.63786989071407e-05, + "loss": 3.6243, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637032933843391e-05, + "loss": 3.6182, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636194339092339e-05, + "loss": 3.6194, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635355744341287e-05, + "loss": 3.6328, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634517149590235e-05, + "loss": 3.6275, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.6336801927195566e-05, + "loss": 3.6284, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6328415979685046e-05, + "loss": 3.6262, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6320030032174526e-05, + "loss": 3.6255, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.6311644084664006e-05, + "loss": 3.6121, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.6303274515957215e-05, + "loss": 3.6179, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6294888568446695e-05, + "loss": 3.6164, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.6286502620936175e-05, + "loss": 3.624, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6278116673425655e-05, + "loss": 3.6194, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.6269747104718864e-05, + "loss": 3.6073, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6261361157208344e-05, + "loss": 3.6231, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.8503096103668213, + "eval_runtime": 316.3112, + "eval_samples_per_second": 1206.378, + "eval_steps_per_second": 37.7, + "step": 839509 + }, + { + "epoch": 0.0, + "learning_rate": 3.6252975209697824e-05, + "loss": 3.6272, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.6244589262187304e-05, + "loss": 3.6206, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.6236203314676784e-05, + "loss": 3.6237, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.6227817367166264e-05, + "loss": 3.6273, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621944779845948e-05, + "loss": 3.6357, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621106185094896e-05, + "loss": 3.6269, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620267590343844e-05, + "loss": 3.6288, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619428995592792e-05, + "loss": 3.6177, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618592038722113e-05, + "loss": 3.613, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617753443971061e-05, + "loss": 3.6194, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616914849220009e-05, + "loss": 3.6342, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.616076254468957e-05, + "loss": 3.6158, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615239297598278e-05, + "loss": 3.6225, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614400702847226e-05, + "loss": 3.6077, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.613562108096174e-05, + "loss": 3.6137, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612723513345122e-05, + "loss": 3.6042, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6118865564744433e-05, + "loss": 3.6201, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6110479617233913e-05, + "loss": 3.62, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610209366972339e-05, + "loss": 3.6132, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609370772221287e-05, + "loss": 3.6241, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608533815350608e-05, + "loss": 3.6318, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607695220599556e-05, + "loss": 3.6247, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606856625848504e-05, + "loss": 3.6189, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.606018031097452e-05, + "loss": 3.6191, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.6051794363464e-05, + "loss": 3.6339, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604342479475721e-05, + "loss": 3.6236, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603503884724669e-05, + "loss": 3.6114, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602665289973617e-05, + "loss": 3.6209, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601826695222565e-05, + "loss": 3.6146, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600989738351887e-05, + "loss": 3.6089, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600151143600835e-05, + "loss": 3.6222, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599312548849783e-05, + "loss": 3.6182, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598473954098731e-05, + "loss": 3.6253, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.5976369972280516e-05, + "loss": 3.6327, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.5967984024769996e-05, + "loss": 3.6158, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.5959598077259476e-05, + "loss": 3.6195, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595121212974895e-05, + "loss": 3.6228, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.5942842561042165e-05, + "loss": 3.6083, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.5934456613531645e-05, + "loss": 3.6156, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.5926070666021125e-05, + "loss": 3.606, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.5917684718510605e-05, + "loss": 3.6062, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590931514980382e-05, + "loss": 3.6121, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.59009292022933e-05, + "loss": 3.6254, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589254325478278e-05, + "loss": 3.6139, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.5884157307272254e-05, + "loss": 3.6082, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587578773856547e-05, + "loss": 3.6187, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586740179105495e-05, + "loss": 3.6163, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585901584354442e-05, + "loss": 3.6096, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.58506298960339e-05, + "loss": 3.5941, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584226032732712e-05, + "loss": 3.6232, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.58338743798166e-05, + "loss": 3.6206, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582548843230608e-05, + "loss": 3.6249, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581710248479556e-05, + "loss": 3.614, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.5808732916088774e-05, + "loss": 3.607, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.5800346968578254e-05, + "loss": 3.6064, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579196102106773e-05, + "loss": 3.6041, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578357507355721e-05, + "loss": 3.6258, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577520550485042e-05, + "loss": 3.5992, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.5766819557339897e-05, + "loss": 3.6343, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.5758433609829377e-05, + "loss": 3.6151, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.5750047662318856e-05, + "loss": 3.5945, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574167809361207e-05, + "loss": 3.6178, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573329214610155e-05, + "loss": 3.6096, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572490619859103e-05, + "loss": 3.5963, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571652025108051e-05, + "loss": 3.6108, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570815068237373e-05, + "loss": 3.621, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.56997647348632e-05, + "loss": 3.6055, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569137878735268e-05, + "loss": 3.6134, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568299283984216e-05, + "loss": 3.5891, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567462327113537e-05, + "loss": 3.6061, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566623732362485e-05, + "loss": 3.6108, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565785137611433e-05, + "loss": 3.6105, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564946542860381e-05, + "loss": 3.6119, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.564109585989702e-05, + "loss": 3.6063, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5632709912386506e-05, + "loss": 3.6261, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.5624323964875986e-05, + "loss": 3.6117, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.5615938017365466e-05, + "loss": 3.6175, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.5607568448658675e-05, + "loss": 3.6064, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.5599182501148155e-05, + "loss": 3.6046, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.5590796553637635e-05, + "loss": 3.6154, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.5582410606127115e-05, + "loss": 3.6126, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.5574024658616595e-05, + "loss": 3.6078, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.5565655089909804e-05, + "loss": 3.6139, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.5557269142399284e-05, + "loss": 3.6056, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.5548883194888764e-05, + "loss": 3.5948, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.5540497247378244e-05, + "loss": 3.6063, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553212767867146e-05, + "loss": 3.6151, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552374173116094e-05, + "loss": 3.5992, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551535578365042e-05, + "loss": 3.6092, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.55069698361399e-05, + "loss": 3.6088, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549860026743311e-05, + "loss": 3.5984, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.549021431992259e-05, + "loss": 3.6008, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548182837241207e-05, + "loss": 3.6017, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547344242490155e-05, + "loss": 3.618, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546507285619476e-05, + "loss": 3.6144, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545668690868424e-05, + "loss": 3.6144, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544830096117372e-05, + "loss": 3.6005, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.54399150136632e-05, + "loss": 3.6004, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543154544495641e-05, + "loss": 3.6101, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542315949744589e-05, + "loss": 3.6155, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541477354993537e-05, + "loss": 3.6129, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540638760242485e-05, + "loss": 3.6135, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539801803371806e-05, + "loss": 3.6044, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538963208620754e-05, + "loss": 3.6037, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538124613869702e-05, + "loss": 3.6148, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.53728601911865e-05, + "loss": 3.603, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536449062247971e-05, + "loss": 3.6032, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535610467496919e-05, + "loss": 3.6064, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534771872745867e-05, + "loss": 3.6059, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533933277994815e-05, + "loss": 3.6053, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533096321124136e-05, + "loss": 3.5961, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532257726373085e-05, + "loss": 3.5968, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531419131622033e-05, + "loss": 3.6123, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530580536870981e-05, + "loss": 3.609, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.5297435800003016e-05, + "loss": 3.6072, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.5289049852492496e-05, + "loss": 3.6129, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.5280663904981976e-05, + "loss": 3.6195, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5272277957471456e-05, + "loss": 3.6079, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.5263908388764665e-05, + "loss": 3.6053, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.5255522441254145e-05, + "loss": 3.5988, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.5247136493743625e-05, + "loss": 3.6036, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.5238750546233105e-05, + "loss": 3.6066, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5230380977526314e-05, + "loss": 3.6035, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.52219950300158e-05, + "loss": 3.5995, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521360908250528e-05, + "loss": 3.6061, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520522313499476e-05, + "loss": 3.606, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519685356628797e-05, + "loss": 3.6009, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518846761877745e-05, + "loss": 3.6075, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.518008167126693e-05, + "loss": 3.6056, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517169572375641e-05, + "loss": 3.6056, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516332615504962e-05, + "loss": 3.6076, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.51549402075391e-05, + "loss": 3.6187, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514655426002858e-05, + "loss": 3.5989, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.513816831251806e-05, + "loss": 3.6057, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512979874381127e-05, + "loss": 3.6058, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5121412796300754e-05, + "loss": 3.6023, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5113026848790234e-05, + "loss": 3.604, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5104640901279714e-05, + "loss": 3.6074, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509627133257292e-05, + "loss": 3.6174, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.50878853850624e-05, + "loss": 3.6153, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507949943755188e-05, + "loss": 3.6086, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.507111349004136e-05, + "loss": 3.6075, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.506274392133457e-05, + "loss": 3.6084, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505435797382405e-05, + "loss": 3.6035, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504597202631353e-05, + "loss": 3.5967, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503758607880301e-05, + "loss": 3.6057, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502921651009622e-05, + "loss": 3.5979, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502083056258571e-05, + "loss": 3.601, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501244461507519e-05, + "loss": 3.5992, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8440616130828857, + "eval_runtime": 304.2942, + "eval_samples_per_second": 1254.02, + "eval_steps_per_second": 39.189, + "step": 915829 + }, + { + "epoch": 1.0, + "learning_rate": 3.500405866756467e-05, + "loss": 3.6083, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499568909885788e-05, + "loss": 3.5974, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498730315134736e-05, + "loss": 3.6008, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497891720383684e-05, + "loss": 3.6099, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497053125632632e-05, + "loss": 3.6089, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.49621453088158e-05, + "loss": 3.605, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.4953775740109006e-05, + "loss": 3.6106, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.4945389792598486e-05, + "loss": 3.5931, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4937003845087966e-05, + "loss": 3.5919, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.4928617897577446e-05, + "loss": 3.6018, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.492024832887066e-05, + "loss": 3.6051, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491186238136014e-05, + "loss": 3.5966, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490347643384962e-05, + "loss": 3.6046, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.48950904863391e-05, + "loss": 3.5841, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488672091763231e-05, + "loss": 3.5937, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487833497012179e-05, + "loss": 3.5778, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486994902261127e-05, + "loss": 3.6017, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4861563075100744e-05, + "loss": 3.5968, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485319350639396e-05, + "loss": 3.5941, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484480755888344e-05, + "loss": 3.5992, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483642161137292e-05, + "loss": 3.6101, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.48280356638624e-05, + "loss": 3.6035, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.4819666095155615e-05, + "loss": 3.5997, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.4811280147645095e-05, + "loss": 3.5953, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.4802894200134575e-05, + "loss": 3.6142, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479450825262405e-05, + "loss": 3.5996, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.4786138683917264e-05, + "loss": 3.5945, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.4777752736406744e-05, + "loss": 3.5999, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476936678889622e-05, + "loss": 3.5865, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.47609808413857e-05, + "loss": 3.5938, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475261127267891e-05, + "loss": 3.601, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.474422532516839e-05, + "loss": 3.5958, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4735839377657866e-05, + "loss": 3.6034, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.472745343014735e-05, + "loss": 3.608, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.471908386144057e-05, + "loss": 3.5943, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.471069791393005e-05, + "loss": 3.601, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.470231196641952e-05, + "loss": 3.6037, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.4693926018909e-05, + "loss": 3.5875, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.468555645020222e-05, + "loss": 3.595, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467717050269169e-05, + "loss": 3.5837, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466878455518117e-05, + "loss": 3.5835, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.466039860767065e-05, + "loss": 3.5914, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465202903896387e-05, + "loss": 3.6034, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464364309145334e-05, + "loss": 3.5915, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463525714394282e-05, + "loss": 3.5928, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462687119643231e-05, + "loss": 3.5916, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.4618501627725516e-05, + "loss": 3.5969, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.4610115680214996e-05, + "loss": 3.5869, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.4601729732704476e-05, + "loss": 3.5736, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.4593343785193956e-05, + "loss": 3.5963, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.4584974216487165e-05, + "loss": 3.6042, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.4576588268976645e-05, + "loss": 3.6021, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.4568202321466125e-05, + "loss": 3.5886, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455983275275934e-05, + "loss": 3.592, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.4551446805248814e-05, + "loss": 3.584, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.4543060857738294e-05, + "loss": 3.5789, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4534674910227774e-05, + "loss": 3.606, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452628896271726e-05, + "loss": 3.5815, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451790301520674e-05, + "loss": 3.6098, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450951706769622e-05, + "loss": 3.592, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.45011311201857e-05, + "loss": 3.5755, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449276155147891e-05, + "loss": 3.5968, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448437560396839e-05, + "loss": 3.5887, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447598965645787e-05, + "loss": 3.5753, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446760370894735e-05, + "loss": 3.5896, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445923414024056e-05, + "loss": 3.5997, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445084819273004e-05, + "loss": 3.5847, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444246224521952e-05, + "loss": 3.5931, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.4434076297709e-05, + "loss": 3.5689, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442569035019848e-05, + "loss": 3.5872, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.4417320781491694e-05, + "loss": 3.587, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4408934833981174e-05, + "loss": 3.5915, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.4400548886470654e-05, + "loss": 3.5882, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.4392162938960134e-05, + "loss": 3.5886, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438379337025334e-05, + "loss": 3.6041, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.437540742274282e-05, + "loss": 3.5939, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.43670214752323e-05, + "loss": 3.5928, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435865190652551e-05, + "loss": 3.5868, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.435026595901499e-05, + "loss": 3.5822, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.434188001150447e-05, + "loss": 3.5961, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433349406399395e-05, + "loss": 3.5892, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432510811648343e-05, + "loss": 3.5894, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.431673854777665e-05, + "loss": 3.594, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430835260026613e-05, + "loss": 3.5872, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429996665275561e-05, + "loss": 3.571, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.429158070524509e-05, + "loss": 3.5892, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.42832111365383e-05, + "loss": 3.5927, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4274825189027777e-05, + "loss": 3.5796, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4266439241517257e-05, + "loss": 3.5852, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.4258053294006736e-05, + "loss": 3.589, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.4249683725299946e-05, + "loss": 3.5785, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.4241297777789426e-05, + "loss": 3.581, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4232911830278906e-05, + "loss": 3.5841, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4224525882768385e-05, + "loss": 3.5932, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.42161563140616e-05, + "loss": 3.592, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420777036655108e-05, + "loss": 3.596, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419938441904056e-05, + "loss": 3.582, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419099847153004e-05, + "loss": 3.5809, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418262890282325e-05, + "loss": 3.5882, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417424295531273e-05, + "loss": 3.5959, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416585700780221e-05, + "loss": 3.5907, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415747106029169e-05, + "loss": 3.5923, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.41491014915849e-05, + "loss": 3.5863, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.414071554407438e-05, + "loss": 3.5838, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413232959656386e-05, + "loss": 3.5926, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.412394364905334e-05, + "loss": 3.5829, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.4115574080346555e-05, + "loss": 3.5831, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.4107188132836035e-05, + "loss": 3.5911, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.4098802185325515e-05, + "loss": 3.5828, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.4090416237814995e-05, + "loss": 3.5826, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.4082046669108204e-05, + "loss": 3.5808, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4073660721597684e-05, + "loss": 3.5742, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4065274774087164e-05, + "loss": 3.591, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.4056888826576644e-05, + "loss": 3.5923, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404851925786985e-05, + "loss": 3.5812, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.404013331035933e-05, + "loss": 3.5942, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403174736284881e-05, + "loss": 3.5978, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402336141533829e-05, + "loss": 3.5878, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401499184663151e-05, + "loss": 3.5882, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400660589912099e-05, + "loss": 3.5812, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399821995161047e-05, + "loss": 3.586, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398983400409995e-05, + "loss": 3.5827, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398146443539316e-05, + "loss": 3.5829, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397307848788264e-05, + "loss": 3.5782, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396469254037212e-05, + "loss": 3.5885, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.39563065928616e-05, + "loss": 3.582, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.3947937024154807e-05, + "loss": 3.5875, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.3939551076644287e-05, + "loss": 3.588, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.3931165129133767e-05, + "loss": 3.5843, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.3922779181623246e-05, + "loss": 3.5817, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391440961291646e-05, + "loss": 3.5916, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390602366540594e-05, + "loss": 3.5933, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389763771789542e-05, + "loss": 3.5804, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.3889251770384895e-05, + "loss": 3.5834, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388088220167811e-05, + "loss": 3.5916, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387249625416759e-05, + "loss": 3.5791, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386411030665707e-05, + "loss": 3.5899, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.3855724359146544e-05, + "loss": 3.5862, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384735479043976e-05, + "loss": 3.599, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.383896884292924e-05, + "loss": 3.5925, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3830582895418713e-05, + "loss": 3.5946, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.38221969479082e-05, + "loss": 3.5842, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.3813827379201416e-05, + "loss": 3.5898, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.3805441431690896e-05, + "loss": 3.5845, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379705548418037e-05, + "loss": 3.5753, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378866953666985e-05, + "loss": 3.5875, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3780299967963065e-05, + "loss": 3.5756, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.3771914020452545e-05, + "loss": 3.587, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376352807294202e-05, + "loss": 3.577, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8450515270233154, + "eval_runtime": 304.287, + "eval_samples_per_second": 1254.05, + "eval_steps_per_second": 39.19, + "step": 992149 + }, + { + "epoch": 0.0, + "learning_rate": 3.37551421254315e-05, + "loss": 3.598, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374675617792098e-05, + "loss": 3.5782, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373837023041046e-05, + "loss": 3.582, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372998428289994e-05, + "loss": 3.5951, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721614714193154e-05, + "loss": 3.585, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3713228766682634e-05, + "loss": 3.5932, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3704842819172114e-05, + "loss": 3.5866, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696456871661594e-05, + "loss": 3.578, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.36880873029548e-05, + "loss": 3.5701, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367970135544428e-05, + "loss": 3.5819, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367131540793376e-05, + "loss": 3.5859, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366292946042324e-05, + "loss": 3.5779, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365455989171645e-05, + "loss": 3.5869, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364617394420593e-05, + "loss": 3.5606, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363778799669541e-05, + "loss": 3.5738, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362940204918489e-05, + "loss": 3.5683, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.36210324804781e-05, + "loss": 3.5815, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361264653296759e-05, + "loss": 3.5732, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360426058545707e-05, + "loss": 3.5775, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359587463794655e-05, + "loss": 3.5847, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.3587505069239756e-05, + "loss": 3.5866, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.3579119121729236e-05, + "loss": 3.587, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3570733174218716e-05, + "loss": 3.5788, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3562347226708196e-05, + "loss": 3.5781, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3553977658001405e-05, + "loss": 3.596, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3545591710490885e-05, + "loss": 3.5811, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.3537205762980365e-05, + "loss": 3.5724, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3528819815469845e-05, + "loss": 3.5813, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3520450246763054e-05, + "loss": 3.5678, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351206429925254e-05, + "loss": 3.5755, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350367835174202e-05, + "loss": 3.583, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.34952924042315e-05, + "loss": 3.5761, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348692283552471e-05, + "loss": 3.5835, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347853688801419e-05, + "loss": 3.5926, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.347015094050367e-05, + "loss": 3.5765, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346176499299315e-05, + "loss": 3.5829, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345339542428636e-05, + "loss": 3.5861, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344500947677584e-05, + "loss": 3.5654, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343662352926532e-05, + "loss": 3.5792, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.34282375817548e-05, + "loss": 3.5614, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341986801304801e-05, + "loss": 3.5697, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411482065537495e-05, + "loss": 3.5695, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3403096118026975e-05, + "loss": 3.5887, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394710170516455e-05, + "loss": 3.5701, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3386340601809664e-05, + "loss": 3.5744, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3377954654299144e-05, + "loss": 3.5736, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369568706788624e-05, + "loss": 3.5783, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3361182759278104e-05, + "loss": 3.572, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335281319057131e-05, + "loss": 3.5561, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334442724306079e-05, + "loss": 3.576, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333604129555027e-05, + "loss": 3.5884, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332765534803975e-05, + "loss": 3.5796, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331928577933296e-05, + "loss": 3.5721, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331091621062618e-05, + "loss": 3.5697, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330253026311566e-05, + "loss": 3.5715, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329414431560514e-05, + "loss": 3.5585, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328575836809462e-05, + "loss": 3.5932, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.32773724205841e-05, + "loss": 3.5595, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326898647307358e-05, + "loss": 3.5919, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326060052556306e-05, + "loss": 3.5751, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325221457805254e-05, + "loss": 3.5583, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3243845009345746e-05, + "loss": 3.5759, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3235459061835226e-05, + "loss": 3.5728, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3227073114324706e-05, + "loss": 3.5595, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218687166814186e-05, + "loss": 3.5654, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.32103175981074e-05, + "loss": 3.5851, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320193165059688e-05, + "loss": 3.5681, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319354570308636e-05, + "loss": 3.571, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318515975557584e-05, + "loss": 3.553, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317679018686905e-05, + "loss": 3.5703, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316840423935853e-05, + "loss": 3.5684, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.316001829184801e-05, + "loss": 3.5736, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315163234433749e-05, + "loss": 3.5685, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.31432627756307e-05, + "loss": 3.5725, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313487682812018e-05, + "loss": 3.582, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312649088060966e-05, + "loss": 3.5715, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311810493309914e-05, + "loss": 3.5757, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.3109735364392356e-05, + "loss": 3.5731, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.3101349416881836e-05, + "loss": 3.5672, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.3092963469371316e-05, + "loss": 3.5746, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.3084577521860796e-05, + "loss": 3.5698, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.3076207953154005e-05, + "loss": 3.5728, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3067822005643485e-05, + "loss": 3.58, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3059436058132965e-05, + "loss": 3.5662, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3051050110622445e-05, + "loss": 3.5509, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3042680541915654e-05, + "loss": 3.5729, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3034294594405134e-05, + "loss": 3.5724, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.3025908646894614e-05, + "loss": 3.5654, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3017522699384094e-05, + "loss": 3.5674, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300915313067731e-05, + "loss": 3.5722, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300076718316679e-05, + "loss": 3.5608, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299238123565627e-05, + "loss": 3.5619, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298399528814574e-05, + "loss": 3.5652, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297562571943896e-05, + "loss": 3.5768, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296723977192844e-05, + "loss": 3.5743, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295885382441792e-05, + "loss": 3.5767, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295046787690739e-05, + "loss": 3.5621, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294209830820061e-05, + "loss": 3.5646, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293371236069009e-05, + "loss": 3.5684, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292532641317956e-05, + "loss": 3.5797, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291694046566905e-05, + "loss": 3.5704, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.2908570896962256e-05, + "loss": 3.5749, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.290018494945174e-05, + "loss": 3.57, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2891799001941216e-05, + "loss": 3.5664, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.2883413054430696e-05, + "loss": 3.5757, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287504348572391e-05, + "loss": 3.561, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286665753821339e-05, + "loss": 3.5688, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.2858271590702865e-05, + "loss": 3.5715, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2849885643192345e-05, + "loss": 3.5669, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284151607448556e-05, + "loss": 3.5642, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.2833130126975034e-05, + "loss": 3.5645, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2824744179464514e-05, + "loss": 3.555, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2816358231954e-05, + "loss": 3.5737, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280798866324721e-05, + "loss": 3.5729, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279960271573669e-05, + "loss": 3.5646, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279121676822617e-05, + "loss": 3.5787, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278283082071565e-05, + "loss": 3.5817, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2774461252008866e-05, + "loss": 3.5689, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276607530449834e-05, + "loss": 3.5702, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275768935698782e-05, + "loss": 3.566, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.27493034094773e-05, + "loss": 3.566, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274093384077051e-05, + "loss": 3.5615, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273254789325999e-05, + "loss": 3.5662, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272416194574947e-05, + "loss": 3.5639, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271577599823895e-05, + "loss": 3.5708, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.2707406429532164e-05, + "loss": 3.5666, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2699020482021644e-05, + "loss": 3.5712, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690634534511124e-05, + "loss": 3.5675, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2682248587000604e-05, + "loss": 3.5647, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267387901829381e-05, + "loss": 3.5626, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266549307078329e-05, + "loss": 3.5768, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265710712327277e-05, + "loss": 3.5779, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264872117576225e-05, + "loss": 3.5665, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.264035160705546e-05, + "loss": 3.5626, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263196565954494e-05, + "loss": 3.5719, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262357971203442e-05, + "loss": 3.5633, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.26151937645239e-05, + "loss": 3.5686, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260682419581712e-05, + "loss": 3.5681, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.25984382483066e-05, + "loss": 3.5854, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.259005230079608e-05, + "loss": 3.5711, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258166635328556e-05, + "loss": 3.5778, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.2573296784578766e-05, + "loss": 3.5684, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.2564910837068246e-05, + "loss": 3.5747, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.2556524889557726e-05, + "loss": 3.5638, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.2548138942047206e-05, + "loss": 3.5593, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.2539769373340415e-05, + "loss": 3.5723, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.2531383425829895e-05, + "loss": 3.5561, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2522997478319375e-05, + "loss": 3.5702, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.2514611530808855e-05, + "loss": 3.5583, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.8452227115631104, + "eval_runtime": 311.6366, + "eval_samples_per_second": 1224.474, + "eval_steps_per_second": 38.266, + "step": 1068469 + }, + { + "epoch": 1.0, + "learning_rate": 3.250624196210207e-05, + "loss": 3.5694, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249785601459155e-05, + "loss": 3.5642, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248947006708103e-05, + "loss": 3.5626, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248108411957051e-05, + "loss": 3.5805, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247271455086372e-05, + "loss": 3.5668, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.24643286033532e-05, + "loss": 3.579, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245594265584268e-05, + "loss": 3.5658, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244755670833216e-05, + "loss": 3.5593, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243918713962537e-05, + "loss": 3.5576, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243080119211485e-05, + "loss": 3.5683, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242241524460433e-05, + "loss": 3.5644, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241402929709381e-05, + "loss": 3.5631, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240567610719076e-05, + "loss": 3.5697, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.2397290159680234e-05, + "loss": 3.5477, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.2388904212169714e-05, + "loss": 3.5524, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.2380518264659194e-05, + "loss": 3.5528, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.2372132317148674e-05, + "loss": 3.5615, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.2363746369638154e-05, + "loss": 3.5598, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.2355360422127634e-05, + "loss": 3.5619, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.2346974474617113e-05, + "loss": 3.5648, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.2338588527106593e-05, + "loss": 3.5701, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.23302189583998e-05, + "loss": 3.5673, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232183301088928e-05, + "loss": 3.5676, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231344706337876e-05, + "loss": 3.5573, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230506111586825e-05, + "loss": 3.5798, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229669154716146e-05, + "loss": 3.5639, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228830559965094e-05, + "loss": 3.5613, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227991965214042e-05, + "loss": 3.5615, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.22715337046299e-05, + "loss": 3.5522, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226316413592311e-05, + "loss": 3.5602, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225477818841259e-05, + "loss": 3.5595, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224639224090207e-05, + "loss": 3.5632, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.2238022672195276e-05, + "loss": 3.5648, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.2229636724684756e-05, + "loss": 3.572, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2221250777174236e-05, + "loss": 3.5622, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.2212864829663716e-05, + "loss": 3.5655, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220449526095693e-05, + "loss": 3.5682, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219610931344641e-05, + "loss": 3.5504, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218772336593589e-05, + "loss": 3.5599, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217933741842537e-05, + "loss": 3.5454, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217096784971858e-05, + "loss": 3.5563, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216258190220806e-05, + "loss": 3.5505, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215419595469754e-05, + "loss": 3.5717, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214581000718702e-05, + "loss": 3.5513, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213744043848023e-05, + "loss": 3.558, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212905449096971e-05, + "loss": 3.5596, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212066854345919e-05, + "loss": 3.5585, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211228259594867e-05, + "loss": 3.5563, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2103913027241886e-05, + "loss": 3.537, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2095527079731366e-05, + "loss": 3.5612, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.2087141132220846e-05, + "loss": 3.569, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.2078755184710326e-05, + "loss": 3.5666, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.2070385616003535e-05, + "loss": 3.5583, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.2062016047296744e-05, + "loss": 3.5486, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.2053630099786224e-05, + "loss": 3.5569, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.2045244152275704e-05, + "loss": 3.5441, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.2036858204765184e-05, + "loss": 3.5722, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.2028472257254664e-05, + "loss": 3.5453, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.2020086309744143e-05, + "loss": 3.5746, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.2011700362233623e-05, + "loss": 3.5589, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2003314414723103e-05, + "loss": 3.5383, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199494484601632e-05, + "loss": 3.5578, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.19865588985058e-05, + "loss": 3.5585, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197817295099528e-05, + "loss": 3.5434, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.196978700348476e-05, + "loss": 3.5448, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.196141743477797e-05, + "loss": 3.5662, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195303148726745e-05, + "loss": 3.5553, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.194464553975693e-05, + "loss": 3.5515, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193625959224641e-05, + "loss": 3.5389, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192787364473589e-05, + "loss": 3.5522, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.19195040760291e-05, + "loss": 3.5487, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191111812851858e-05, + "loss": 3.562, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190273218100806e-05, + "loss": 3.5495, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189434623349754e-05, + "loss": 3.5592, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188597666479075e-05, + "loss": 3.5621, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187759071728023e-05, + "loss": 3.5571, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186920476976971e-05, + "loss": 3.5587, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186083520106292e-05, + "loss": 3.5559, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.18524492535524e-05, + "loss": 3.5544, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184406330604188e-05, + "loss": 3.558, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183567735853136e-05, + "loss": 3.5545, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182730778982457e-05, + "loss": 3.5556, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181892184231405e-05, + "loss": 3.5548, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.181053589480353e-05, + "loss": 3.5521, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180214994729301e-05, + "loss": 3.5378, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1793780378586227e-05, + "loss": 3.5571, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1785394431075707e-05, + "loss": 3.5482, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1777008483565187e-05, + "loss": 3.5541, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176862253605466e-05, + "loss": 3.549, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.1760252967347876e-05, + "loss": 3.5576, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1751867019837356e-05, + "loss": 3.5461, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.1743481072326835e-05, + "loss": 3.543, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173509512481631e-05, + "loss": 3.5478, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.1726725556109525e-05, + "loss": 3.5615, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.1718339608599004e-05, + "loss": 3.5557, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.1709953661088484e-05, + "loss": 3.5611, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.1701567713577964e-05, + "loss": 3.5469, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169319814487118e-05, + "loss": 3.5529, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168481219736066e-05, + "loss": 3.5506, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.1676426249850133e-05, + "loss": 3.564, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166804030233961e-05, + "loss": 3.5544, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165967073363283e-05, + "loss": 3.5597, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.16512847861223e-05, + "loss": 3.5505, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164289883861178e-05, + "loss": 3.551, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163451289110126e-05, + "loss": 3.5638, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162614332239448e-05, + "loss": 3.545, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161775737488396e-05, + "loss": 3.5491, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160937142737344e-05, + "loss": 3.5538, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160098547986292e-05, + "loss": 3.5487, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.1592615911156134e-05, + "loss": 3.5514, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158422996364561e-05, + "loss": 3.5507, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157584401613509e-05, + "loss": 3.5403, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156745806862457e-05, + "loss": 3.5569, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.1559088499917776e-05, + "loss": 3.5541, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.1550702552407256e-05, + "loss": 3.5488, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.1542316604896736e-05, + "loss": 3.5603, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1533930657386216e-05, + "loss": 3.5666, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.1525561088679425e-05, + "loss": 3.5543, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151717514116891e-05, + "loss": 3.5537, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150878919365839e-05, + "loss": 3.5476, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.150040324614787e-05, + "loss": 3.552, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149203367744108e-05, + "loss": 3.5408, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148364772993056e-05, + "loss": 3.5533, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147526178242004e-05, + "loss": 3.5456, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146687583490952e-05, + "loss": 3.5559, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145850626620273e-05, + "loss": 3.5483, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.145012031869221e-05, + "loss": 3.551, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144173437118169e-05, + "loss": 3.5529, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143334842367117e-05, + "loss": 3.5499, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142497885496438e-05, + "loss": 3.5442, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.1416592907453865e-05, + "loss": 3.5601, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.1408206959943345e-05, + "loss": 3.5639, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.1399821012432825e-05, + "loss": 3.5556, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.1391451443726034e-05, + "loss": 3.5438, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1383065496215514e-05, + "loss": 3.553, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.1374679548704994e-05, + "loss": 3.5482, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.1366293601194474e-05, + "loss": 3.5548, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.1357924032487683e-05, + "loss": 3.5497, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.1349538084977163e-05, + "loss": 3.5681, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134115213746664e-05, + "loss": 3.5547, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133276618995612e-05, + "loss": 3.5634, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132439662124933e-05, + "loss": 3.551, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131601067373882e-05, + "loss": 3.5552, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.13076247262283e-05, + "loss": 3.5458, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129923877871778e-05, + "loss": 3.5442, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.129086921001099e-05, + "loss": 3.558, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128248326250047e-05, + "loss": 3.5407, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127409731498995e-05, + "loss": 3.5537, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126571136747943e-05, + "loss": 3.5441, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.8458786010742188, + "eval_runtime": 307.182, + "eval_samples_per_second": 1242.231, + "eval_steps_per_second": 38.821, + "step": 1144789 + }, + { + "epoch": 0.0, + "learning_rate": 3.125734179877264e-05, + "loss": 3.5465, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124895585126212e-05, + "loss": 3.5511, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.12405699037516e-05, + "loss": 3.546, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123218395624108e-05, + "loss": 3.5579, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.1223814387534286e-05, + "loss": 3.5541, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121542844002377e-05, + "loss": 3.5606, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120704249251325e-05, + "loss": 3.5494, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119865654500273e-05, + "loss": 3.5478, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.119027059749221e-05, + "loss": 3.538, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118190102878542e-05, + "loss": 3.5515, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.11735150812749e-05, + "loss": 3.5497, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116512913376438e-05, + "loss": 3.5472, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115674318625386e-05, + "loss": 3.5506, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114837361754707e-05, + "loss": 3.5367, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113998767003655e-05, + "loss": 3.5381, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113160172252603e-05, + "loss": 3.5379, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112321577501551e-05, + "loss": 3.54, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.1114846206308726e-05, + "loss": 3.5427, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.1106460258798206e-05, + "loss": 3.5488, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.1098074311287686e-05, + "loss": 3.5421, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.1089688363777166e-05, + "loss": 3.5599, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.1081318795070375e-05, + "loss": 3.55, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.1072932847559855e-05, + "loss": 3.5485, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.1064546900049335e-05, + "loss": 3.5441, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.1056177331342544e-05, + "loss": 3.5626, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1047791383832024e-05, + "loss": 3.5445, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1039405436321504e-05, + "loss": 3.548, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.1031019488810984e-05, + "loss": 3.5427, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.1022649920104193e-05, + "loss": 3.543, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101426397259368e-05, + "loss": 3.5427, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100587802508316e-05, + "loss": 3.5427, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099749207757264e-05, + "loss": 3.551, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098912250886585e-05, + "loss": 3.5504, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098073656135533e-05, + "loss": 3.5539, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097235061384481e-05, + "loss": 3.547, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096396466633429e-05, + "loss": 3.5506, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.09555950976275e-05, + "loss": 3.5486, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094720915011698e-05, + "loss": 3.5374, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093882320260646e-05, + "loss": 3.5438, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.093043725509594e-05, + "loss": 3.529, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092206768638915e-05, + "loss": 3.54, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091368173887863e-05, + "loss": 3.534, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.0905295791368114e-05, + "loss": 3.5558, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.0896909843857594e-05, + "loss": 3.5418, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.08885402751508e-05, + "loss": 3.537, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.088015432764028e-05, + "loss": 3.5434, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087176838012976e-05, + "loss": 3.5477, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086338243261924e-05, + "loss": 3.5399, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085501286391245e-05, + "loss": 3.5217, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084662691640193e-05, + "loss": 3.543, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083824096889141e-05, + "loss": 3.5545, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082985502138089e-05, + "loss": 3.5489, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.08214854526741e-05, + "loss": 3.5426, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081311588396732e-05, + "loss": 3.5314, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0804729936456797e-05, + "loss": 3.5419, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0796343988946277e-05, + "loss": 3.5282, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0787958041435756e-05, + "loss": 3.5536, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.0779572093925236e-05, + "loss": 3.5308, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.0771186146414716e-05, + "loss": 3.5576, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.0762800198904196e-05, + "loss": 3.545, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0754414251393676e-05, + "loss": 3.5256, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.0746044682686885e-05, + "loss": 3.5418, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.0737658735176365e-05, + "loss": 3.5487, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.0729272787665845e-05, + "loss": 3.5239, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.0720886840155325e-05, + "loss": 3.5307, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.0712517271448534e-05, + "loss": 3.5509, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070413132393802e-05, + "loss": 3.5392, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.06957453764275e-05, + "loss": 3.5332, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068735942891698e-05, + "loss": 3.5259, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067898986021019e-05, + "loss": 3.5376, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067060391269967e-05, + "loss": 3.53, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066221796518915e-05, + "loss": 3.5477, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065383201767863e-05, + "loss": 3.5339, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064546244897184e-05, + "loss": 3.5441, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063707650146132e-05, + "loss": 3.5445, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.06286905539508e-05, + "loss": 3.544, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.062030460644027e-05, + "loss": 3.5406, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061193503773349e-05, + "loss": 3.5402, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.0603549090222975e-05, + "loss": 3.5424, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.0595163142712455e-05, + "loss": 3.5411, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058677719520193e-05, + "loss": 3.5415, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.0578407626495144e-05, + "loss": 3.5404, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.0570021678984624e-05, + "loss": 3.5383, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.0561635731474104e-05, + "loss": 3.5408, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055324978396358e-05, + "loss": 3.5236, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054488021525679e-05, + "loss": 3.538, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053649426774627e-05, + "loss": 3.5382, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0528108320235746e-05, + "loss": 3.5378, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.0519722372725226e-05, + "loss": 3.5368, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511352804018445e-05, + "loss": 3.5384, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502966856507925e-05, + "loss": 3.5315, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.04945809089974e-05, + "loss": 3.5267, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.048619496148688e-05, + "loss": 3.5317, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477825392780097e-05, + "loss": 3.5451, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469439445269577e-05, + "loss": 3.5418, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.046105349775905e-05, + "loss": 3.5444, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.045266755024853e-05, + "loss": 3.5322, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0444297981541746e-05, + "loss": 3.5363, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435912034031223e-05, + "loss": 3.5312, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427526086520703e-05, + "loss": 3.5465, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0419140139010183e-05, + "loss": 3.5379, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.04107705703034e-05, + "loss": 3.5459, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0402384622792872e-05, + "loss": 3.5342, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393998675282352e-05, + "loss": 3.5315, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385612727771835e-05, + "loss": 3.5523, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037724315906505e-05, + "loss": 3.5301, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0368857211554524e-05, + "loss": 3.5296, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360471264044004e-05, + "loss": 3.5427, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0352085316533484e-05, + "loss": 3.538, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343715747826697e-05, + "loss": 3.5295, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0335329800316177e-05, + "loss": 3.5369, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0326943852805657e-05, + "loss": 3.5227, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318557905295137e-05, + "loss": 3.541, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0310188336588346e-05, + "loss": 3.5363, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0301802389077826e-05, + "loss": 3.5393, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0293416441567306e-05, + "loss": 3.5422, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.028503049405679e-05, + "loss": 3.5526, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276660925349998e-05, + "loss": 3.5427, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0268274977839478e-05, + "loss": 3.5358, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259889030328958e-05, + "loss": 3.5359, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251503082818438e-05, + "loss": 3.5306, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.024313351411165e-05, + "loss": 3.5316, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.023474756660113e-05, + "loss": 3.5367, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.022636161909061e-05, + "loss": 3.5304, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.021799205038382e-05, + "loss": 3.5392, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.02096061028733e-05, + "loss": 3.5344, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.020122015536278e-05, + "loss": 3.5396, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.019283420785226e-05, + "loss": 3.5345, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184464639145472e-05, + "loss": 3.5318, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.017607869163495e-05, + "loss": 3.5289, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.016769274412443e-05, + "loss": 3.5445, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015930679661391e-05, + "loss": 3.5472, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.015093722790712e-05, + "loss": 3.5412, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142551280396604e-05, + "loss": 3.5282, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0134165332886084e-05, + "loss": 3.5336, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125779385375564e-05, + "loss": 3.5371, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0117409816668773e-05, + "loss": 3.5403, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0109023869158253e-05, + "loss": 3.5398, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100637921647733e-05, + "loss": 3.5489, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0092251974137213e-05, + "loss": 3.5371, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083882405430425e-05, + "loss": 3.5508, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0075496457919905e-05, + "loss": 3.5349, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0067110510409385e-05, + "loss": 3.5404, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058724562898865e-05, + "loss": 3.5351, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0050354994192074e-05, + "loss": 3.5266, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0041969046681558e-05, + "loss": 3.543, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033583099171038e-05, + "loss": 3.5258, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0025197151660518e-05, + "loss": 3.5346, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016827582953727e-05, + "loss": 3.5334, + "step": 1220608 + }, + { + "epoch": 0.03, + "eval_loss": 3.8479256629943848, + "eval_runtime": 304.955, + "eval_samples_per_second": 1251.303, + "eval_steps_per_second": 39.104, + "step": 1221109 + }, + { + "epoch": 1.0, + "learning_rate": 3.0008441635443207e-05, + "loss": 3.5329, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 3.0000055687932687e-05, + "loss": 3.535, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991669740422167e-05, + "loss": 3.5291, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.998330017171538e-05, + "loss": 3.5424, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.997491422420486e-05, + "loss": 3.5412, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.996652827669434e-05, + "loss": 3.5489, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.995814232918382e-05, + "loss": 3.5313, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949772760477028e-05, + "loss": 3.5308, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.994138681296651e-05, + "loss": 3.526, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.993300086545599e-05, + "loss": 3.5378, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.992461491794547e-05, + "loss": 3.5313, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.991624534923868e-05, + "loss": 3.5356, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990785940172816e-05, + "loss": 3.5319, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.989947345421764e-05, + "loss": 3.5232, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.989108750670712e-05, + "loss": 3.5289, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882717938000333e-05, + "loss": 3.5239, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9874331990489813e-05, + "loss": 3.5219, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9865946042979293e-05, + "loss": 3.5327, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9857560095468773e-05, + "loss": 3.5286, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984919052676198e-05, + "loss": 3.5316, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840804579251465e-05, + "loss": 3.5482, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832418631740945e-05, + "loss": 3.5303, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9824032684230425e-05, + "loss": 3.5369, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815646736719905e-05, + "loss": 3.5294, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9807277168013114e-05, + "loss": 3.5449, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9798891220502594e-05, + "loss": 3.5306, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790505272992074e-05, + "loss": 3.534, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9782119325481557e-05, + "loss": 3.5262, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773749756774766e-05, + "loss": 3.5311, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765363809264246e-05, + "loss": 3.5268, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9756977861753726e-05, + "loss": 3.53, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748591914243206e-05, + "loss": 3.5367, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.974022234553642e-05, + "loss": 3.5326, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.97318363980259e-05, + "loss": 3.5386, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.972345045051538e-05, + "loss": 3.5356, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9715080881808588e-05, + "loss": 3.5295, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706694934298068e-05, + "loss": 3.54, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698308986787548e-05, + "loss": 3.5194, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689923039277028e-05, + "loss": 3.5325, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.968155347057024e-05, + "loss": 3.5149, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.967316752305972e-05, + "loss": 3.5242, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.96647815755492e-05, + "loss": 3.5186, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.965639562803868e-05, + "loss": 3.5387, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.964800968052816e-05, + "loss": 3.5305, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639640111821372e-05, + "loss": 3.5238, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9631254164310852e-05, + "loss": 3.5291, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.9622868216800332e-05, + "loss": 3.5336, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.9614482269289812e-05, + "loss": 3.5228, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960611270058302e-05, + "loss": 3.5142, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.95977267530725e-05, + "loss": 3.5221, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.958934080556198e-05, + "loss": 3.5374, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.958095485805146e-05, + "loss": 3.5384, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572585289344674e-05, + "loss": 3.5263, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9564215720637883e-05, + "loss": 3.5197, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555829773127363e-05, + "loss": 3.5307, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9547443825616843e-05, + "loss": 3.5123, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9539057878106323e-05, + "loss": 3.5391, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530671930595806e-05, + "loss": 3.5139, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9522285983085286e-05, + "loss": 3.5409, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513900035574766e-05, + "loss": 3.5322, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505514088064246e-05, + "loss": 3.513, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9497144519357455e-05, + "loss": 3.5239, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488758571846935e-05, + "loss": 3.5347, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9480372624336415e-05, + "loss": 3.5095, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471986676825898e-05, + "loss": 3.5136, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463617108119107e-05, + "loss": 3.5374, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9455231160608587e-05, + "loss": 3.5258, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446845213098067e-05, + "loss": 3.5219, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438459265587544e-05, + "loss": 3.5115, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.943008969688076e-05, + "loss": 3.521, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.942170374937024e-05, + "loss": 3.5135, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.941331780185972e-05, + "loss": 3.5351, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9404931854349193e-05, + "loss": 3.5177, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.939656228564241e-05, + "loss": 3.5306, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.938817633813189e-05, + "loss": 3.5279, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.937979039062137e-05, + "loss": 3.5319, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9371404443110845e-05, + "loss": 3.5237, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.936303487440406e-05, + "loss": 3.5265, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.935464892689354e-05, + "loss": 3.5276, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9346262979383014e-05, + "loss": 3.5251, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337877031872497e-05, + "loss": 3.5271, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329507463165713e-05, + "loss": 3.5234, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9321121515655193e-05, + "loss": 3.5269, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312735568144666e-05, + "loss": 3.5234, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9304349620634146e-05, + "loss": 3.514, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9295980051927362e-05, + "loss": 3.519, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287594104416842e-05, + "loss": 3.5247, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.927920815690632e-05, + "loss": 3.5235, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.92708222093958e-05, + "loss": 3.5209, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262452640689015e-05, + "loss": 3.5269, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9254066693178488e-05, + "loss": 3.5183, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245680745667968e-05, + "loss": 3.5119, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.923729479815745e-05, + "loss": 3.5157, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9228925229450667e-05, + "loss": 3.5287, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.922053928194014e-05, + "loss": 3.5267, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.921215333442962e-05, + "loss": 3.5316, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.92037673869191e-05, + "loss": 3.5233, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195397818212316e-05, + "loss": 3.5194, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9187011870701793e-05, + "loss": 3.5196, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178625923191272e-05, + "loss": 3.5303, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9170239975680752e-05, + "loss": 3.5264, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916187040697396e-05, + "loss": 3.5355, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915348445946344e-05, + "loss": 3.5193, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914509851195292e-05, + "loss": 3.5145, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9136712564442405e-05, + "loss": 3.5408, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9128342995735614e-05, + "loss": 3.5123, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9119957048225094e-05, + "loss": 3.5193, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9111571100714574e-05, + "loss": 3.5253, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9103185153204054e-05, + "loss": 3.5243, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9094815584497266e-05, + "loss": 3.5157, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086429636986746e-05, + "loss": 3.5192, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9078043689476226e-05, + "loss": 3.5136, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069657741965706e-05, + "loss": 3.5248, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9061288173258915e-05, + "loss": 3.5245, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052902225748395e-05, + "loss": 3.5211, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044516278237875e-05, + "loss": 3.5286, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.903613033072736e-05, + "loss": 3.5352, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027760762020568e-05, + "loss": 3.5288, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9019374814510048e-05, + "loss": 3.5242, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9010988866999527e-05, + "loss": 3.5197, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002602919489007e-05, + "loss": 3.5141, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.899423335078222e-05, + "loss": 3.5197, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.89858474032717e-05, + "loss": 3.5226, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.897746145576118e-05, + "loss": 3.5175, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.896907550825066e-05, + "loss": 3.5218, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.896070593954387e-05, + "loss": 3.5227, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.895231999203335e-05, + "loss": 3.5218, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.894393404452283e-05, + "loss": 3.5224, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935548097012312e-05, + "loss": 3.5177, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.892717852830552e-05, + "loss": 3.5163, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8918792580795e-05, + "loss": 3.5284, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.891040663328448e-05, + "loss": 3.5296, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.890202068577396e-05, + "loss": 3.5299, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893651117067174e-05, + "loss": 3.5108, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8885265169556654e-05, + "loss": 3.5241, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876879222046133e-05, + "loss": 3.5214, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8868509653339343e-05, + "loss": 3.5273, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8860123705828823e-05, + "loss": 3.5201, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8851737758318302e-05, + "loss": 3.5366, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8843351810807782e-05, + "loss": 3.5216, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8834982242100995e-05, + "loss": 3.5395, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826596294590475e-05, + "loss": 3.5196, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8818210347079955e-05, + "loss": 3.53, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809824399569435e-05, + "loss": 3.5177, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8801454830862644e-05, + "loss": 3.5135, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8793068883352127e-05, + "loss": 3.5297, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784682935841607e-05, + "loss": 3.5135, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8776296988331087e-05, + "loss": 3.5215, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767927419624296e-05, + "loss": 3.5189, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759541472113776e-05, + "loss": 3.5167, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.85018253326416, + "eval_runtime": 303.923, + "eval_samples_per_second": 1255.552, + "eval_steps_per_second": 39.237, + "step": 1297429 + }, + { + "epoch": 0.0, + "learning_rate": 2.8751155524603256e-05, + "loss": 3.5199, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742769577092736e-05, + "loss": 3.5208, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734383629582216e-05, + "loss": 3.528, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.872601406087543e-05, + "loss": 3.5208, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.871762811336491e-05, + "loss": 3.5393, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.870924216585439e-05, + "loss": 3.5158, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.870085621834387e-05, + "loss": 3.5181, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.869248664963708e-05, + "loss": 3.5102, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.868410070212656e-05, + "loss": 3.5229, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.867571475461604e-05, + "loss": 3.5207, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866732880710552e-05, + "loss": 3.5185, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865895923839873e-05, + "loss": 3.5198, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650589669691942e-05, + "loss": 3.5048, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8642203722181422e-05, + "loss": 3.5156, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633817774670902e-05, + "loss": 3.5107, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8625431827160382e-05, + "loss": 3.5104, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8617045879649862e-05, + "loss": 3.5138, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608659932139342e-05, + "loss": 3.5152, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8600273984628822e-05, + "loss": 3.515, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859190441592203e-05, + "loss": 3.5366, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583518468411515e-05, + "loss": 3.5164, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8575132520900994e-05, + "loss": 3.5195, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566746573390474e-05, + "loss": 3.5177, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8558377004683684e-05, + "loss": 3.5279, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549991057173163e-05, + "loss": 3.5189, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541605109662643e-05, + "loss": 3.523, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8533219162152123e-05, + "loss": 3.509, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524849593445336e-05, + "loss": 3.5182, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516463645934816e-05, + "loss": 3.509, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8508077698424296e-05, + "loss": 3.5184, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499691750913776e-05, + "loss": 3.5214, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491322182206985e-05, + "loss": 3.5177, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482936234696468e-05, + "loss": 3.5268, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474550287185948e-05, + "loss": 3.5214, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8466164339675428e-05, + "loss": 3.5166, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457794770968637e-05, + "loss": 3.5222, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449408823458117e-05, + "loss": 3.5114, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8441022875947597e-05, + "loss": 3.5135, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432636928437077e-05, + "loss": 3.503, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842426735973029e-05, + "loss": 3.5095, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.841588141221977e-05, + "loss": 3.5092, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.840749546470925e-05, + "loss": 3.5215, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839910951719873e-05, + "loss": 3.5151, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.839073994849194e-05, + "loss": 3.5096, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382354000981422e-05, + "loss": 3.5184, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373968053470902e-05, + "loss": 3.5163, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365582105960382e-05, + "loss": 3.5106, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835721253725359e-05, + "loss": 3.5003, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834882658974307e-05, + "loss": 3.5057, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.834044064223255e-05, + "loss": 3.525, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.833205469472203e-05, + "loss": 3.5243, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323685126015243e-05, + "loss": 3.5067, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8315299178504723e-05, + "loss": 3.5108, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306929609797932e-05, + "loss": 3.5151, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298543662287412e-05, + "loss": 3.4989, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8290157714776892e-05, + "loss": 3.5193, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281771767266376e-05, + "loss": 3.5073, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273385819755855e-05, + "loss": 3.5231, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264999872245335e-05, + "loss": 3.5181, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.825661392473481e-05, + "loss": 3.5057, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8248244356028024e-05, + "loss": 3.5058, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239858408517504e-05, + "loss": 3.5219, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231472461006984e-05, + "loss": 3.4941, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.822308651349646e-05, + "loss": 3.5005, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214716944789677e-05, + "loss": 3.5209, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206330997279157e-05, + "loss": 3.5142, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197945049768637e-05, + "loss": 3.5055, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189559102258113e-05, + "loss": 3.499, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.818118953355133e-05, + "loss": 3.5079, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.817280358604081e-05, + "loss": 3.5039, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8164417638530282e-05, + "loss": 3.5147, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8156031691019762e-05, + "loss": 3.5073, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147662122312978e-05, + "loss": 3.5166, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8139276174802458e-05, + "loss": 3.5145, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130890227291935e-05, + "loss": 3.5198, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122504279781415e-05, + "loss": 3.5084, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811413471107463e-05, + "loss": 3.5158, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810574876356411e-05, + "loss": 3.5134, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8097362816053584e-05, + "loss": 3.5105, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8088976868543067e-05, + "loss": 3.5165, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080607299836283e-05, + "loss": 3.5105, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8072221352325756e-05, + "loss": 3.5136, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063835404815236e-05, + "loss": 3.5092, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055449457304716e-05, + "loss": 3.4974, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8047079888597932e-05, + "loss": 3.5032, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803869394108741e-05, + "loss": 3.5127, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.803030799357689e-05, + "loss": 3.5133, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021922046066368e-05, + "loss": 3.5071, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013552477359584e-05, + "loss": 3.5089, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8005166529849057e-05, + "loss": 3.503, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996780582338537e-05, + "loss": 3.498, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.798839463482802e-05, + "loss": 3.5011, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.798002506612123e-05, + "loss": 3.512, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.797163911861071e-05, + "loss": 3.5153, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.796325317110019e-05, + "loss": 3.5162, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.795486722358967e-05, + "loss": 3.5154, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946497654882882e-05, + "loss": 3.5042, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7938111707372362e-05, + "loss": 3.5066, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929725759861842e-05, + "loss": 3.5104, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7921339812351322e-05, + "loss": 3.516, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791297024364453e-05, + "loss": 3.5196, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790458429613401e-05, + "loss": 3.5066, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789619834862349e-05, + "loss": 3.5029, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887812401112974e-05, + "loss": 3.5251, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7879442832406183e-05, + "loss": 3.5002, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7871056884895663e-05, + "loss": 3.5105, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862670937385143e-05, + "loss": 3.5083, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7854284989874623e-05, + "loss": 3.5114, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845915421167836e-05, + "loss": 3.4999, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837529473657316e-05, + "loss": 3.511, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7829143526146796e-05, + "loss": 3.4991, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820757578636276e-05, + "loss": 3.5082, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7812388009929485e-05, + "loss": 3.5104, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7804002062418965e-05, + "loss": 3.5032, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795616114908445e-05, + "loss": 3.5201, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787230167397925e-05, + "loss": 3.5236, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778860598691137e-05, + "loss": 3.5137, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770474651180617e-05, + "loss": 3.5086, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7762088703670097e-05, + "loss": 3.507, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753702756159577e-05, + "loss": 3.5015, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.774533318745279e-05, + "loss": 3.5025, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.773694723994227e-05, + "loss": 3.5136, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.772856129243175e-05, + "loss": 3.501, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.772017534492123e-05, + "loss": 3.5068, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.771180577621444e-05, + "loss": 3.5105, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.770341982870392e-05, + "loss": 3.5119, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.76950338811934e-05, + "loss": 3.5042, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686647933682878e-05, + "loss": 3.5034, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767827836497609e-05, + "loss": 3.5098, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.766989241746557e-05, + "loss": 3.5109, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.766150646995505e-05, + "loss": 3.5176, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765312052244453e-05, + "loss": 3.5167, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.764475095373774e-05, + "loss": 3.4984, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7636365006227223e-05, + "loss": 3.5093, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627979058716703e-05, + "loss": 3.5077, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619593111206183e-05, + "loss": 3.5114, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7611223542499392e-05, + "loss": 3.507, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602837594988872e-05, + "loss": 3.5193, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.7594451647478352e-05, + "loss": 3.5086, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7586082078771564e-05, + "loss": 3.5276, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577696131261044e-05, + "loss": 3.506, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569310183750524e-05, + "loss": 3.5151, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560924236240004e-05, + "loss": 3.507, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552538288729484e-05, + "loss": 3.5013, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7544168720022693e-05, + "loss": 3.516, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535782772512177e-05, + "loss": 3.5042, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527396825001657e-05, + "loss": 3.5046, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7519010877491137e-05, + "loss": 3.5012, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510641308784346e-05, + "loss": 3.5026, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.8507542610168457, + "eval_runtime": 302.1215, + "eval_samples_per_second": 1263.038, + "eval_steps_per_second": 39.471, + "step": 1373749 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 9.375106127071427e+17, + "trial_name": null, + "trial_params": null +}