diff --git "a/checkpoint-3052726/trainer_state.json" "b/checkpoint-3052726/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-3052726/trainer_state.json" @@ -0,0 +1,36117 @@ +{ + "best_metric": 3.8440616130828857, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/transformer/2/checkpoints/checkpoint-915829", + "epoch": 1.0249799687230363, + "eval_steps": 10, + "global_step": 3052726, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 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 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502255361273826e-05, + "loss": 3.5097, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493869413763306e-05, + "loss": 3.5047, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485483466252786e-05, + "loss": 3.5174, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7477113897545998e-05, + "loss": 3.5057, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468727950035478e-05, + "loss": 3.5256, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7460342002524958e-05, + "loss": 3.5056, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451956055014438e-05, + "loss": 3.5086, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443586486307647e-05, + "loss": 3.4937, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743520053879713e-05, + "loss": 3.5106, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742681459128661e-05, + "loss": 3.5062, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741842864377609e-05, + "loss": 3.5014, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.74100590750693e-05, + "loss": 3.5144, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.740167312755878e-05, + "loss": 3.4889, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.739328718004826e-05, + "loss": 3.5071, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384917611341472e-05, + "loss": 3.4892, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376531663830952e-05, + "loss": 3.5009, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7368145716320432e-05, + "loss": 3.4968, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735975976880991e-05, + "loss": 3.5049, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.735139020010312e-05, + "loss": 3.4992, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.73430042525926e-05, + "loss": 3.5246, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334618305082084e-05, + "loss": 3.5046, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7326232357571564e-05, + "loss": 3.5067, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317862788864773e-05, + "loss": 3.5047, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309476841354253e-05, + "loss": 3.5171, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7301090893843733e-05, + "loss": 3.5056, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292704946333213e-05, + "loss": 3.5123, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7284335377626425e-05, + "loss": 3.494, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275949430115905e-05, + "loss": 3.5038, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267563482605385e-05, + "loss": 3.4946, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7259177535094865e-05, + "loss": 3.5072, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250807966388074e-05, + "loss": 3.507, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242422018877554e-05, + "loss": 3.5061, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7234036071367038e-05, + "loss": 3.516, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225650123856518e-05, + "loss": 3.5047, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7217280555149727e-05, + "loss": 3.5037, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208894607639207e-05, + "loss": 3.5088, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200508660128687e-05, + "loss": 3.4997, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7192122712618167e-05, + "loss": 3.5004, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718375314391138e-05, + "loss": 3.4912, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717536719640086e-05, + "loss": 3.4938, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.716698124889034e-05, + "loss": 3.4963, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.715859530137982e-05, + "loss": 3.5068, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7150225732673028e-05, + "loss": 3.5065, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141839785162508e-05, + "loss": 3.4957, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.713345383765199e-05, + "loss": 3.5064, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.712506789014147e-05, + "loss": 3.5007, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.711669832143468e-05, + "loss": 3.4958, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.710831237392416e-05, + "loss": 3.4935, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.709992642641364e-05, + "loss": 3.4882, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.709154047890312e-05, + "loss": 3.5112, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7083170910196333e-05, + "loss": 3.5113, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074784962685813e-05, + "loss": 3.4988, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7066399015175293e-05, + "loss": 3.4968, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7058029446468502e-05, + "loss": 3.5013, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049643498957982e-05, + "loss": 3.4855, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7041257551447462e-05, + "loss": 3.5045, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7032871603936945e-05, + "loss": 3.49, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024485656426425e-05, + "loss": 3.5091, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7016099708915905e-05, + "loss": 3.507, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007713761405378e-05, + "loss": 3.4942, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6999344192698594e-05, + "loss": 3.4893, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990958245188074e-05, + "loss": 3.51, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.698257229767755e-05, + "loss": 3.4815, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.697418635016703e-05, + "loss": 3.4926, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965816781460246e-05, + "loss": 3.5054, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6957430833949726e-05, + "loss": 3.5042, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.69490448864392e-05, + "loss": 3.4922, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940658938928683e-05, + "loss": 3.4853, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6932289370221895e-05, + "loss": 3.4921, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.692390342271138e-05, + "loss": 3.4903, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915517475200852e-05, + "loss": 3.5023, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6907131527690332e-05, + "loss": 3.4919, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898761958983548e-05, + "loss": 3.5054, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6890376011473024e-05, + "loss": 3.5033, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6881990063962504e-05, + "loss": 3.5046, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873604116451984e-05, + "loss": 3.4947, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.68652345477452e-05, + "loss": 3.5024, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856848600234673e-05, + "loss": 3.5008, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848462652724153e-05, + "loss": 3.4951, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6840076705213633e-05, + "loss": 3.5044, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.683170713650685e-05, + "loss": 3.5006, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6823321188996326e-05, + "loss": 3.4958, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6814935241485806e-05, + "loss": 3.4962, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806549293975285e-05, + "loss": 3.4845, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6798179725268498e-05, + "loss": 3.4958, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789793777757978e-05, + "loss": 3.4961, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781407830247458e-05, + "loss": 3.5038, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6773021882736938e-05, + "loss": 3.494, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764652314030147e-05, + "loss": 3.4969, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6756266366519627e-05, + "loss": 3.4919, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747880419009107e-05, + "loss": 3.4846, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739494471498587e-05, + "loss": 3.487, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.67311249027918e-05, + "loss": 3.4958, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.672273895528128e-05, + "loss": 3.5062, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.671435300777076e-05, + "loss": 3.5045, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.670596706026024e-05, + "loss": 3.4982, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697597491553448e-05, + "loss": 3.4949, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.668921154404293e-05, + "loss": 3.493, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.668082559653241e-05, + "loss": 3.4968, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.667243964902189e-05, + "loss": 3.5054, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.66640700803151e-05, + "loss": 3.506, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.665568413280458e-05, + "loss": 3.4956, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664729818529406e-05, + "loss": 3.4862, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.663891223778354e-05, + "loss": 3.5084, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630542669076753e-05, + "loss": 3.4881, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6622156721566233e-05, + "loss": 3.4974, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6613770774055713e-05, + "loss": 3.4947, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6605384826545193e-05, + "loss": 3.4932, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6597015257838402e-05, + "loss": 3.4881, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588629310327885e-05, + "loss": 3.5001, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6580243362817365e-05, + "loss": 3.4848, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6571857415306845e-05, + "loss": 3.4925, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6563487846600054e-05, + "loss": 3.5029, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6555101899089534e-05, + "loss": 3.4878, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546715951579014e-05, + "loss": 3.5083, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6538330004068494e-05, + "loss": 3.5097, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6529960435361707e-05, + "loss": 3.5033, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521574487851187e-05, + "loss": 3.4947, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6513188540340667e-05, + "loss": 3.4965, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504802592830146e-05, + "loss": 3.492, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6496433024123356e-05, + "loss": 3.4846, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.648804707661284e-05, + "loss": 3.5011, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.647966112910232e-05, + "loss": 3.4869, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.64712751815918e-05, + "loss": 3.4948, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462905612885008e-05, + "loss": 3.5004, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454519665374488e-05, + "loss": 3.4971, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6446133717863968e-05, + "loss": 3.4922, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6437747770353448e-05, + "loss": 3.492, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642937820164666e-05, + "loss": 3.4984, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.642099225413614e-05, + "loss": 3.4973, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.641260630662562e-05, + "loss": 3.499, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.64042203591151e-05, + "loss": 3.507, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.639585079040831e-05, + "loss": 3.4856, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387464842897793e-05, + "loss": 3.496, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6379078895387273e-05, + "loss": 3.4996, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370692947876753e-05, + "loss": 3.4971, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636232337916996e-05, + "loss": 3.4927, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.635393743165944e-05, + "loss": 3.5068, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.634555148414892e-05, + "loss": 3.4984, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.63371655366384e-05, + "loss": 3.5122, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328795967931614e-05, + "loss": 3.4954, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6320410020421094e-05, + "loss": 3.4984, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6312024072910574e-05, + "loss": 3.4961, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303638125400054e-05, + "loss": 3.4916, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6295268556693263e-05, + "loss": 3.4958, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286882609182746e-05, + "loss": 3.4939, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6278496661672226e-05, + "loss": 3.4917, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6270127092965435e-05, + "loss": 3.4886, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6261741145454915e-05, + "loss": 3.4876, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.8538849353790283, + "eval_runtime": 302.1533, + "eval_samples_per_second": 1262.905, + "eval_steps_per_second": 39.467, + "step": 1450069 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253355197944395e-05, + "loss": 3.4965, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244969250433875e-05, + "loss": 3.4923, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236583302923355e-05, + "loss": 3.504, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622819735541284e-05, + "loss": 3.4917, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219827786706048e-05, + "loss": 3.5149, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211441839195528e-05, + "loss": 3.4904, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6203055891685007e-05, + "loss": 3.4946, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194669944174487e-05, + "loss": 3.4838, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.61863003754677e-05, + "loss": 3.4956, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.617791442795718e-05, + "loss": 3.4957, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.616952848044666e-05, + "loss": 3.4885, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.616114253293614e-05, + "loss": 3.498, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.615277296422935e-05, + "loss": 3.4792, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.614438701671883e-05, + "loss": 3.4915, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.613600106920831e-05, + "loss": 3.484, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127615121697792e-05, + "loss": 3.4863, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6119245552991e-05, + "loss": 3.4813, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611085960548048e-05, + "loss": 3.4899, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.610247365796996e-05, + "loss": 3.4893, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609408771045944e-05, + "loss": 3.5087, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085718141752654e-05, + "loss": 3.489, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6077332194242134e-05, + "loss": 3.4991, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068946246731614e-05, + "loss": 3.4904, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060560299221093e-05, + "loss": 3.5005, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6052190730514303e-05, + "loss": 3.489, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043804783003783e-05, + "loss": 3.4987, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035418835493262e-05, + "loss": 3.4884, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6027032887982742e-05, + "loss": 3.4866, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018663319275955e-05, + "loss": 3.4792, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6010277371765435e-05, + "loss": 3.4938, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001891424254915e-05, + "loss": 3.4977, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993505476744395e-05, + "loss": 3.491, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5985135908037604e-05, + "loss": 3.5051, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976749960527087e-05, + "loss": 3.4962, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5968364013016567e-05, + "loss": 3.4858, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959994444309776e-05, + "loss": 3.4962, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951608496799256e-05, + "loss": 3.4915, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5943222549288736e-05, + "loss": 3.484, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934836601778216e-05, + "loss": 3.4787, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.592646703307143e-05, + "loss": 3.4814, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.591808108556091e-05, + "loss": 3.4877, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.590969513805039e-05, + "loss": 3.492, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.590130919053987e-05, + "loss": 3.4942, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892939621833078e-05, + "loss": 3.4818, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884553674322558e-05, + "loss": 3.4968, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.587616772681204e-05, + "loss": 3.4884, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.586778177930152e-05, + "loss": 3.4863, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.585941221059473e-05, + "loss": 3.4763, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.585102626308421e-05, + "loss": 3.4737, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.584264031557369e-05, + "loss": 3.5046, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583425436806317e-05, + "loss": 3.498, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825884799356382e-05, + "loss": 3.4858, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817498851845862e-05, + "loss": 3.4869, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580912928313907e-05, + "loss": 3.4867, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.580074333562855e-05, + "loss": 3.472, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.579235738811803e-05, + "loss": 3.4919, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.578397144060751e-05, + "loss": 3.4833, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775585493096995e-05, + "loss": 3.4889, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5767199545586468e-05, + "loss": 3.5001, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758813598075948e-05, + "loss": 3.4825, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750427650565428e-05, + "loss": 3.4749, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5742058081858644e-05, + "loss": 3.5007, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.573367213434812e-05, + "loss": 3.4693, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.57252861868376e-05, + "loss": 3.4769, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716916618130816e-05, + "loss": 3.4947, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570853067062029e-05, + "loss": 3.4923, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.570014472310977e-05, + "loss": 3.4803, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.569175877559925e-05, + "loss": 3.4757, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5683389206892465e-05, + "loss": 3.4744, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567500325938194e-05, + "loss": 3.4754, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566661731187142e-05, + "loss": 3.4943, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.56582313643609e-05, + "loss": 3.4766, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649861795654117e-05, + "loss": 3.4945, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641475848143594e-05, + "loss": 3.4888, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5633089900633074e-05, + "loss": 3.4961, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624703953122554e-05, + "loss": 3.4838, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5616334384415763e-05, + "loss": 3.4823, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607948436905243e-05, + "loss": 3.4899, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599562489394723e-05, + "loss": 3.4817, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5591176541884203e-05, + "loss": 3.4956, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582806973177415e-05, + "loss": 3.4867, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574421025666895e-05, + "loss": 3.4832, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5566035078156375e-05, + "loss": 3.4849, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557649130645855e-05, + "loss": 3.4704, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5549279561939064e-05, + "loss": 3.4827, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540893614428547e-05, + "loss": 3.4867, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532507666918027e-05, + "loss": 3.4911, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5524121719407507e-05, + "loss": 3.4798, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515752150700716e-05, + "loss": 3.4846, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507366203190196e-05, + "loss": 3.4787, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498980255679676e-05, + "loss": 3.4753, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490594308169156e-05, + "loss": 3.4735, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.548222473946237e-05, + "loss": 3.4835, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.547383879195185e-05, + "loss": 3.4979, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.546545284444133e-05, + "loss": 3.4939, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.545706689693081e-05, + "loss": 3.4855, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448697328224018e-05, + "loss": 3.4763, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.54403113807135e-05, + "loss": 3.4822, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.543192543320298e-05, + "loss": 3.4876, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542353948569246e-05, + "loss": 3.4898, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.541516991698567e-05, + "loss": 3.4929, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.540678396947515e-05, + "loss": 3.4853, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539839802196463e-05, + "loss": 3.4728, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.539001207445411e-05, + "loss": 3.4987, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381642505747322e-05, + "loss": 3.4756, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5373256558236802e-05, + "loss": 3.4866, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364870610726282e-05, + "loss": 3.4776, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5356484663215762e-05, + "loss": 3.4872, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.534811509450897e-05, + "loss": 3.477, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339729146998455e-05, + "loss": 3.4865, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5331343199487935e-05, + "loss": 3.4779, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322957251977415e-05, + "loss": 3.4783, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314587683270624e-05, + "loss": 3.4868, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5306201735760104e-05, + "loss": 3.4786, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297815788249584e-05, + "loss": 3.4934, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5289429840739064e-05, + "loss": 3.4991, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5281060272032276e-05, + "loss": 3.49, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272674324521756e-05, + "loss": 3.4844, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5264288377011236e-05, + "loss": 3.4833, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255902429500716e-05, + "loss": 3.4774, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247532860793925e-05, + "loss": 3.4767, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.523914691328341e-05, + "loss": 3.4888, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.523076096577289e-05, + "loss": 3.4699, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.522237501826237e-05, + "loss": 3.4855, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5214005449555577e-05, + "loss": 3.4831, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205619502045057e-05, + "loss": 3.4878, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5197233554534537e-05, + "loss": 3.4832, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188847607024017e-05, + "loss": 3.4809, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.518047803831723e-05, + "loss": 3.482, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517209209080671e-05, + "loss": 3.4878, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516370614329619e-05, + "loss": 3.4845, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.515532019578567e-05, + "loss": 3.4945, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.514695062707888e-05, + "loss": 3.4741, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138564679568362e-05, + "loss": 3.486, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5130178732057842e-05, + "loss": 3.4843, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.512180916335105e-05, + "loss": 3.4831, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511342321584053e-05, + "loss": 3.4817, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510503726833001e-05, + "loss": 3.4947, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.509665132081949e-05, + "loss": 3.4842, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5088281752112704e-05, + "loss": 3.5011, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079895804602183e-05, + "loss": 3.4819, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071509857091663e-05, + "loss": 3.487, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5063123909581143e-05, + "loss": 3.4801, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054754340874352e-05, + "loss": 3.4807, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5046368393363832e-05, + "loss": 3.4807, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037982445853312e-05, + "loss": 3.4844, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029596498342796e-05, + "loss": 3.481, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5021226929636005e-05, + "loss": 3.4744, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012840982125485e-05, + "loss": 3.4805, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8549447059631348, + "eval_runtime": 304.1507, + "eval_samples_per_second": 1254.612, + "eval_steps_per_second": 39.208, + "step": 1526389 + }, + { + "epoch": 1.0, + "learning_rate": 2.5004455034614965e-05, + "loss": 3.4833, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.4996069087104445e-05, + "loss": 3.4802, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4987699518397657e-05, + "loss": 3.4895, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4979313570887137e-05, + "loss": 3.4847, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4970927623376617e-05, + "loss": 3.4994, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4962541675866097e-05, + "loss": 3.4832, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4954172107159306e-05, + "loss": 3.481, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4945786159648786e-05, + "loss": 3.4671, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4937400212138266e-05, + "loss": 3.4831, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.492901426462775e-05, + "loss": 3.4813, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.492064469592096e-05, + "loss": 3.479, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.491225874841044e-05, + "loss": 3.4816, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.490387280089992e-05, + "loss": 3.4698, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.48954868533894e-05, + "loss": 3.48, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.488711728468261e-05, + "loss": 3.4727, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.487873133717209e-05, + "loss": 3.4718, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.487034538966157e-05, + "loss": 3.4708, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.486195944215105e-05, + "loss": 3.4804, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.485358987344426e-05, + "loss": 3.473, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.484520392593374e-05, + "loss": 3.4993, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.483681797842322e-05, + "loss": 3.48, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.48284320309127e-05, + "loss": 3.4871, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4820062462205912e-05, + "loss": 3.4772, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4811676514695392e-05, + "loss": 3.4858, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4803290567184872e-05, + "loss": 3.4809, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.479490461967435e-05, + "loss": 3.4871, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786535050967565e-05, + "loss": 3.4741, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4778149103457044e-05, + "loss": 3.4786, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4769763155946524e-05, + "loss": 3.4708, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4761377208436e-05, + "loss": 3.4787, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4753007639729213e-05, + "loss": 3.4864, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4744621692218693e-05, + "loss": 3.4784, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4736235744708173e-05, + "loss": 3.4922, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727849797197653e-05, + "loss": 3.4817, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719480228490866e-05, + "loss": 3.4752, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4711094280980346e-05, + "loss": 3.4853, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.4702708333469822e-05, + "loss": 3.4816, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4694322385959302e-05, + "loss": 3.4714, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4685952817252518e-05, + "loss": 3.4672, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4677566869741998e-05, + "loss": 3.4687, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4669180922231475e-05, + "loss": 3.4738, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4660794974720955e-05, + "loss": 3.4819, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.4652425406014167e-05, + "loss": 3.4816, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.4644039458503647e-05, + "loss": 3.4697, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.4635653510993127e-05, + "loss": 3.4789, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4627267563482607e-05, + "loss": 3.4785, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461889799477582e-05, + "loss": 3.4742, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4610512047265296e-05, + "loss": 3.4669, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4602126099754776e-05, + "loss": 3.4564, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4593740152244256e-05, + "loss": 3.4938, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4585370583537472e-05, + "loss": 3.4838, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.457698463602695e-05, + "loss": 3.4785, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456859868851643e-05, + "loss": 3.4755, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.456022911980964e-05, + "loss": 3.4699, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551843172299117e-05, + "loss": 3.4632, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.45434572247886e-05, + "loss": 3.4764, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.453507127727808e-05, + "loss": 3.4752, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.452668532976756e-05, + "loss": 3.4758, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.451829938225704e-05, + "loss": 3.4908, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.450991343474652e-05, + "loss": 3.4692, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4501527487236e-05, + "loss": 3.4629, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.449315791852921e-05, + "loss": 3.4884, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.448477197101869e-05, + "loss": 3.4612, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4476386023508173e-05, + "loss": 3.4651, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4468016454801382e-05, + "loss": 3.4829, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4459630507290862e-05, + "loss": 3.4786, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4451244559780342e-05, + "loss": 3.4704, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442858612269822e-05, + "loss": 3.4636, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4434489043563034e-05, + "loss": 3.4611, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4426103096052514e-05, + "loss": 3.4644, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4417717148541994e-05, + "loss": 3.4817, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4409331201031474e-05, + "loss": 3.4654, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4400961632324683e-05, + "loss": 3.4812, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4392575684814163e-05, + "loss": 3.476, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4384189737303643e-05, + "loss": 3.4894, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375803789793123e-05, + "loss": 3.4701, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367434221086336e-05, + "loss": 3.4704, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4359048273575816e-05, + "loss": 3.4775, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4350662326065296e-05, + "loss": 3.4648, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4342276378554772e-05, + "loss": 3.4871, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333906809847988e-05, + "loss": 3.4739, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4325520862337468e-05, + "loss": 3.4721, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4317134914826948e-05, + "loss": 3.4741, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4308748967316425e-05, + "loss": 3.4614, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4300379398609637e-05, + "loss": 3.4667, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4291993451099117e-05, + "loss": 3.4717, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4283607503588597e-05, + "loss": 3.4795, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4275221556078077e-05, + "loss": 3.4656, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.426685198737129e-05, + "loss": 3.474, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.425846603986077e-05, + "loss": 3.4664, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4250080092350246e-05, + "loss": 3.4652, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4241694144839726e-05, + "loss": 3.4608, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4233324576132942e-05, + "loss": 3.4691, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4224938628622422e-05, + "loss": 3.4842, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4216552681111898e-05, + "loss": 3.4814, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4208166733601378e-05, + "loss": 3.477, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.419979716489459e-05, + "loss": 3.4665, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.419141121738407e-05, + "loss": 3.4696, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.418302526987355e-05, + "loss": 3.4705, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.417463932236303e-05, + "loss": 3.4811, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4166269753656243e-05, + "loss": 3.4798, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.415788380614572e-05, + "loss": 3.4708, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.41494978586352e-05, + "loss": 3.4642, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.414111191112468e-05, + "loss": 3.4882, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132742342417895e-05, + "loss": 3.4626, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4124356394907372e-05, + "loss": 3.4754, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.4115970447396852e-05, + "loss": 3.4666, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4107584499886332e-05, + "loss": 3.4743, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.409921493117954e-05, + "loss": 3.4625, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.409082898366902e-05, + "loss": 3.4786, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4082443036158504e-05, + "loss": 3.4613, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4074057088647984e-05, + "loss": 3.4711, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4065687519941193e-05, + "loss": 3.4741, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4057301572430673e-05, + "loss": 3.4714, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4048915624920153e-05, + "loss": 3.4784, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4040529677409633e-05, + "loss": 3.4887, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4032160108702846e-05, + "loss": 3.4749, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023774161192326e-05, + "loss": 3.4751, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4015388213681806e-05, + "loss": 3.4725, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4007002266171286e-05, + "loss": 3.4669, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3998632697464495e-05, + "loss": 3.4636, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3990246749953975e-05, + "loss": 3.4802, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3981860802443458e-05, + "loss": 3.4563, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3973474854932938e-05, + "loss": 3.4729, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3965105286226147e-05, + "loss": 3.4673, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3956719338715627e-05, + "loss": 3.4769, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3948333391205107e-05, + "loss": 3.4697, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3939947443694587e-05, + "loss": 3.4712, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.39315778749878e-05, + "loss": 3.4668, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.392319192747728e-05, + "loss": 3.4793, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.391480597996676e-05, + "loss": 3.4699, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.390642003245624e-05, + "loss": 3.4836, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.389805046374945e-05, + "loss": 3.4601, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3889664516238928e-05, + "loss": 3.473, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.388127856872841e-05, + "loss": 3.4734, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.387290900002162e-05, + "loss": 3.4721, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.38645230525111e-05, + "loss": 3.47, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385613710500058e-05, + "loss": 3.4821, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384775115749006e-05, + "loss": 3.4721, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3839381588783273e-05, + "loss": 3.4924, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3830995641272753e-05, + "loss": 3.4687, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822609693762233e-05, + "loss": 3.4744, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3814223746251713e-05, + "loss": 3.4678, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3805854177544922e-05, + "loss": 3.4683, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3797468230034402e-05, + "loss": 3.4733, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3789082282523882e-05, + "loss": 3.4699, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780696335013365e-05, + "loss": 3.472, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3772326766306574e-05, + "loss": 3.4585, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3763940818796054e-05, + "loss": 3.4714, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.857028007507324, + "eval_runtime": 312.6878, + "eval_samples_per_second": 1220.358, + "eval_steps_per_second": 38.137, + "step": 1602709 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755554871285534e-05, + "loss": 3.4721, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3747168923775014e-05, + "loss": 3.4685, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738782976264494e-05, + "loss": 3.4757, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730397028753974e-05, + "loss": 3.4746, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3722027460047187e-05, + "loss": 3.4817, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713641512536667e-05, + "loss": 3.4741, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3705255565026143e-05, + "loss": 3.4684, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696869617515623e-05, + "loss": 3.4611, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3688500048808836e-05, + "loss": 3.4684, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.368011410129832e-05, + "loss": 3.4712, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671728153787796e-05, + "loss": 3.4708, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663342206277275e-05, + "loss": 3.4668, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654972637570488e-05, + "loss": 3.4633, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646586690059965e-05, + "loss": 3.463, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3638200742549444e-05, + "loss": 3.4615, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629814795038928e-05, + "loss": 3.4573, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.362144522633214e-05, + "loss": 3.461, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3613059278821617e-05, + "loss": 3.4684, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604673331311097e-05, + "loss": 3.4644, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596287383800577e-05, + "loss": 3.4838, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.358791781509379e-05, + "loss": 3.4714, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357953186758327e-05, + "loss": 3.4764, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.357114592007275e-05, + "loss": 3.4642, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356277635136596e-05, + "loss": 3.4731, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554390403855438e-05, + "loss": 3.4674, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3546004456344918e-05, + "loss": 3.479, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537618508834398e-05, + "loss": 3.466, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3529248940127614e-05, + "loss": 3.4641, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.352086299261709e-05, + "loss": 3.46, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351247704510657e-05, + "loss": 3.4679, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350409109759605e-05, + "loss": 3.4712, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495721528889263e-05, + "loss": 3.4717, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3487335581378743e-05, + "loss": 3.4766, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478949633868223e-05, + "loss": 3.4724, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470563686357703e-05, + "loss": 3.4627, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3462194117650912e-05, + "loss": 3.4769, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3453808170140392e-05, + "loss": 3.4699, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3445422222629872e-05, + "loss": 3.4588, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3437036275119352e-05, + "loss": 3.4578, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428666706412564e-05, + "loss": 3.4538, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420280758902044e-05, + "loss": 3.4595, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411894811391524e-05, + "loss": 3.4745, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403508863881004e-05, + "loss": 3.4698, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3395139295174213e-05, + "loss": 3.4589, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386753347663697e-05, + "loss": 3.4685, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378367400153177e-05, + "loss": 3.4638, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369981452642657e-05, + "loss": 3.4668, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361611883935866e-05, + "loss": 3.4542, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3353225936425346e-05, + "loss": 3.442, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344839988914826e-05, + "loss": 3.4865, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3336454041404305e-05, + "loss": 3.4701, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3328084472697518e-05, + "loss": 3.4684, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319698525186998e-05, + "loss": 3.4586, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.331132895648021e-05, + "loss": 3.4643, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302943008969687e-05, + "loss": 3.4511, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294557061459167e-05, + "loss": 3.4618, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328617111394865e-05, + "loss": 3.463, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327778516643813e-05, + "loss": 3.4647, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326939921892761e-05, + "loss": 3.4766, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.326101327141709e-05, + "loss": 3.4594, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252627323906567e-05, + "loss": 3.4519, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.324425775519978e-05, + "loss": 3.4793, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.323587180768926e-05, + "loss": 3.4474, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3227485860178742e-05, + "loss": 3.4516, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321909991266822e-05, + "loss": 3.469, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321073034396143e-05, + "loss": 3.4729, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.320234439645091e-05, + "loss": 3.4523, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319395844894039e-05, + "loss": 3.4575, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185588880233604e-05, + "loss": 3.4459, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3177202932723084e-05, + "loss": 3.4552, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168816985212564e-05, + "loss": 3.4676, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.316043103770204e-05, + "loss": 3.4519, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3152061468995253e-05, + "loss": 3.4688, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3143675521484733e-05, + "loss": 3.4641, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3135289573974213e-05, + "loss": 3.4769, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126903626463693e-05, + "loss": 3.4578, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118534057756905e-05, + "loss": 3.4639, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3110148110246385e-05, + "loss": 3.4643, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101762162735862e-05, + "loss": 3.454, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3093376215225342e-05, + "loss": 3.4717, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3085006646518558e-05, + "loss": 3.4648, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076620699008038e-05, + "loss": 3.4648, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3068234751497514e-05, + "loss": 3.4637, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059848803986994e-05, + "loss": 3.4503, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051479235280207e-05, + "loss": 3.4526, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3043093287769687e-05, + "loss": 3.4627, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034707340259166e-05, + "loss": 3.4679, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3026321392748646e-05, + "loss": 3.4539, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.301795182404186e-05, + "loss": 3.4624, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009565876531335e-05, + "loss": 3.4529, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3001179929020815e-05, + "loss": 3.4551, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992793981510295e-05, + "loss": 3.4497, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298442441280351e-05, + "loss": 3.4613, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2976038465292988e-05, + "loss": 3.4731, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967652517782468e-05, + "loss": 3.466, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2959266570271948e-05, + "loss": 3.4653, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.295089700156516e-05, + "loss": 3.4556, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942511054054637e-05, + "loss": 3.459, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.293412510654412e-05, + "loss": 3.4616, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.29257391590336e-05, + "loss": 3.4694, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291736959032681e-05, + "loss": 3.4641, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.290898364281629e-05, + "loss": 3.4628, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.290059769530577e-05, + "loss": 3.4578, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.289221174779525e-05, + "loss": 3.4746, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288384217908846e-05, + "loss": 3.4515, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287545623157794e-05, + "loss": 3.4603, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286707028406742e-05, + "loss": 3.4525, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.28586843365569e-05, + "loss": 3.4674, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.285031476785011e-05, + "loss": 3.4522, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.284192882033959e-05, + "loss": 3.4627, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833542872829074e-05, + "loss": 3.4503, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2825156925318554e-05, + "loss": 3.4584, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816787356611763e-05, + "loss": 3.4618, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2808401409101243e-05, + "loss": 3.4589, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2800015461590723e-05, + "loss": 3.468, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2791629514080203e-05, + "loss": 3.475, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2783259945373415e-05, + "loss": 3.4641, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774873997862895e-05, + "loss": 3.466, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766488050352375e-05, + "loss": 3.4572, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2758102102841855e-05, + "loss": 3.4528, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749732534135064e-05, + "loss": 3.4584, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2741346586624544e-05, + "loss": 3.4672, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732960639114027e-05, + "loss": 3.4443, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724574691603507e-05, + "loss": 3.4607, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2716205122896717e-05, + "loss": 3.4597, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707819175386196e-05, + "loss": 3.4627, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699433227875676e-05, + "loss": 3.4619, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.269106365916889e-05, + "loss": 3.4583, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.268267771165837e-05, + "loss": 3.4589, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267429176414785e-05, + "loss": 3.4658, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.266590581663733e-05, + "loss": 3.4631, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657536247930538e-05, + "loss": 3.4724, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2649150300420018e-05, + "loss": 3.4504, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640764352909498e-05, + "loss": 3.4627, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.263237840539898e-05, + "loss": 3.4624, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262400883669219e-05, + "loss": 3.4596, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261562288918167e-05, + "loss": 3.4609, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260723694167115e-05, + "loss": 3.4667, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.259885099416063e-05, + "loss": 3.4615, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590481425453843e-05, + "loss": 3.4819, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2582095477943323e-05, + "loss": 3.46, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573709530432803e-05, + "loss": 3.4599, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2565323582922282e-05, + "loss": 3.4562, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255695401421549e-05, + "loss": 3.4634, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.254856806670497e-05, + "loss": 3.4543, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.254018211919445e-05, + "loss": 3.4593, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531796171683935e-05, + "loss": 3.4631, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523426602977144e-05, + "loss": 3.4418, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2515040655466624e-05, + "loss": 3.4625, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8584563732147217, + "eval_runtime": 308.823, + "eval_samples_per_second": 1235.63, + "eval_steps_per_second": 38.614, + "step": 1679029 + }, + { + "epoch": 1.0, + "learning_rate": 2.2506654707956104e-05, + "loss": 3.4636, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2498268760445584e-05, + "loss": 3.4601, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489899191738796e-05, + "loss": 3.4609, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481513244228276e-05, + "loss": 3.4609, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2473127296717756e-05, + "loss": 3.4743, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464741349207233e-05, + "loss": 3.4586, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2456371780500445e-05, + "loss": 3.4632, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2447985832989925e-05, + "loss": 3.4465, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2439599885479405e-05, + "loss": 3.4571, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2431213937968885e-05, + "loss": 3.4598, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422844369262098e-05, + "loss": 3.4599, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2414458421751578e-05, + "loss": 3.456, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2406072474241057e-05, + "loss": 3.451, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397686526730534e-05, + "loss": 3.4512, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.238931695802375e-05, + "loss": 3.454, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.238093101051323e-05, + "loss": 3.4458, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2372545063002706e-05, + "loss": 3.4499, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2364159115492186e-05, + "loss": 3.4527, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.23557895467854e-05, + "loss": 3.4565, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.234740359927488e-05, + "loss": 3.4696, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233901765176436e-05, + "loss": 3.4617, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.233063170425384e-05, + "loss": 3.4682, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.232226213554705e-05, + "loss": 3.451, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231387618803653e-05, + "loss": 3.4608, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305490240526008e-05, + "loss": 3.4582, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2297104293015488e-05, + "loss": 3.4665, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.22887347243087e-05, + "loss": 3.4528, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.228034877679818e-05, + "loss": 3.4553, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.227196282928766e-05, + "loss": 3.4474, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263593260580873e-05, + "loss": 3.4543, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2255207313070353e-05, + "loss": 3.4571, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.224682136555983e-05, + "loss": 3.4672, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238435418049312e-05, + "loss": 3.4623, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2230049470538792e-05, + "loss": 3.4635, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221663523028272e-05, + "loss": 3.4552, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2213277575517752e-05, + "loss": 3.4582, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2204891628007232e-05, + "loss": 3.4573, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.219652205930044e-05, + "loss": 3.4508, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.218813611178992e-05, + "loss": 3.447, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179750164279405e-05, + "loss": 3.4432, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171364216768885e-05, + "loss": 3.4509, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162994648062094e-05, + "loss": 3.4592, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2154608700551574e-05, + "loss": 3.4582, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2146222753041054e-05, + "loss": 3.4506, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2137836805530534e-05, + "loss": 3.4544, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2129467236823746e-05, + "loss": 3.4558, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2121081289313226e-05, + "loss": 3.4513, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112695341802706e-05, + "loss": 3.4458, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2104325773095915e-05, + "loss": 3.4299, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2095939825585395e-05, + "loss": 3.4717, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2087553878074875e-05, + "loss": 3.4554, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.207916793056436e-05, + "loss": 3.4633, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070798361857567e-05, + "loss": 3.4496, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2062428793150777e-05, + "loss": 3.4501, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2054042845640257e-05, + "loss": 3.4407, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045656898129736e-05, + "loss": 3.4493, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203727095061922e-05, + "loss": 3.4582, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.20288850031087e-05, + "loss": 3.4474, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.202049905559818e-05, + "loss": 3.4701, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.201211310808766e-05, + "loss": 3.4465, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003727160577136e-05, + "loss": 3.4397, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.199535759187035e-05, + "loss": 3.4665, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198697164435983e-05, + "loss": 3.4369, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197858569684931e-05, + "loss": 3.4378, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.197019974933879e-05, + "loss": 3.4608, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961830180632e-05, + "loss": 3.4587, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.195344423312148e-05, + "loss": 3.4401, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1945058285610958e-05, + "loss": 3.4499, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936672338100438e-05, + "loss": 3.4354, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928302769393653e-05, + "loss": 3.4477, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919916821883133e-05, + "loss": 3.4544, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.191153087437261e-05, + "loss": 3.4431, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1903161305665822e-05, + "loss": 3.4564, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894775358155302e-05, + "loss": 3.4574, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1886389410644782e-05, + "loss": 3.4655, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1878003463134262e-05, + "loss": 3.4477, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869633894427475e-05, + "loss": 3.4506, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1861247946916955e-05, + "loss": 3.4572, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.185286199940643e-05, + "loss": 3.443, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.184447605189591e-05, + "loss": 3.4591, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1836106483189124e-05, + "loss": 3.4548, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827720535678607e-05, + "loss": 3.45, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1819334588168084e-05, + "loss": 3.4564, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810948640657564e-05, + "loss": 3.4371, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1802579071950776e-05, + "loss": 3.4428, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1794193124440253e-05, + "loss": 3.4527, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1785807176929736e-05, + "loss": 3.4566, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1777421229419216e-05, + "loss": 3.4436, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.176905166071243e-05, + "loss": 3.4512, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760665713201905e-05, + "loss": 3.4392, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1752279765691385e-05, + "loss": 3.4464, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1743893818180865e-05, + "loss": 3.4387, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1735524249474077e-05, + "loss": 3.4483, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1727138301963557e-05, + "loss": 3.4653, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1718752354453037e-05, + "loss": 3.4511, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1710366406942517e-05, + "loss": 3.4525, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701996838235726e-05, + "loss": 3.4469, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1693610890725206e-05, + "loss": 3.4468, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168522494321469e-05, + "loss": 3.4476, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167683899570417e-05, + "loss": 3.4596, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166846942699738e-05, + "loss": 3.4546, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.166008347948686e-05, + "loss": 3.4559, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.165169753197634e-05, + "loss": 3.4394, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.164331158446582e-05, + "loss": 3.4613, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163494201575903e-05, + "loss": 3.4453, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162655606824851e-05, + "loss": 3.4525, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161817012073799e-05, + "loss": 3.4351, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160978417322747e-05, + "loss": 3.4572, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.160141460452068e-05, + "loss": 3.4404, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.159302865701016e-05, + "loss": 3.453, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584642709499643e-05, + "loss": 3.4394, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1576256761989123e-05, + "loss": 3.4526, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567887193282332e-05, + "loss": 3.4492, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559501245771812e-05, + "loss": 3.4446, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1551115298261292e-05, + "loss": 3.4567, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542729350750772e-05, + "loss": 3.4592, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1534359782043985e-05, + "loss": 3.4548, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525973834533465e-05, + "loss": 3.4547, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517587887022945e-05, + "loss": 3.4474, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1509201939512425e-05, + "loss": 3.4427, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1500832370805634e-05, + "loss": 3.4453, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1492446423295114e-05, + "loss": 3.4531, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1484060475784597e-05, + "loss": 3.4359, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475674528274077e-05, + "loss": 3.449, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1467304959567286e-05, + "loss": 3.4506, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458919012056766e-05, + "loss": 3.4525, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1450533064546246e-05, + "loss": 3.4484, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1442147117035726e-05, + "loss": 3.4502, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143377754832894e-05, + "loss": 3.4455, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.142539160081842e-05, + "loss": 3.4577, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.14170056533079e-05, + "loss": 3.4521, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408636084601107e-05, + "loss": 3.4565, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1400250137090587e-05, + "loss": 3.4418, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391864189580067e-05, + "loss": 3.4542, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1383478242069547e-05, + "loss": 3.451, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137510867336276e-05, + "loss": 3.4466, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.136672272585224e-05, + "loss": 3.449, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.135833677834172e-05, + "loss": 3.4537, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.13499508308312e-05, + "loss": 3.4514, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1341581262124412e-05, + "loss": 3.4695, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1333195314613892e-05, + "loss": 3.4467, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324809367103372e-05, + "loss": 3.4522, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1316423419592852e-05, + "loss": 3.4467, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.130805385088606e-05, + "loss": 3.4511, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.129966790337554e-05, + "loss": 3.4447, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.129128195586502e-05, + "loss": 3.446, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.12828960083545e-05, + "loss": 3.451, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1274526439647713e-05, + "loss": 3.4305, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1266140492137193e-05, + "loss": 3.4532, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.86088490486145, + "eval_runtime": 308.0847, + "eval_samples_per_second": 1238.591, + "eval_steps_per_second": 38.707, + "step": 1755349 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257754544626673e-05, + "loss": 3.4539, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124936859711615e-05, + "loss": 3.4452, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.124098264960563e-05, + "loss": 3.4507, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232596702095113e-05, + "loss": 3.4524, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1224227133388326e-05, + "loss": 3.4592, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215841185877802e-05, + "loss": 3.4499, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207455238367282e-05, + "loss": 3.4526, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1199069290856762e-05, + "loss": 3.4392, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190699722149975e-05, + "loss": 3.443, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1182313774639455e-05, + "loss": 3.4505, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173927827128935e-05, + "loss": 3.4475, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165541879618415e-05, + "loss": 3.4417, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1157172310911624e-05, + "loss": 3.4464, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148786363401104e-05, + "loss": 3.437, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1140400415890584e-05, + "loss": 3.4396, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1132014468380067e-05, + "loss": 3.4386, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123644899673276e-05, + "loss": 3.4338, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1115258952162756e-05, + "loss": 3.4485, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106873004652236e-05, + "loss": 3.4388, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098487057141716e-05, + "loss": 3.4593, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.109011748843493e-05, + "loss": 3.4521, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081731540924408e-05, + "loss": 3.4559, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1073345593413888e-05, + "loss": 3.4408, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064976024707097e-05, + "loss": 3.4475, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056590077196577e-05, + "loss": 3.4495, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1048204129686057e-05, + "loss": 3.4566, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039818182175537e-05, + "loss": 3.4415, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.103144861346875e-05, + "loss": 3.446, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102306266595823e-05, + "loss": 3.4356, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1014693097251442e-05, + "loss": 3.4437, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100630714974092e-05, + "loss": 3.4443, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.09979212022304e-05, + "loss": 3.4562, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989535254719882e-05, + "loss": 3.4511, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0981149307209362e-05, + "loss": 3.4545, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972763359698842e-05, + "loss": 3.4451, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0964377412188322e-05, + "loss": 3.447, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955991464677802e-05, + "loss": 3.4505, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094762189597101e-05, + "loss": 3.4405, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093923594846049e-05, + "loss": 3.4352, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.093085000094997e-05, + "loss": 3.4299, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922464053439454e-05, + "loss": 3.4392, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0914094484732663e-05, + "loss": 3.4433, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905708537222143e-05, + "loss": 3.4468, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0897322589711623e-05, + "loss": 3.4431, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.08889366422011e-05, + "loss": 3.4429, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880567073494316e-05, + "loss": 3.4451, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0872181125983796e-05, + "loss": 3.4433, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863795178473276e-05, + "loss": 3.4342, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0855409230962752e-05, + "loss": 3.421, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0847039662255965e-05, + "loss": 3.4569, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838653714745445e-05, + "loss": 3.4467, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0830267767234925e-05, + "loss": 3.4544, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821898198528137e-05, + "loss": 3.4387, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813528629821346e-05, + "loss": 3.4399, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0805142682310826e-05, + "loss": 3.4295, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796756734800306e-05, + "loss": 3.4396, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0788370787289786e-05, + "loss": 3.449, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.077998483977927e-05, + "loss": 3.4328, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.077159889226875e-05, + "loss": 3.4606, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0763212944758226e-05, + "loss": 3.4409, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754826997247706e-05, + "loss": 3.4234, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746457428540918e-05, + "loss": 3.4559, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0738071481030398e-05, + "loss": 3.4284, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729685533519878e-05, + "loss": 3.4255, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0721299586009358e-05, + "loss": 3.4515, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.071293001730257e-05, + "loss": 3.4467, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704544069792047e-05, + "loss": 3.4284, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0696158122281527e-05, + "loss": 3.4364, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687772174771007e-05, + "loss": 3.427, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679402606064223e-05, + "loss": 3.4355, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.06710166585537e-05, + "loss": 3.442, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.066263071104318e-05, + "loss": 3.4342, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065424476353266e-05, + "loss": 3.4473, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645875194825872e-05, + "loss": 3.4396, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637489247315352e-05, + "loss": 3.4516, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0629103299804832e-05, + "loss": 3.4365, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620717352294312e-05, + "loss": 3.4437, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.061234778358752e-05, + "loss": 3.4444, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603961836077e-05, + "loss": 3.4314, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.059557588856648e-05, + "loss": 3.45, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0587206319859693e-05, + "loss": 3.4447, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578820372349173e-05, + "loss": 3.437, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570434424838653e-05, + "loss": 3.4471, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0562048477328133e-05, + "loss": 3.4252, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553678908621346e-05, + "loss": 3.4304, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0545292961110822e-05, + "loss": 3.4431, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536907013600306e-05, + "loss": 3.4448, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528521066089786e-05, + "loss": 3.4335, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0520151497382995e-05, + "loss": 3.4411, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511765549872475e-05, + "loss": 3.427, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0503379602361955e-05, + "loss": 3.4326, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494993654851434e-05, + "loss": 3.4313, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0486624086144647e-05, + "loss": 3.4376, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0478238138634127e-05, + "loss": 3.4506, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469852191123607e-05, + "loss": 3.4428, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461466243613087e-05, + "loss": 3.4444, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0453096674906296e-05, + "loss": 3.4354, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444710727395776e-05, + "loss": 3.4382, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0436324779885256e-05, + "loss": 3.4345, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042793883237474e-05, + "loss": 3.448, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419569263667948e-05, + "loss": 3.4424, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0411183316157428e-05, + "loss": 3.4484, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402797368646908e-05, + "loss": 3.4287, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0394411421136388e-05, + "loss": 3.4471, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.03860418524296e-05, + "loss": 3.4377, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037765590491908e-05, + "loss": 3.4407, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036926995740856e-05, + "loss": 3.4256, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.036088400989804e-05, + "loss": 3.4474, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.035251444119125e-05, + "loss": 3.4299, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034412849368073e-05, + "loss": 3.4403, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033574254617021e-05, + "loss": 3.4257, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0327356598659693e-05, + "loss": 3.4415, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318987029952902e-05, + "loss": 3.4372, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310601082442382e-05, + "loss": 3.4324, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0302215134931862e-05, + "loss": 3.4465, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293829187421342e-05, + "loss": 3.4518, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285459618714554e-05, + "loss": 3.4466, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0277073671204034e-05, + "loss": 3.4436, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268687723693514e-05, + "loss": 3.4364, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0260301776182994e-05, + "loss": 3.4318, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0251932207476203e-05, + "loss": 3.4355, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0243546259965683e-05, + "loss": 3.4406, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0235160312455163e-05, + "loss": 3.4271, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226774364944647e-05, + "loss": 3.4391, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0218404796237856e-05, + "loss": 3.4415, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0210018848727336e-05, + "loss": 3.4381, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201632901216816e-05, + "loss": 3.4371, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0193246953706295e-05, + "loss": 3.4365, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184877384999508e-05, + "loss": 3.4348, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176491437488988e-05, + "loss": 3.4443, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0168105489978468e-05, + "loss": 3.4425, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159719542467944e-05, + "loss": 3.4452, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0151349973761157e-05, + "loss": 3.4271, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142964026250637e-05, + "loss": 3.446, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134578078740117e-05, + "loss": 3.4386, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.012620851003333e-05, + "loss": 3.4376, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.011782256252281e-05, + "loss": 3.4401, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.010943661501229e-05, + "loss": 3.4372, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.010105066750177e-05, + "loss": 3.4449, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092681098794978e-05, + "loss": 3.4597, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.008429515128446e-05, + "loss": 3.4359, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007590920377394e-05, + "loss": 3.4404, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067523256263418e-05, + "loss": 3.4425, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.005915368755663e-05, + "loss": 3.4389, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.005076774004611e-05, + "loss": 3.432, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.004238179253559e-05, + "loss": 3.4335, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.003399584502507e-05, + "loss": 3.4414, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025626276318283e-05, + "loss": 3.4229, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0017240328807763e-05, + "loss": 3.441, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8635284900665283, + "eval_runtime": 302.4446, + "eval_samples_per_second": 1261.689, + "eval_steps_per_second": 39.429, + "step": 1831669 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008854381297243e-05, + "loss": 3.44, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.000046843378672e-05, + "loss": 3.4363, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9992098865079932e-05, + "loss": 3.4383, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983712917569415e-05, + "loss": 3.4442, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9975326970058892e-05, + "loss": 3.4479, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9966941022548372e-05, + "loss": 3.4364, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9958571453841584e-05, + "loss": 3.4432, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9950185506331064e-05, + "loss": 3.4295, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.994179955882054e-05, + "loss": 3.4296, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9933413611310024e-05, + "loss": 3.4424, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9925044042603237e-05, + "loss": 3.4387, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916658095092717e-05, + "loss": 3.4291, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.9908272147582193e-05, + "loss": 3.4419, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9899886200071673e-05, + "loss": 3.4231, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9891516631364886e-05, + "loss": 3.4295, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9883130683854366e-05, + "loss": 3.4225, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874744736343846e-05, + "loss": 3.4298, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9866358788833325e-05, + "loss": 3.433, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9857989220126538e-05, + "loss": 3.4297, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9849603272616015e-05, + "loss": 3.4466, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9841217325105494e-05, + "loss": 3.443, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832831377594978e-05, + "loss": 3.4431, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9824461808888187e-05, + "loss": 3.4315, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9816075861377667e-05, + "loss": 3.437, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807689913867147e-05, + "loss": 3.4406, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9799303966356627e-05, + "loss": 3.4437, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.979093439764984e-05, + "loss": 3.4318, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.978254845013932e-05, + "loss": 3.4414, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.97741625026288e-05, + "loss": 3.4212, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.976577655511828e-05, + "loss": 3.4391, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9757406986411488e-05, + "loss": 3.4321, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9749021038900968e-05, + "loss": 3.4425, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740635091390448e-05, + "loss": 3.4432, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.973224914387993e-05, + "loss": 3.4454, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.972387957517314e-05, + "loss": 3.4302, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.971549362766262e-05, + "loss": 3.4356, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.97071076801521e-05, + "loss": 3.4411, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.969872173264158e-05, + "loss": 3.4275, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9690352163934793e-05, + "loss": 3.4273, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681966216424273e-05, + "loss": 3.4227, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673580268913753e-05, + "loss": 3.424, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9665194321403233e-05, + "loss": 3.4303, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656824752696442e-05, + "loss": 3.4385, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9648438805185922e-05, + "loss": 3.4342, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9640052857675402e-05, + "loss": 3.4276, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631666910164885e-05, + "loss": 3.4331, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9623297341458094e-05, + "loss": 3.4368, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614911393947574e-05, + "loss": 3.4232, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9606525446437054e-05, + "loss": 3.4116, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9598139498926534e-05, + "loss": 3.4429, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9589769930219747e-05, + "loss": 3.4372, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9581383982709227e-05, + "loss": 3.4412, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572998035198707e-05, + "loss": 3.4287, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564628466491916e-05, + "loss": 3.4299, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9556242518981396e-05, + "loss": 3.4224, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9547856571470876e-05, + "loss": 3.4256, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9539470623960355e-05, + "loss": 3.4401, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953108467644984e-05, + "loss": 3.4186, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522698728939315e-05, + "loss": 3.4495, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9514312781428795e-05, + "loss": 3.4305, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505926833918275e-05, + "loss": 3.4121, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9497557265211488e-05, + "loss": 3.445, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9489171317700964e-05, + "loss": 3.4247, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480785370190448e-05, + "loss": 3.4144, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9472399422679928e-05, + "loss": 3.4376, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.946402985397314e-05, + "loss": 3.4372, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455643906462617e-05, + "loss": 3.423, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9447257958952097e-05, + "loss": 3.4236, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438872011441577e-05, + "loss": 3.4135, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.943050244273479e-05, + "loss": 3.426, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.942211649522427e-05, + "loss": 3.434, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.941373054771375e-05, + "loss": 3.4213, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940534460020323e-05, + "loss": 3.4353, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396975031496438e-05, + "loss": 3.4292, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388589083985918e-05, + "loss": 3.4401, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.93802031364754e-05, + "loss": 3.4298, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.937181718896488e-05, + "loss": 3.4351, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936344762025809e-05, + "loss": 3.4292, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935506167274757e-05, + "loss": 3.4226, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934667572523705e-05, + "loss": 3.4408, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933828977772653e-05, + "loss": 3.4315, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329920209019743e-05, + "loss": 3.4291, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321534261509223e-05, + "loss": 3.4383, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9313148313998703e-05, + "loss": 3.4138, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304778745291912e-05, + "loss": 3.4207, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9296392797781392e-05, + "loss": 3.4313, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9288006850270872e-05, + "loss": 3.4341, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279620902760355e-05, + "loss": 3.4202, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9271251334053564e-05, + "loss": 3.4356, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262865386543044e-05, + "loss": 3.421, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9254479439032524e-05, + "loss": 3.4228, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9246093491522004e-05, + "loss": 3.419, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9237723922815216e-05, + "loss": 3.4262, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9229337975304696e-05, + "loss": 3.4407, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9220952027794176e-05, + "loss": 3.4315, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212566080283656e-05, + "loss": 3.4324, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9204196511576865e-05, + "loss": 3.4247, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9195810564066345e-05, + "loss": 3.4262, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9187424616555825e-05, + "loss": 3.4272, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.917903866904531e-05, + "loss": 3.4352, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170669100338518e-05, + "loss": 3.4285, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9162283152827998e-05, + "loss": 3.4358, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153897205317478e-05, + "loss": 3.4277, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145511257806958e-05, + "loss": 3.4299, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913714168910017e-05, + "loss": 3.4289, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912875574158965e-05, + "loss": 3.4285, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.912036979407913e-05, + "loss": 3.4164, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.911198384656861e-05, + "loss": 3.436, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.910361427786182e-05, + "loss": 3.4194, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.90952283303513e-05, + "loss": 3.4261, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.908684238284078e-05, + "loss": 3.4206, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9078456435330262e-05, + "loss": 3.425, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.907008686662347e-05, + "loss": 3.4305, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.906170091911295e-05, + "loss": 3.4233, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.905331497160243e-05, + "loss": 3.4364, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.904492902409191e-05, + "loss": 3.4427, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036559455385124e-05, + "loss": 3.4335, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9028173507874604e-05, + "loss": 3.4325, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019787560364084e-05, + "loss": 3.4292, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9011401612853564e-05, + "loss": 3.4221, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9003032044146773e-05, + "loss": 3.4279, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994646096636253e-05, + "loss": 3.4268, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8986260149125733e-05, + "loss": 3.4194, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977874201615213e-05, + "loss": 3.4247, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8969504632908425e-05, + "loss": 3.4294, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8961118685397905e-05, + "loss": 3.4294, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8952732737887385e-05, + "loss": 3.4274, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894434679037686e-05, + "loss": 3.4264, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935977221670077e-05, + "loss": 3.424, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927591274159557e-05, + "loss": 3.434, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8919205326649037e-05, + "loss": 3.4295, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910819379138514e-05, + "loss": 3.4401, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8902449810431726e-05, + "loss": 3.4205, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8894063862921206e-05, + "loss": 3.4304, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8885677915410686e-05, + "loss": 3.4306, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8877291967900166e-05, + "loss": 3.4286, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886892239919338e-05, + "loss": 3.4265, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.886053645168286e-05, + "loss": 3.4304, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8852150504172335e-05, + "loss": 3.4319, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843780935465548e-05, + "loss": 3.4491, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.883539498795503e-05, + "loss": 3.4257, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882700904044451e-05, + "loss": 3.4339, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818623092933988e-05, + "loss": 3.4311, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.88102535242272e-05, + "loss": 3.4262, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.880186757671668e-05, + "loss": 3.4221, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793481629206157e-05, + "loss": 3.4225, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.878509568169564e-05, + "loss": 3.4278, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776726112988853e-05, + "loss": 3.419, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8768340165478332e-05, + "loss": 3.4268, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.863565444946289, + "eval_runtime": 302.2125, + "eval_samples_per_second": 1262.658, + "eval_steps_per_second": 39.459, + "step": 1907989 + }, + { + "epoch": 0.0, + "learning_rate": 1.875995421796781e-05, + "loss": 3.4336, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.875156827045729e-05, + "loss": 3.4257, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.874318232294677e-05, + "loss": 3.427, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.873479637543625e-05, + "loss": 3.433, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.872642680672946e-05, + "loss": 3.4401, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.871804085921894e-05, + "loss": 3.4303, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.870965491170842e-05, + "loss": 3.432, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.87012689641979e-05, + "loss": 3.4189, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.869289939549111e-05, + "loss": 3.4178, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684513447980594e-05, + "loss": 3.4322, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8676127500470074e-05, + "loss": 3.4273, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667741552959554e-05, + "loss": 3.4205, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8659371984252763e-05, + "loss": 3.4299, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8650986036742243e-05, + "loss": 3.4126, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8642616468035455e-05, + "loss": 3.4196, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8634230520524935e-05, + "loss": 3.4102, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625844573014415e-05, + "loss": 3.4213, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617458625503895e-05, + "loss": 3.428, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8609072677993375e-05, + "loss": 3.4149, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600686730482855e-05, + "loss": 3.4358, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8592300782972335e-05, + "loss": 3.4334, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858391483546181e-05, + "loss": 3.4324, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8575545266755027e-05, + "loss": 3.4225, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8567159319244507e-05, + "loss": 3.425, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558773371733987e-05, + "loss": 3.4313, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8550387424223464e-05, + "loss": 3.434, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8542017855516676e-05, + "loss": 3.4169, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533631908006156e-05, + "loss": 3.4279, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8525245960495636e-05, + "loss": 3.4145, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.851687639178885e-05, + "loss": 3.4241, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850849044427833e-05, + "loss": 3.4272, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.850010449676781e-05, + "loss": 3.4286, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491718549257285e-05, + "loss": 3.4283, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483332601746765e-05, + "loss": 3.4383, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847494665423625e-05, + "loss": 3.4229, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846656070672573e-05, + "loss": 3.4233, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.845817475921521e-05, + "loss": 3.4309, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449805190508417e-05, + "loss": 3.4151, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441419242997897e-05, + "loss": 3.4169, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8433033295487377e-05, + "loss": 3.4138, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424647347976857e-05, + "loss": 3.4149, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.841627777927007e-05, + "loss": 3.4179, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.840789183175955e-05, + "loss": 3.4339, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.839950588424903e-05, + "loss": 3.4204, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.839111993673851e-05, + "loss": 3.4186, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.838275036803172e-05, + "loss": 3.4194, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8374364420521202e-05, + "loss": 3.4293, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365978473010682e-05, + "loss": 3.4092, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357592525500162e-05, + "loss": 3.4037, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834922295679337e-05, + "loss": 3.431, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.834083700928285e-05, + "loss": 3.4281, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.833245106177233e-05, + "loss": 3.4334, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832406511426181e-05, + "loss": 3.4161, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315711924358756e-05, + "loss": 3.4162, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8307325976848233e-05, + "loss": 3.4124, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8298940029337713e-05, + "loss": 3.4145, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8290554081827193e-05, + "loss": 3.4314, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8282168134316672e-05, + "loss": 3.4078, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273782186806156e-05, + "loss": 3.4392, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265396239295636e-05, + "loss": 3.424, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8257010291785116e-05, + "loss": 3.3979, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8248640723078325e-05, + "loss": 3.4342, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8240254775567805e-05, + "loss": 3.4164, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231868828057285e-05, + "loss": 3.4021, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223482880546765e-05, + "loss": 3.4273, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8215113311839977e-05, + "loss": 3.4272, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206727364329457e-05, + "loss": 3.4114, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8198341416818937e-05, + "loss": 3.4151, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189955469308414e-05, + "loss": 3.4031, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181585900601626e-05, + "loss": 3.413, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.817319995309111e-05, + "loss": 3.4216, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.816481400558059e-05, + "loss": 3.4134, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156428058070066e-05, + "loss": 3.4279, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.814805848936328e-05, + "loss": 3.4149, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.813967254185276e-05, + "loss": 3.4307, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8131286594342235e-05, + "loss": 3.422, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.812290064683172e-05, + "loss": 3.4227, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.811453107812493e-05, + "loss": 3.418, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.810614513061441e-05, + "loss": 3.4144, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097759183103887e-05, + "loss": 3.4257, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089373235593367e-05, + "loss": 3.4198, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.808100366688658e-05, + "loss": 3.4207, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072617719376063e-05, + "loss": 3.4225, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8064248150669272e-05, + "loss": 3.4086, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055862203158752e-05, + "loss": 3.4064, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8047476255648232e-05, + "loss": 3.4202, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.803909030813771e-05, + "loss": 3.4266, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.803070436062719e-05, + "loss": 3.4096, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8022318413116672e-05, + "loss": 3.4201, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013932465606152e-05, + "loss": 3.4134, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005546518095632e-05, + "loss": 3.4085, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.799717694938884e-05, + "loss": 3.4094, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.798879100187832e-05, + "loss": 3.4171, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.79804050543678e-05, + "loss": 3.4288, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.797201910685728e-05, + "loss": 3.4204, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963649538150493e-05, + "loss": 3.4225, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7955263590639973e-05, + "loss": 3.414, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946877643129453e-05, + "loss": 3.4158, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7938491695618933e-05, + "loss": 3.4166, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7930122126912142e-05, + "loss": 3.4272, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921736179401626e-05, + "loss": 3.4209, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7913350231891106e-05, + "loss": 3.4245, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904964284380586e-05, + "loss": 3.4159, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896578336870066e-05, + "loss": 3.4174, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7888192389359542e-05, + "loss": 3.4227, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879806441849022e-05, + "loss": 3.417, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7871420494338502e-05, + "loss": 3.4086, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7863050925631715e-05, + "loss": 3.421, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854664978121194e-05, + "loss": 3.4138, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7846279030610674e-05, + "loss": 3.4156, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837893083100154e-05, + "loss": 3.412, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829523514393363e-05, + "loss": 3.4096, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7821137566882843e-05, + "loss": 3.4206, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812751619372327e-05, + "loss": 3.4126, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804365671861807e-05, + "loss": 3.4247, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795996103155016e-05, + "loss": 3.4296, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787610155644496e-05, + "loss": 3.4244, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7779224208133976e-05, + "loss": 3.4212, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770838260623456e-05, + "loss": 3.4159, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762468691916668e-05, + "loss": 3.4117, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7754082744406148e-05, + "loss": 3.4176, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745696796895628e-05, + "loss": 3.4211, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7737310849385108e-05, + "loss": 3.4054, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728941280678317e-05, + "loss": 3.4153, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720571711971533e-05, + "loss": 3.4145, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7712185764461013e-05, + "loss": 3.4222, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770379981695049e-05, + "loss": 3.4145, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769541386943997e-05, + "loss": 3.4137, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.768702792192945e-05, + "loss": 3.4123, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767864197441893e-05, + "loss": 3.4271, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.767025602690841e-05, + "loss": 3.4173, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661886458201622e-05, + "loss": 3.4307, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7653500510691102e-05, + "loss": 3.4076, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7645114563180582e-05, + "loss": 3.4176, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636728615670062e-05, + "loss": 3.4233, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762835904696327e-05, + "loss": 3.4145, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.761997309945275e-05, + "loss": 3.4174, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611587151942234e-05, + "loss": 3.4159, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7603201204431714e-05, + "loss": 3.4227, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7594831635724923e-05, + "loss": 3.4335, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7586445688214403e-05, + "loss": 3.4172, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7578059740703883e-05, + "loss": 3.422, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569673793193363e-05, + "loss": 3.4211, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7561304224486576e-05, + "loss": 3.4159, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552918276976055e-05, + "loss": 3.4121, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544532329465535e-05, + "loss": 3.4151, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7536146381955015e-05, + "loss": 3.4176, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527776813248224e-05, + "loss": 3.4113, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7519390865737704e-05, + "loss": 3.4129, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8652753829956055, + "eval_runtime": 311.4179, + "eval_samples_per_second": 1225.334, + "eval_steps_per_second": 38.293, + "step": 1984309 + }, + { + "epoch": 1.0, + "learning_rate": 1.7511004918227188e-05, + "loss": 3.4179, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502618970716668e-05, + "loss": 3.4143, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7494249402009877e-05, + "loss": 3.4167, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485863454499357e-05, + "loss": 3.4243, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477477506988837e-05, + "loss": 3.4317, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7469091559478313e-05, + "loss": 3.4151, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.746072199077153e-05, + "loss": 3.4241, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.745233604326101e-05, + "loss": 3.4134, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.744395009575049e-05, + "loss": 3.408, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435564148239966e-05, + "loss": 3.4162, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7427194579533178e-05, + "loss": 3.423, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418808632022658e-05, + "loss": 3.4115, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.741042268451214e-05, + "loss": 3.4189, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7402036737001618e-05, + "loss": 3.4013, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.739368354709856e-05, + "loss": 3.4116, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.738529759958804e-05, + "loss": 3.3945, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.737691165207752e-05, + "loss": 3.4149, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368525704567003e-05, + "loss": 3.4152, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7360139757056483e-05, + "loss": 3.4056, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351753809545963e-05, + "loss": 3.4247, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734336786203544e-05, + "loss": 3.4215, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.733498191452492e-05, + "loss": 3.4199, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326612345818132e-05, + "loss": 3.4147, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7318226398307612e-05, + "loss": 3.4137, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309840450797092e-05, + "loss": 3.4243, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.730145450328657e-05, + "loss": 3.4253, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7293084934579784e-05, + "loss": 3.4031, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728469898706926e-05, + "loss": 3.4188, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727631303955874e-05, + "loss": 3.4047, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267943470851957e-05, + "loss": 3.4113, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259557523341437e-05, + "loss": 3.4177, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7251171575830913e-05, + "loss": 3.4156, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242785628320393e-05, + "loss": 3.4154, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7234399680809873e-05, + "loss": 3.4288, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7226013733299353e-05, + "loss": 3.414, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217627785788833e-05, + "loss": 3.415, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7209241838278313e-05, + "loss": 3.4208, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200872269571525e-05, + "loss": 3.4048, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192486322061005e-05, + "loss": 3.4071, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7184100374550485e-05, + "loss": 3.4065, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7175714427039965e-05, + "loss": 3.4012, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7167344858333174e-05, + "loss": 3.4081, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158958910822658e-05, + "loss": 3.4224, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150572963312138e-05, + "loss": 3.409, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7142187015801618e-05, + "loss": 3.4095, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133817447094827e-05, + "loss": 3.4117, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125431499584307e-05, + "loss": 3.4161, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7117045552073787e-05, + "loss": 3.3986, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108659604563267e-05, + "loss": 3.3922, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.710029003585648e-05, + "loss": 3.4223, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709190408834596e-05, + "loss": 3.4173, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.708351814083544e-05, + "loss": 3.4243, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7075132193324915e-05, + "loss": 3.4059, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.706677900342186e-05, + "loss": 3.4054, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705839305591134e-05, + "loss": 3.4043, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.705000710840082e-05, + "loss": 3.4043, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.70416211608903e-05, + "loss": 3.4237, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703323521337978e-05, + "loss": 3.3927, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702484926586926e-05, + "loss": 3.4328, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016463318358737e-05, + "loss": 3.4114, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.700807737084822e-05, + "loss": 3.3915, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999707802141433e-05, + "loss": 3.4174, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6991321854630913e-05, + "loss": 3.4052, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.698293590712039e-05, + "loss": 3.3938, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.697454995960987e-05, + "loss": 3.4134, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.696618039090308e-05, + "loss": 3.418, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957794443392565e-05, + "loss": 3.3977, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6949424874685774e-05, + "loss": 3.4094, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6941038927175254e-05, + "loss": 3.3901, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932652979664734e-05, + "loss": 3.4037, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692426703215421e-05, + "loss": 3.4097, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691588108464369e-05, + "loss": 3.4049, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907495137133174e-05, + "loss": 3.4114, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6899109189622654e-05, + "loss": 3.4087, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890723242112134e-05, + "loss": 3.4207, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6882353673405343e-05, + "loss": 3.407, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873967725894823e-05, + "loss": 3.4196, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865581778384303e-05, + "loss": 3.4069, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6857195830873783e-05, + "loss": 3.4011, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848826262166995e-05, + "loss": 3.4156, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840440314656475e-05, + "loss": 3.4088, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6832054367145955e-05, + "loss": 3.4097, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823684798439164e-05, + "loss": 3.416, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6815298850928644e-05, + "loss": 3.4012, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806912903418128e-05, + "loss": 3.3924, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798526955907607e-05, + "loss": 3.4077, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6790157387200817e-05, + "loss": 3.4146, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781771439690297e-05, + "loss": 3.4005, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6773385492179776e-05, + "loss": 3.4096, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764999544669256e-05, + "loss": 3.4053, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.675662997596247e-05, + "loss": 3.3976, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.674824402845195e-05, + "loss": 3.3959, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.673985808094143e-05, + "loss": 3.4072, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.673147213343091e-05, + "loss": 3.42, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6723102564724118e-05, + "loss": 3.4113, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714716617213598e-05, + "loss": 3.4118, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.670633066970308e-05, + "loss": 3.4041, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669794472219256e-05, + "loss": 3.4039, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.668957515348577e-05, + "loss": 3.4059, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6681205584778983e-05, + "loss": 3.4147, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.667281963726846e-05, + "loss": 3.4121, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664433689757943e-05, + "loss": 3.415, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6656047742247423e-05, + "loss": 3.4074, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647661794736903e-05, + "loss": 3.4038, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6639275847226383e-05, + "loss": 3.4122, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630889899715862e-05, + "loss": 3.4088, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.662250395220534e-05, + "loss": 3.3998, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.661413438349855e-05, + "loss": 3.4119, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605748435988035e-05, + "loss": 3.4044, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6597362488477515e-05, + "loss": 3.4049, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.658897654096699e-05, + "loss": 3.3978, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580606972260204e-05, + "loss": 3.4008, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6572221024749684e-05, + "loss": 3.4113, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.656383507723916e-05, + "loss": 3.4059, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6555449129728644e-05, + "loss": 3.4113, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6547079561021856e-05, + "loss": 3.4184, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538693613511336e-05, + "loss": 3.418, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6530307666000813e-05, + "loss": 3.4085, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521921718490293e-05, + "loss": 3.4097, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6513552149783505e-05, + "loss": 3.4002, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650516620227299e-05, + "loss": 3.4116, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496780254762465e-05, + "loss": 3.4038, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488394307251945e-05, + "loss": 3.3995, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6480024738545158e-05, + "loss": 3.4006, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471638791034634e-05, + "loss": 3.4115, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6463252843524114e-05, + "loss": 3.4102, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454866896013597e-05, + "loss": 3.404, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.644649732730681e-05, + "loss": 3.403, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6438111379796286e-05, + "loss": 3.4071, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429725432285766e-05, + "loss": 3.4139, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6421339484775246e-05, + "loss": 3.4094, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641296991606846e-05, + "loss": 3.4176, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640458396855794e-05, + "loss": 3.4028, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639619802104742e-05, + "loss": 3.4065, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638782845234063e-05, + "loss": 3.4131, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6379442504830108e-05, + "loss": 3.4034, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6371056557319588e-05, + "loss": 3.4079, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362670609809068e-05, + "loss": 3.4097, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6354301041102284e-05, + "loss": 3.4112, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.634591509359176e-05, + "loss": 3.4227, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.633752914608124e-05, + "loss": 3.4096, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632914319857072e-05, + "loss": 3.4078, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320773629863933e-05, + "loss": 3.4109, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6312387682353413e-05, + "loss": 3.4047, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6304001734842892e-05, + "loss": 3.4048, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295615787332372e-05, + "loss": 3.4034, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.628724621862558e-05, + "loss": 3.4037, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627886027111506e-05, + "loss": 3.4055, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.627047432360454e-05, + "loss": 3.4015, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.867785930633545, + "eval_runtime": 312.5006, + "eval_samples_per_second": 1221.089, + "eval_steps_per_second": 38.16, + "step": 2060629 + }, + { + "epoch": 0.0, + "learning_rate": 1.626208837609402e-05, + "loss": 3.4077, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253702428583505e-05, + "loss": 3.4061, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6245316481072985e-05, + "loss": 3.4092, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236930533562465e-05, + "loss": 3.4124, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228560964855674e-05, + "loss": 3.4196, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6220175017345154e-05, + "loss": 3.4069, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211789069834634e-05, + "loss": 3.4118, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6203403122324114e-05, + "loss": 3.4035, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6195033553617326e-05, + "loss": 3.397, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186647606106806e-05, + "loss": 3.403, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6178261658596286e-05, + "loss": 3.4157, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6169875711085763e-05, + "loss": 3.3973, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6161506142378975e-05, + "loss": 3.4084, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615312019486846e-05, + "loss": 3.3902, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614473424735794e-05, + "loss": 3.3982, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6136348299847415e-05, + "loss": 3.3874, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127978731140627e-05, + "loss": 3.4066, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119592783630107e-05, + "loss": 3.4042, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6111206836119587e-05, + "loss": 3.3989, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102820888609067e-05, + "loss": 3.4064, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609445131990228e-05, + "loss": 3.4144, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608606537239176e-05, + "loss": 3.4114, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077679424881236e-05, + "loss": 3.4028, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6069293477370716e-05, + "loss": 3.4019, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.606092390866393e-05, + "loss": 3.4188, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052537961153412e-05, + "loss": 3.4102, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604415201364289e-05, + "loss": 3.399, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603576606613237e-05, + "loss": 3.4065, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602739649742558e-05, + "loss": 3.3982, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601902692871879e-05, + "loss": 3.3958, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010640981208274e-05, + "loss": 3.4064, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6002255033697753e-05, + "loss": 3.4046, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993869086187233e-05, + "loss": 3.4102, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598548313867671e-05, + "loss": 3.4171, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597709719116619e-05, + "loss": 3.4006, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596871124365567e-05, + "loss": 3.4067, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.596032529614515e-05, + "loss": 3.4076, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951955727438362e-05, + "loss": 3.397, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5943569779927842e-05, + "loss": 3.4013, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5935183832417322e-05, + "loss": 3.3924, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5926797884906802e-05, + "loss": 3.3919, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591842831620001e-05, + "loss": 3.3977, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.591004236868949e-05, + "loss": 3.4136, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901656421178975e-05, + "loss": 3.4009, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5893270473668455e-05, + "loss": 3.3934, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884900904961664e-05, + "loss": 3.4053, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876514957451144e-05, + "loss": 3.4037, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5868129009940624e-05, + "loss": 3.3925, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859743062430104e-05, + "loss": 3.3797, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5851373493723316e-05, + "loss": 3.4105, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842987546212796e-05, + "loss": 3.4081, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834601598702276e-05, + "loss": 3.413, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5826215651191756e-05, + "loss": 3.4005, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5817862461288698e-05, + "loss": 3.3931, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580947651377818e-05, + "loss": 3.3931, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5801090566267657e-05, + "loss": 3.3905, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792704618757137e-05, + "loss": 3.4108, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5784318671246617e-05, + "loss": 3.386, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775932723736097e-05, + "loss": 3.418, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767546776225577e-05, + "loss": 3.3999, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5759160828715057e-05, + "loss": 3.3846, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575079126000827e-05, + "loss": 3.4042, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.574240531249775e-05, + "loss": 3.3963, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.573401936498723e-05, + "loss": 3.385, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.572563341747671e-05, + "loss": 3.3992, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.571726384876992e-05, + "loss": 3.4105, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.57088779012594e-05, + "loss": 3.3937, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700491953748882e-05, + "loss": 3.3988, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5692106006238362e-05, + "loss": 3.3804, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568373643753157e-05, + "loss": 3.3957, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567535049002105e-05, + "loss": 3.3959, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.566696454251053e-05, + "loss": 3.3977, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565857859500001e-05, + "loss": 3.3992, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5650209026293223e-05, + "loss": 3.3965, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641823078782703e-05, + "loss": 3.4147, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5633437131272183e-05, + "loss": 3.3981, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562505118376166e-05, + "loss": 3.4071, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616681615054872e-05, + "loss": 3.396, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5608295667544352e-05, + "loss": 3.3931, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599909720033836e-05, + "loss": 3.405, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591523772523312e-05, + "loss": 3.3992, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5583154203816525e-05, + "loss": 3.3981, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574768256306005e-05, + "loss": 3.4034, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5566382308795485e-05, + "loss": 3.3941, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555799636128496e-05, + "loss": 3.3798, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549626792578177e-05, + "loss": 3.3959, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5541240845067657e-05, + "loss": 3.4052, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532854897557134e-05, + "loss": 3.3908, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524485328850346e-05, + "loss": 3.4005, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5516099381339826e-05, + "loss": 3.3956, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507713433829306e-05, + "loss": 3.3858, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5499327486318786e-05, + "loss": 3.3918, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490957917612e-05, + "loss": 3.3915, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548257197010148e-05, + "loss": 3.4067, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5474186022590958e-05, + "loss": 3.4025, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465800075080435e-05, + "loss": 3.4011, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545743050637365e-05, + "loss": 3.3919, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544904455886313e-05, + "loss": 3.3929, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440658611352607e-05, + "loss": 3.3963, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5432272663842087e-05, + "loss": 3.403, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.54239030951353e-05, + "loss": 3.4017, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541551714762478e-05, + "loss": 3.4046, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.540713120011426e-05, + "loss": 3.3974, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539874525260374e-05, + "loss": 3.3935, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5390375683896952e-05, + "loss": 3.4051, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381989736386432e-05, + "loss": 3.3962, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.537360378887591e-05, + "loss": 3.3942, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.536521784136539e-05, + "loss": 3.3971, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356848272658604e-05, + "loss": 3.3947, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534846232514808e-05, + "loss": 3.3937, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.534007637763756e-05, + "loss": 3.3879, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.533169043012704e-05, + "loss": 3.389, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5323320861420253e-05, + "loss": 3.4037, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.531493491390973e-05, + "loss": 3.4, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306548966399213e-05, + "loss": 3.3995, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5298163018888693e-05, + "loss": 3.4041, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289793450181902e-05, + "loss": 3.4132, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5281407502671382e-05, + "loss": 3.3984, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5273021555160862e-05, + "loss": 3.3971, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5264635607650342e-05, + "loss": 3.3937, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5256266038943553e-05, + "loss": 3.395, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247880091433035e-05, + "loss": 3.3942, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239494143922515e-05, + "loss": 3.3939, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5231108196411995e-05, + "loss": 3.3916, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222738627705205e-05, + "loss": 3.3985, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5214352680194685e-05, + "loss": 3.3989, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205966732684165e-05, + "loss": 3.393, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197580785173645e-05, + "loss": 3.3966, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5189211216466856e-05, + "loss": 3.3981, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180825268956336e-05, + "loss": 3.3985, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172439321445816e-05, + "loss": 3.3999, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5164053373935298e-05, + "loss": 3.4089, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155683805228507e-05, + "loss": 3.3916, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5147297857717988e-05, + "loss": 3.3988, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138911910207468e-05, + "loss": 3.3981, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130525962696948e-05, + "loss": 3.3936, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5122156393990159e-05, + "loss": 3.3931, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113770446479639e-05, + "loss": 3.397, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105384498969119e-05, + "loss": 3.4094, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096998551458599e-05, + "loss": 3.4107, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.508862898275181e-05, + "loss": 3.3987, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.508024303524129e-05, + "loss": 3.4, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.507185708773077e-05, + "loss": 3.4002, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063471140220251e-05, + "loss": 3.3961, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.505510157151346e-05, + "loss": 3.3907, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.504671562400294e-05, + "loss": 3.3972, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5038329676492422e-05, + "loss": 3.391, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029943728981902e-05, + "loss": 3.3938, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021574160275113e-05, + "loss": 3.3925, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8690683841705322, + "eval_runtime": 306.5215, + "eval_samples_per_second": 1244.908, + "eval_steps_per_second": 38.904, + "step": 2136949 + }, + { + "epoch": 1.0, + "learning_rate": 1.5013188212764593e-05, + "loss": 3.3971, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004802265254073e-05, + "loss": 3.3937, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4996432696547283e-05, + "loss": 3.397, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4988046749036763e-05, + "loss": 3.404, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979660801526243e-05, + "loss": 3.4068, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4971274854015723e-05, + "loss": 3.3989, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962905285308934e-05, + "loss": 3.4046, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954519337798414e-05, + "loss": 3.3888, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4946133390287894e-05, + "loss": 3.3881, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937747442777376e-05, + "loss": 3.3972, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4929377874070585e-05, + "loss": 3.3972, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920991926560066e-05, + "loss": 3.3928, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912605979049546e-05, + "loss": 3.4029, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4904236410342755e-05, + "loss": 3.3776, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895850462832237e-05, + "loss": 3.3898, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887464515321717e-05, + "loss": 3.3748, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4879078567811197e-05, + "loss": 3.3966, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870692620300677e-05, + "loss": 3.3928, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4862306672790155e-05, + "loss": 3.392, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853920725279635e-05, + "loss": 3.3942, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845534777769115e-05, + "loss": 3.405, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.483716520906233e-05, + "loss": 3.3996, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828779261551806e-05, + "loss": 3.3962, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820393314041286e-05, + "loss": 3.3934, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4812007366530767e-05, + "loss": 3.4075, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803637797823977e-05, + "loss": 3.3972, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4795251850313458e-05, + "loss": 3.3909, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786865902802938e-05, + "loss": 3.3959, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778479955292418e-05, + "loss": 3.3815, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4770126765389361e-05, + "loss": 3.3908, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761740817878841e-05, + "loss": 3.3967, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4753354870368321e-05, + "loss": 3.3931, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744968922857801e-05, + "loss": 3.3994, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.473658297534728e-05, + "loss": 3.4055, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.472819702783676e-05, + "loss": 3.3919, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.471981108032624e-05, + "loss": 3.3987, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711425132815721e-05, + "loss": 3.3985, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.470305556410893e-05, + "loss": 3.3865, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694669616598412e-05, + "loss": 3.39, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4686283669087892e-05, + "loss": 3.381, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677897721577372e-05, + "loss": 3.3806, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669528152870583e-05, + "loss": 3.3912, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4661142205360062e-05, + "loss": 3.4012, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652756257849542e-05, + "loss": 3.3885, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644370310339022e-05, + "loss": 3.391, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4636000741632233e-05, + "loss": 3.3917, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627614794121713e-05, + "loss": 3.3958, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4619228846611193e-05, + "loss": 3.3796, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610842899100675e-05, + "loss": 3.3709, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4602473330393884e-05, + "loss": 3.3971, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4594087382883364e-05, + "loss": 3.4022, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585701435372845e-05, + "loss": 3.4041, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4577315487862325e-05, + "loss": 3.3833, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568962297959269e-05, + "loss": 3.388, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560576350448745e-05, + "loss": 3.3806, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4552190402938227e-05, + "loss": 3.3801, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543804455427707e-05, + "loss": 3.4039, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535418507917187e-05, + "loss": 3.3795, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4527032560406667e-05, + "loss": 3.4074, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518646612896147e-05, + "loss": 3.3911, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4510260665385628e-05, + "loss": 3.3762, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501891096678838e-05, + "loss": 3.3951, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493505149168317e-05, + "loss": 3.3851, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4485119201657799e-05, + "loss": 3.3764, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476733254147279e-05, + "loss": 3.3878, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.446836368544049e-05, + "loss": 3.4008, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.445997773792997e-05, + "loss": 3.3807, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.445159179041945e-05, + "loss": 3.3898, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4443205842908928e-05, + "loss": 3.3692, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.443483627420214e-05, + "loss": 3.3864, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.442645032669162e-05, + "loss": 3.3855, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.44180643791811e-05, + "loss": 3.391, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409678431670579e-05, + "loss": 3.3858, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4401308862963791e-05, + "loss": 3.3906, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392922915453271e-05, + "loss": 3.4027, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384536967942753e-05, + "loss": 3.393, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.437615102043223e-05, + "loss": 3.3947, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367781451725444e-05, + "loss": 3.3884, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359395504214923e-05, + "loss": 3.3829, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.43510095567044e-05, + "loss": 3.3961, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342639987997614e-05, + "loss": 3.387, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4334254040487094e-05, + "loss": 3.3901, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325868092976574e-05, + "loss": 3.3935, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317482145466052e-05, + "loss": 3.3884, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4309096197955532e-05, + "loss": 3.3691, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300710250445012e-05, + "loss": 3.3878, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4292324302934492e-05, + "loss": 3.3933, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283938355423972e-05, + "loss": 3.3827, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275568786717183e-05, + "loss": 3.3858, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4267182839206663e-05, + "loss": 3.3869, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258796891696145e-05, + "loss": 3.3775, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250410944185625e-05, + "loss": 3.3802, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4242041375478835e-05, + "loss": 3.3865, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233655427968315e-05, + "loss": 3.3923, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4225269480457795e-05, + "loss": 3.3924, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216883532947275e-05, + "loss": 3.394, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208513964240486e-05, + "loss": 3.3843, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4200128016729966e-05, + "loss": 3.3851, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191742069219446e-05, + "loss": 3.3872, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4183372500512657e-05, + "loss": 3.3946, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174986553002137e-05, + "loss": 3.3914, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166600605491617e-05, + "loss": 3.3914, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4158214657981098e-05, + "loss": 3.3867, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149828710470578e-05, + "loss": 3.3859, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141442762960055e-05, + "loss": 3.3931, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4133056815449536e-05, + "loss": 3.3865, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124670867939016e-05, + "loss": 3.3821, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4116301299232229e-05, + "loss": 3.3902, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107915351721707e-05, + "loss": 3.383, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099529404211187e-05, + "loss": 3.3835, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4091143456700667e-05, + "loss": 3.3833, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.408277388799388e-05, + "loss": 3.3775, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074387940483358e-05, + "loss": 3.3929, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4066001992972838e-05, + "loss": 3.3917, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057616045462318e-05, + "loss": 3.3844, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4049246476755529e-05, + "loss": 3.3965, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040860529245008e-05, + "loss": 3.4001, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.403247458173449e-05, + "loss": 3.3879, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.402408863422397e-05, + "loss": 3.3904, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.401571906551718e-05, + "loss": 3.3851, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.400733311800666e-05, + "loss": 3.388, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399894717049614e-05, + "loss": 3.3849, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.399056122298562e-05, + "loss": 3.384, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3982191654278832e-05, + "loss": 3.3802, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973805706768311e-05, + "loss": 3.3904, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3965419759257791e-05, + "loss": 3.3854, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3957033811747271e-05, + "loss": 3.3891, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948664243040482e-05, + "loss": 3.3875, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3940278295529962e-05, + "loss": 3.3882, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931892348019444e-05, + "loss": 3.3845, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923506400508924e-05, + "loss": 3.3948, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3915136831802133e-05, + "loss": 3.3932, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906750884291615e-05, + "loss": 3.3848, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898364936781094e-05, + "loss": 3.3867, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889978989270574e-05, + "loss": 3.393, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881609420563785e-05, + "loss": 3.3806, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3873223473053265e-05, + "loss": 3.3882, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864837525542745e-05, + "loss": 3.3878, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856467956835956e-05, + "loss": 3.4009, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3848082009325436e-05, + "loss": 3.3958, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839696061814916e-05, + "loss": 3.3944, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3831310114304396e-05, + "loss": 3.3868, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822940545597607e-05, + "loss": 3.3931, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814554598087087e-05, + "loss": 3.3885, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3806168650576568e-05, + "loss": 3.38, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797782703066048e-05, + "loss": 3.3873, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789413134359259e-05, + "loss": 3.3799, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3781027186848739e-05, + "loss": 3.3885, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772641239338219e-05, + "loss": 3.3798, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.869236469268799, + "eval_runtime": 301.5405, + "eval_samples_per_second": 1265.472, + "eval_steps_per_second": 39.547, + "step": 2213269 + }, + { + "epoch": 0.0, + "learning_rate": 1.3764255291827699e-05, + "loss": 3.3974, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755869344317179e-05, + "loss": 3.3822, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747483396806657e-05, + "loss": 3.3868, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3739097449296137e-05, + "loss": 3.4006, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.373072788058935e-05, + "loss": 3.3879, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3722341933078831e-05, + "loss": 3.3977, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713955985568308e-05, + "loss": 3.3883, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705570038057788e-05, + "loss": 3.3828, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3697200469351002e-05, + "loss": 3.3743, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688814521840478e-05, + "loss": 3.3873, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.368042857432996e-05, + "loss": 3.3869, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.367204262681944e-05, + "loss": 3.3839, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663673058112652e-05, + "loss": 3.3937, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.365528711060213e-05, + "loss": 3.3656, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.364690116309161e-05, + "loss": 3.3783, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.363851521558109e-05, + "loss": 3.3713, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3630145646874303e-05, + "loss": 3.385, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621759699363781e-05, + "loss": 3.3789, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3613373751853261e-05, + "loss": 3.3829, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604987804342741e-05, + "loss": 3.3872, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596618235635952e-05, + "loss": 3.3912, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3588232288125432e-05, + "loss": 3.3922, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579846340614914e-05, + "loss": 3.3851, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571460393104394e-05, + "loss": 3.3827, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3563090824397603e-05, + "loss": 3.3993, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554704876887084e-05, + "loss": 3.3888, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3546318929376564e-05, + "loss": 3.3778, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537932981866044e-05, + "loss": 3.3875, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529563413159255e-05, + "loss": 3.3737, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3521177465648735e-05, + "loss": 3.3829, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512791518138215e-05, + "loss": 3.3896, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3504405570627695e-05, + "loss": 3.3842, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3496036001920906e-05, + "loss": 3.3883, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487650054410386e-05, + "loss": 3.3965, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3479264106899867e-05, + "loss": 3.3817, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470878159389347e-05, + "loss": 3.3902, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462508590682556e-05, + "loss": 3.3926, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3454122643172038e-05, + "loss": 3.3728, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445736695661518e-05, + "loss": 3.3827, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437350748150998e-05, + "loss": 3.3691, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428981179444209e-05, + "loss": 3.3735, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420595231933689e-05, + "loss": 3.3787, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3412209284423169e-05, + "loss": 3.396, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403823336912649e-05, + "loss": 3.3754, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.339545376820586e-05, + "loss": 3.3809, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.338706782069534e-05, + "loss": 3.382, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.337868187318482e-05, + "loss": 3.3847, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.337031230447803e-05, + "loss": 3.3757, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.336192635696751e-05, + "loss": 3.3616, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353540409456992e-05, + "loss": 3.3854, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3345154461946472e-05, + "loss": 3.394, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.333678489323968e-05, + "loss": 3.3884, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328398945729162e-05, + "loss": 3.3733, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3320012998218642e-05, + "loss": 3.3757, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311627050708122e-05, + "loss": 3.3739, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3303257482001333e-05, + "loss": 3.3672, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294871534490813e-05, + "loss": 3.3973, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286485586980293e-05, + "loss": 3.3676, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3278099639469773e-05, + "loss": 3.3953, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269730070762984e-05, + "loss": 3.3815, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3261344123252464e-05, + "loss": 3.3683, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252958175741945e-05, + "loss": 3.3846, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244572228231425e-05, + "loss": 3.3787, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3236202659524634e-05, + "loss": 3.367, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227816712014116e-05, + "loss": 3.3723, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219430764503596e-05, + "loss": 3.394, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3211044816993076e-05, + "loss": 3.3726, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202675248286287e-05, + "loss": 3.3763, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3194289300775767e-05, + "loss": 3.3611, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185903353265247e-05, + "loss": 3.3774, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177517405754727e-05, + "loss": 3.3749, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3169147837047937e-05, + "loss": 3.3819, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160761889537417e-05, + "loss": 3.3741, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3152375942026899e-05, + "loss": 3.3835, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143989994516376e-05, + "loss": 3.3895, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135620425809588e-05, + "loss": 3.3797, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.312723447829907e-05, + "loss": 3.3842, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.311884853078855e-05, + "loss": 3.3827, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110462583278026e-05, + "loss": 3.374, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.310209301457124e-05, + "loss": 3.3848, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.309370706706072e-05, + "loss": 3.3783, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.30853211195502e-05, + "loss": 3.3811, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076935172039679e-05, + "loss": 3.3867, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068565603332891e-05, + "loss": 3.375, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3060179655822371e-05, + "loss": 3.3578, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.305179370831185e-05, + "loss": 3.3815, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.304340776080133e-05, + "loss": 3.3804, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3035038192094542e-05, + "loss": 3.3764, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026652244584023e-05, + "loss": 3.3769, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.30182662970735e-05, + "loss": 3.3814, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.300988034956298e-05, + "loss": 3.3662, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001510780856194e-05, + "loss": 3.3692, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2993124833345674e-05, + "loss": 3.3742, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984738885835152e-05, + "loss": 3.3864, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2976352938324632e-05, + "loss": 3.3815, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967983369617845e-05, + "loss": 3.3849, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959597422107323e-05, + "loss": 3.3727, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2951211474596803e-05, + "loss": 3.3754, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942825527086283e-05, + "loss": 3.3769, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934455958379495e-05, + "loss": 3.3863, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2926070010868974e-05, + "loss": 3.3779, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917684063358454e-05, + "loss": 3.3831, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2909314494651666e-05, + "loss": 3.3781, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900928547141148e-05, + "loss": 3.3739, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892542599630624e-05, + "loss": 3.3855, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2884156652120104e-05, + "loss": 3.3712, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875787083413318e-05, + "loss": 3.3759, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867401135902795e-05, + "loss": 3.3801, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2859015188392277e-05, + "loss": 3.3722, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850629240881757e-05, + "loss": 3.3718, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2842259672174969e-05, + "loss": 3.3744, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833873724664447e-05, + "loss": 3.3644, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825487777153927e-05, + "loss": 3.3822, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2817101829643407e-05, + "loss": 3.3821, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.280873226093662e-05, + "loss": 3.3746, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800346313426098e-05, + "loss": 3.3854, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791960365915578e-05, + "loss": 3.3937, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783574418405058e-05, + "loss": 3.3768, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2775204849698269e-05, + "loss": 3.381, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766818902187749e-05, + "loss": 3.3778, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.275843295467723e-05, + "loss": 3.3756, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.275004700716671e-05, + "loss": 3.3707, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.274167743845992e-05, + "loss": 3.3741, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2733291490949401e-05, + "loss": 3.374, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724905543438881e-05, + "loss": 3.3802, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716519595928361e-05, + "loss": 3.3765, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2708150027221572e-05, + "loss": 3.3797, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699764079711052e-05, + "loss": 3.3764, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691378132200532e-05, + "loss": 3.3763, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682992184690012e-05, + "loss": 3.3729, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674622615983222e-05, + "loss": 3.388, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2666236668472702e-05, + "loss": 3.3848, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657850720962184e-05, + "loss": 3.3768, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649464773451664e-05, + "loss": 3.3725, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2641095204744873e-05, + "loss": 3.3827, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632709257234355e-05, + "loss": 3.3732, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2624323309723835e-05, + "loss": 3.3751, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615937362213315e-05, + "loss": 3.3779, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607567793506525e-05, + "loss": 3.3917, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2599181845996005e-05, + "loss": 3.3824, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590795898485485e-05, + "loss": 3.3861, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582409950974965e-05, + "loss": 3.3775, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2574040382268176e-05, + "loss": 3.384, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565654434757656e-05, + "loss": 3.3741, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2557268487247138e-05, + "loss": 3.3707, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548882539736618e-05, + "loss": 3.3804, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540512971029827e-05, + "loss": 3.3666, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2532127023519308e-05, + "loss": 3.3818, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523741076008788e-05, + "loss": 3.3677, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8704640865325928, + "eval_runtime": 325.1683, + "eval_samples_per_second": 1173.519, + "eval_steps_per_second": 36.673, + "step": 2289589 + }, + { + "epoch": 1.0, + "learning_rate": 1.2515355128498268e-05, + "loss": 3.3802, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506985559791479e-05, + "loss": 3.3765, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498599612280959e-05, + "loss": 3.3749, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2490213664770437e-05, + "loss": 3.3892, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481827717259919e-05, + "loss": 3.3793, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.247345814855313e-05, + "loss": 3.3881, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.246507220104261e-05, + "loss": 3.3783, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.245668625353209e-05, + "loss": 3.3729, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.244830030602157e-05, + "loss": 3.3709, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.243993073731478e-05, + "loss": 3.3803, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431544789804262e-05, + "loss": 3.3733, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.242315884229374e-05, + "loss": 3.3749, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2414789273586953e-05, + "loss": 3.3819, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2406403326076433e-05, + "loss": 3.36, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2398033757369644e-05, + "loss": 3.3656, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2389647809859124e-05, + "loss": 3.3638, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2381261862348603e-05, + "loss": 3.3723, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372875914838083e-05, + "loss": 3.3716, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364489967327562e-05, + "loss": 3.373, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2356104019817043e-05, + "loss": 3.3753, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347718072306523e-05, + "loss": 3.3822, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2339332124796002e-05, + "loss": 3.3791, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330962556089214e-05, + "loss": 3.379, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2322576608578694e-05, + "loss": 3.371, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2314190661068174e-05, + "loss": 3.3928, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305804713557654e-05, + "loss": 3.3767, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297435144850865e-05, + "loss": 3.3751, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2289049197340345e-05, + "loss": 3.3735, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2280663249829826e-05, + "loss": 3.3664, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2272293681123035e-05, + "loss": 3.3733, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263907733612515e-05, + "loss": 3.3759, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2255521786101997e-05, + "loss": 3.3781, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2247135838591475e-05, + "loss": 3.3769, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238749891080955e-05, + "loss": 3.3846, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2230363943570435e-05, + "loss": 3.3727, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221977996059917e-05, + "loss": 3.379, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213592048549395e-05, + "loss": 3.3814, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2205222479842608e-05, + "loss": 3.3652, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2196836532332088e-05, + "loss": 3.3713, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2188450584821566e-05, + "loss": 3.3571, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2180064637311046e-05, + "loss": 3.3679, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171695068604258e-05, + "loss": 3.3655, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2163309121093738e-05, + "loss": 3.3849, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154923173583216e-05, + "loss": 3.3652, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146537226072698e-05, + "loss": 3.3716, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2138167657365909e-05, + "loss": 3.3736, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129781709855389e-05, + "loss": 3.3733, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121395762344869e-05, + "loss": 3.368, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2113009814834349e-05, + "loss": 3.3494, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104640246127561e-05, + "loss": 3.3758, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.209625429861704e-05, + "loss": 3.3825, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.208786835110652e-05, + "loss": 3.3804, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079482403596e-05, + "loss": 3.3692, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2071129213692943e-05, + "loss": 3.3608, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062743266182423e-05, + "loss": 3.3698, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2054357318671903e-05, + "loss": 3.3575, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045971371161383e-05, + "loss": 3.3838, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037585423650861e-05, + "loss": 3.3577, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2029199476140343e-05, + "loss": 3.3876, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020813528629822e-05, + "loss": 3.3746, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2012427581119302e-05, + "loss": 3.3537, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2004058012412513e-05, + "loss": 3.3723, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995672064901993e-05, + "loss": 3.3728, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1987286117391473e-05, + "loss": 3.3602, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978900169880951e-05, + "loss": 3.3584, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970530601174164e-05, + "loss": 3.3818, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1962144653663644e-05, + "loss": 3.3674, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953775084956856e-05, + "loss": 3.3667, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1945389137446335e-05, + "loss": 3.3547, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1937003189935815e-05, + "loss": 3.3669, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1928617242425296e-05, + "loss": 3.3616, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1920231294914776e-05, + "loss": 3.377, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911845347404254e-05, + "loss": 3.3625, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1903459399893734e-05, + "loss": 3.3747, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1895073452383216e-05, + "loss": 3.3778, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1886703883676425e-05, + "loss": 3.3696, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1878317936165905e-05, + "loss": 3.3725, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869931988655387e-05, + "loss": 3.3716, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861546041144867e-05, + "loss": 3.3695, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1853176472438077e-05, + "loss": 3.3739, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844790524927557e-05, + "loss": 3.3694, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1836404577417037e-05, + "loss": 3.372, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1828018629906516e-05, + "loss": 3.3717, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1819649061199728e-05, + "loss": 3.3674, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1811263113689208e-05, + "loss": 3.3536, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802877166178688e-05, + "loss": 3.3701, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794491218668168e-05, + "loss": 3.3642, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1786121649961379e-05, + "loss": 3.3705, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777735702450859e-05, + "loss": 3.3646, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.176934975494034e-05, + "loss": 3.3731, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760963807429819e-05, + "loss": 3.3597, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752594238723031e-05, + "loss": 3.3575, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1744208291212511e-05, + "loss": 3.3629, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.173582234370199e-05, + "loss": 3.3779, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1727452774995202e-05, + "loss": 3.3687, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1719066827484682e-05, + "loss": 3.3755, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710680879974162e-05, + "loss": 3.3634, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.170229493246364e-05, + "loss": 3.3683, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693925363756852e-05, + "loss": 3.3646, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1685539416246332e-05, + "loss": 3.3793, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1677153468735812e-05, + "loss": 3.3698, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668767521225292e-05, + "loss": 3.3762, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1660397952518503e-05, + "loss": 3.3639, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1652012005007985e-05, + "loss": 3.3659, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643626057497463e-05, + "loss": 3.3788, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1635240109986943e-05, + "loss": 3.3624, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626870541280155e-05, + "loss": 3.3645, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1618484593769635e-05, + "loss": 3.3707, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1610098646259114e-05, + "loss": 3.3626, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1601712698748594e-05, + "loss": 3.3656, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1593343130041806e-05, + "loss": 3.3663, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1584957182531286e-05, + "loss": 3.3532, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1576571235020766e-05, + "loss": 3.3738, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1568185287510246e-05, + "loss": 3.3696, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559815718803457e-05, + "loss": 3.3638, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1551429771292937e-05, + "loss": 3.3746, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1543043823782417e-05, + "loss": 3.3836, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1534657876271897e-05, + "loss": 3.3685, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.152628830756511e-05, + "loss": 3.3705, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1517902360054587e-05, + "loss": 3.3644, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1509516412544067e-05, + "loss": 3.3681, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1501130465033547e-05, + "loss": 3.3585, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.149276089632676e-05, + "loss": 3.3688, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1484374948816238e-05, + "loss": 3.3599, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.147598900130572e-05, + "loss": 3.3732, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.14676030537952e-05, + "loss": 3.366, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1459233485088409e-05, + "loss": 3.3681, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.145084753757789e-05, + "loss": 3.3698, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.144246159006737e-05, + "loss": 3.3675, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.143407564255685e-05, + "loss": 3.3614, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425706073850061e-05, + "loss": 3.3766, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1417320126339541e-05, + "loss": 3.3779, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408934178829021e-05, + "loss": 3.373, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400548231318501e-05, + "loss": 3.3622, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1392178662611712e-05, + "loss": 3.3694, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383792715101192e-05, + "loss": 3.3656, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1375406767590672e-05, + "loss": 3.3684, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1367020820080152e-05, + "loss": 3.3645, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1358651251373362e-05, + "loss": 3.3832, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1350265303862844e-05, + "loss": 3.3714, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341879356352322e-05, + "loss": 3.3787, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1333493408841802e-05, + "loss": 3.3683, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1325123840135015e-05, + "loss": 3.3717, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316737892624495e-05, + "loss": 3.3639, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1308351945113973e-05, + "loss": 3.3617, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1299982376407186e-05, + "loss": 3.3697, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1291596428896665e-05, + "loss": 3.3573, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1283210481386145e-05, + "loss": 3.3703, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1274824533875625e-05, + "loss": 3.3609, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.8714027404785156, + "eval_runtime": 320.5111, + "eval_samples_per_second": 1190.57, + "eval_steps_per_second": 37.206, + "step": 2365909 + }, + { + "epoch": 0.0, + "learning_rate": 1.1266454965168836e-05, + "loss": 3.3563, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1258069017658316e-05, + "loss": 3.3704, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1249683070147796e-05, + "loss": 3.3652, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1241297122637276e-05, + "loss": 3.3766, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1232927553930487e-05, + "loss": 3.3732, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224541606419968e-05, + "loss": 3.378, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1216155658909447e-05, + "loss": 3.3674, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207769711398927e-05, + "loss": 3.3644, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.119940014269214e-05, + "loss": 3.356, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1191014195181619e-05, + "loss": 3.3706, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1182628247671097e-05, + "loss": 3.3651, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1174242300160579e-05, + "loss": 3.364, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.116587273145379e-05, + "loss": 3.37, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.115748678394327e-05, + "loss": 3.3544, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.114910083643275e-05, + "loss": 3.3575, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.114071488892223e-05, + "loss": 3.3553, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.113234532021544e-05, + "loss": 3.3581, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.112395937270492e-05, + "loss": 3.3622, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.11155734251944e-05, + "loss": 3.3672, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.110718747768388e-05, + "loss": 3.3612, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098817908977093e-05, + "loss": 3.3761, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1090431961466571e-05, + "loss": 3.3672, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1082046013956051e-05, + "loss": 3.3676, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073660066445533e-05, + "loss": 3.3649, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1065290497738742e-05, + "loss": 3.3817, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1056904550228222e-05, + "loss": 3.3635, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1048518602717703e-05, + "loss": 3.3656, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1040132655207183e-05, + "loss": 3.3604, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031763086500394e-05, + "loss": 3.3638, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1023393517793605e-05, + "loss": 3.3618, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1015007570283085e-05, + "loss": 3.3629, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1006621622772567e-05, + "loss": 3.37, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0998235675262045e-05, + "loss": 3.3716, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989849727751525e-05, + "loss": 3.373, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0981463780241005e-05, + "loss": 3.3632, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0973077832730485e-05, + "loss": 3.3707, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0964691885219965e-05, + "loss": 3.3672, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0956322316513175e-05, + "loss": 3.3575, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0947936369002657e-05, + "loss": 3.3642, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0939550421492135e-05, + "loss": 3.3471, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0931164473981615e-05, + "loss": 3.3583, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922794905274828e-05, + "loss": 3.3523, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0914408957764306e-05, + "loss": 3.3757, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0906023010253786e-05, + "loss": 3.3605, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0897637062743268e-05, + "loss": 3.3588, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0889267494036478e-05, + "loss": 3.3637, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0880881546525957e-05, + "loss": 3.3674, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0872495599015438e-05, + "loss": 3.3573, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0864109651504918e-05, + "loss": 3.3421, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855740082798129e-05, + "loss": 3.363, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0847354135287609e-05, + "loss": 3.3732, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838968187777089e-05, + "loss": 3.37, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830582240266569e-05, + "loss": 3.361, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.082221267155978e-05, + "loss": 3.3516, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.081382672404926e-05, + "loss": 3.3627, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.080544077653874e-05, + "loss": 3.3504, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0797054829028221e-05, + "loss": 3.3716, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.078868526032143e-05, + "loss": 3.3494, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.078029931281091e-05, + "loss": 3.3746, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771913365300392e-05, + "loss": 3.3659, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.076352741778987e-05, + "loss": 3.3464, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0755157849083083e-05, + "loss": 3.3618, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746771901572563e-05, + "loss": 3.3679, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0738385954062043e-05, + "loss": 3.3448, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0730000006551521e-05, + "loss": 3.3505, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0721630437844733e-05, + "loss": 3.3748, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0713244490334213e-05, + "loss": 3.358, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704858542823693e-05, + "loss": 3.3532, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0696472595313173e-05, + "loss": 3.3469, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0688103026606384e-05, + "loss": 3.3599, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0679717079095864e-05, + "loss": 3.3501, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0671331131585344e-05, + "loss": 3.3669, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0662945184074824e-05, + "loss": 3.3519, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0654575615368036e-05, + "loss": 3.3649, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0646189667857516e-05, + "loss": 3.3635, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0637803720346995e-05, + "loss": 3.3646, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0629434151640207e-05, + "loss": 3.3607, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0621048204129687e-05, + "loss": 3.3606, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0612662256619165e-05, + "loss": 3.3614, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0604276309108645e-05, + "loss": 3.3634, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595906740401858e-05, + "loss": 3.359, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0587520792891338e-05, + "loss": 3.3595, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0579134845380818e-05, + "loss": 3.3601, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570748897870298e-05, + "loss": 3.3607, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0562379329163508e-05, + "loss": 3.3441, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.055399338165299e-05, + "loss": 3.3571, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545607434142468e-05, + "loss": 3.3586, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0537221486631948e-05, + "loss": 3.3604, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.052885191792516e-05, + "loss": 3.3577, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0520465970414639e-05, + "loss": 3.3605, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0512080022904119e-05, + "loss": 3.3526, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503694075393599e-05, + "loss": 3.3483, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0495324506686811e-05, + "loss": 3.3513, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.048693855917629e-05, + "loss": 3.3675, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478552611665771e-05, + "loss": 3.3615, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0470166664155251e-05, + "loss": 3.3666, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461797095448462e-05, + "loss": 3.3565, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0453411147937942e-05, + "loss": 3.3598, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0445025200427422e-05, + "loss": 3.353, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436639252916902e-05, + "loss": 3.3693, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0428269684210113e-05, + "loss": 3.3587, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419883736699593e-05, + "loss": 3.3666, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411497789189073e-05, + "loss": 3.355, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0403111841678553e-05, + "loss": 3.3541, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394742272971763e-05, + "loss": 3.3715, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0386356325461243e-05, + "loss": 3.3526, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377970377950725e-05, + "loss": 3.3507, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369584430440203e-05, + "loss": 3.3649, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0361214861733414e-05, + "loss": 3.3564, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352828914222896e-05, + "loss": 3.3498, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0344442966712376e-05, + "loss": 3.3622, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0336057019201854e-05, + "loss": 3.3442, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0327687450495066e-05, + "loss": 3.3602, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0319301502984546e-05, + "loss": 3.3577, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0310915555474026e-05, + "loss": 3.3584, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302529607963506e-05, + "loss": 3.3639, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0294160039256717e-05, + "loss": 3.3754, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285774091746197e-05, + "loss": 3.3603, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0277388144235677e-05, + "loss": 3.3585, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0269002196725157e-05, + "loss": 3.3577, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0260632628018368e-05, + "loss": 3.3513, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.025224668050785e-05, + "loss": 3.3537, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0243860732997328e-05, + "loss": 3.3556, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0235474785486808e-05, + "loss": 3.3525, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.022710521678002e-05, + "loss": 3.362, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.02187192692695e-05, + "loss": 3.3551, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0210333321758978e-05, + "loss": 3.362, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.020194737424846e-05, + "loss": 3.3576, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.019357780554167e-05, + "loss": 3.3555, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0185191858031149e-05, + "loss": 3.352, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.017680591052063e-05, + "loss": 3.3673, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0168436341813841e-05, + "loss": 3.367, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0160050394303321e-05, + "loss": 3.3656, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0151664446792801e-05, + "loss": 3.3499, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0143278499282281e-05, + "loss": 3.3564, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0134908930575492e-05, + "loss": 3.3598, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0126522983064974e-05, + "loss": 3.3593, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0118137035554452e-05, + "loss": 3.3586, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0109751088043932e-05, + "loss": 3.3693, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0101381519337144e-05, + "loss": 3.3588, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092995571826623e-05, + "loss": 3.371, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0084609624316103e-05, + "loss": 3.3566, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0076223676805584e-05, + "loss": 3.3636, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067854108098795e-05, + "loss": 3.3589, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0059468160588275e-05, + "loss": 3.3482, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0051082213077755e-05, + "loss": 3.3652, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042696265567235e-05, + "loss": 3.3492, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0034326696860446e-05, + "loss": 3.3588, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025940749349926e-05, + "loss": 3.3531, + "step": 2441728 + }, + { + "epoch": 0.03, + "eval_loss": 3.871986150741577, + "eval_runtime": 313.8535, + "eval_samples_per_second": 1215.825, + "eval_steps_per_second": 37.995, + "step": 2442229 + }, + { + "epoch": 1.0, + "learning_rate": 1.0017554801839406e-05, + "loss": 3.3537, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0009168854328886e-05, + "loss": 3.3581, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000799285622096e-05, + "loss": 3.3561, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.992413338111576e-06, + "loss": 3.367, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.984027390601056e-06, + "loss": 3.3657, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.975641443090536e-06, + "loss": 3.3696, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.967271874383747e-06, + "loss": 3.3554, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958885926873229e-06, + "loss": 3.3539, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.950499979362709e-06, + "loss": 3.3516, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.942130410655918e-06, + "loss": 3.3627, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.9337444631454e-06, + "loss": 3.3549, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.92535851563488e-06, + "loss": 3.3578, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.91697256812436e-06, + "loss": 3.3557, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.908586620613838e-06, + "loss": 3.3466, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.90020067310332e-06, + "loss": 3.3501, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.89183110439653e-06, + "loss": 3.3482, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.88344515688601e-06, + "loss": 3.3444, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.87505920937549e-06, + "loss": 3.3556, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.86667326186497e-06, + "loss": 3.3517, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.85828731435445e-06, + "loss": 3.3549, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.84990136684393e-06, + "loss": 3.3708, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.84151541933341e-06, + "loss": 3.354, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.83314585062662e-06, + "loss": 3.3622, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.8247599031161e-06, + "loss": 3.3531, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.81637395560558e-06, + "loss": 3.3699, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.80798800809506e-06, + "loss": 3.3541, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.799618439388273e-06, + "loss": 3.3562, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.791232491877751e-06, + "loss": 3.3496, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.782846544367231e-06, + "loss": 3.3576, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.774476975660444e-06, + "loss": 3.3506, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.766091028149924e-06, + "loss": 3.355, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.757705080639402e-06, + "loss": 3.3602, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.749319133128884e-06, + "loss": 3.3557, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.740933185618363e-06, + "loss": 3.363, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.732547238107842e-06, + "loss": 3.3581, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.724161290597322e-06, + "loss": 3.353, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.715775343086803e-06, + "loss": 3.3633, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.707405774380014e-06, + "loss": 3.3479, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.699019826869492e-06, + "loss": 3.3537, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.690633879358974e-06, + "loss": 3.3396, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.682247931848454e-06, + "loss": 3.3491, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.673878363141665e-06, + "loss": 3.3438, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.665492415631145e-06, + "loss": 3.3637, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.657106468120625e-06, + "loss": 3.3524, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648720520610105e-06, + "loss": 3.3465, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.640350951903315e-06, + "loss": 3.3567, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.631965004392795e-06, + "loss": 3.3576, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.623579056882275e-06, + "loss": 3.3463, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.615193109371755e-06, + "loss": 3.3388, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606823540664966e-06, + "loss": 3.3474, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.598437593154446e-06, + "loss": 3.3618, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.590051645643928e-06, + "loss": 3.3628, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.581665698133406e-06, + "loss": 3.35, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.57331250823035e-06, + "loss": 3.3428, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.56492656071983e-06, + "loss": 3.3535, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.55654061320931e-06, + "loss": 3.3392, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.548154665698789e-06, + "loss": 3.3616, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.539768718188269e-06, + "loss": 3.3395, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.531382770677749e-06, + "loss": 3.3647, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.522996823167227e-06, + "loss": 3.3563, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.514610875656709e-06, + "loss": 3.3385, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.50624130694992e-06, + "loss": 3.3501, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.4978553594394e-06, + "loss": 3.3603, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.48946941192888e-06, + "loss": 3.3374, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.48108346441836e-06, + "loss": 3.3376, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472713895711572e-06, + "loss": 3.3645, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.46432794820105e-06, + "loss": 3.3498, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.45594200069053e-06, + "loss": 3.3454, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.44755605318001e-06, + "loss": 3.3378, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.439186484473223e-06, + "loss": 3.3479, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.430800536962701e-06, + "loss": 3.3399, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.422414589452181e-06, + "loss": 3.3598, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.414028641941663e-06, + "loss": 3.3422, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.405659073234873e-06, + "loss": 3.3596, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.397273125724353e-06, + "loss": 3.3516, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.388887178213833e-06, + "loss": 3.3579, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.380501230703313e-06, + "loss": 3.3482, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.372131661996524e-06, + "loss": 3.3541, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363745714486004e-06, + "loss": 3.3532, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.355359766975484e-06, + "loss": 3.3507, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.346973819464964e-06, + "loss": 3.3516, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.338604250758175e-06, + "loss": 3.3489, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.330218303247655e-06, + "loss": 3.3527, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.321832355737135e-06, + "loss": 3.3489, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.313446408226615e-06, + "loss": 3.3376, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.305076839519825e-06, + "loss": 3.344, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.296690892009307e-06, + "loss": 3.3486, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.288304944498787e-06, + "loss": 3.3509, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.279918996988265e-06, + "loss": 3.3469, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.271549428281478e-06, + "loss": 3.3531, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.263163480770958e-06, + "loss": 3.3417, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.254777533260438e-06, + "loss": 3.3351, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.246391585749916e-06, + "loss": 3.3413, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.238022017043128e-06, + "loss": 3.3567, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.229636069532608e-06, + "loss": 3.3518, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.221250122022088e-06, + "loss": 3.3556, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.212864174511568e-06, + "loss": 3.3486, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.204494605804779e-06, + "loss": 3.3432, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.19610865829426e-06, + "loss": 3.3462, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.187722710783739e-06, + "loss": 3.3558, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.179336763273219e-06, + "loss": 3.3498, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.170967194566431e-06, + "loss": 3.3612, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.162581247055911e-06, + "loss": 3.3466, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.15419529954539e-06, + "loss": 3.3409, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.14580935203487e-06, + "loss": 3.3663, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.137439783328082e-06, + "loss": 3.3401, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.12905383581756e-06, + "loss": 3.3459, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.120667888307042e-06, + "loss": 3.352, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.112298319600253e-06, + "loss": 3.3487, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.103912372089733e-06, + "loss": 3.3398, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.095526424579213e-06, + "loss": 3.3473, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.087140477068693e-06, + "loss": 3.3407, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.078770908361903e-06, + "loss": 3.3513, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.070384960851385e-06, + "loss": 3.3477, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.061999013340863e-06, + "loss": 3.3463, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053613065830343e-06, + "loss": 3.3583, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.045243497123556e-06, + "loss": 3.3636, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036857549613034e-06, + "loss": 3.3514, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.028471602102514e-06, + "loss": 3.3502, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.020085654591996e-06, + "loss": 3.3472, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011716085885206e-06, + "loss": 3.3414, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.003330138374685e-06, + "loss": 3.3486, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.994944190864166e-06, + "loss": 3.3467, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.986558243353646e-06, + "loss": 3.3448, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.978188674646857e-06, + "loss": 3.3489, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.969802727136337e-06, + "loss": 3.3499, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.961416779625817e-06, + "loss": 3.3493, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.953030832115297e-06, + "loss": 3.3477, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.944661263408508e-06, + "loss": 3.3435, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.936275315897988e-06, + "loss": 3.3445, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.927889368387468e-06, + "loss": 3.3575, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.919503420876948e-06, + "loss": 3.357, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.911133852170158e-06, + "loss": 3.3599, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.902747904659638e-06, + "loss": 3.3378, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.89436195714912e-06, + "loss": 3.3494, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.885976009638598e-06, + "loss": 3.3475, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.87760644093181e-06, + "loss": 3.3519, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.86922049342129e-06, + "loss": 3.3445, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.86083454591077e-06, + "loss": 3.3631, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.852448598400249e-06, + "loss": 3.3476, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.844079029693461e-06, + "loss": 3.3665, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.835693082182941e-06, + "loss": 3.3448, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.827307134672421e-06, + "loss": 3.3558, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.818921187161901e-06, + "loss": 3.3466, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.810551618455112e-06, + "loss": 3.3422, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.802165670944592e-06, + "loss": 3.3542, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.793779723434072e-06, + "loss": 3.3411, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.785393775923552e-06, + "loss": 3.3481, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.777024207216763e-06, + "loss": 3.344, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.768638259706244e-06, + "loss": 3.3438, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.8738043308258057, + "eval_runtime": 303.4528, + "eval_samples_per_second": 1257.497, + "eval_steps_per_second": 39.298, + "step": 2518549 + }, + { + "epoch": 0.0, + "learning_rate": 8.760252312195723e-06, + "loss": 3.3474, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.751866364685203e-06, + "loss": 3.3502, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.743480417174683e-06, + "loss": 3.3563, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.735110848467893e-06, + "loss": 3.3489, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.726724900957373e-06, + "loss": 3.366, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.718338953446855e-06, + "loss": 3.3448, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.709953005936335e-06, + "loss": 3.3435, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.701583437229546e-06, + "loss": 3.3419, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.693213868522757e-06, + "loss": 3.352, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.684827921012236e-06, + "loss": 3.348, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.676441973501716e-06, + "loss": 3.3448, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.668056025991196e-06, + "loss": 3.349, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.659670078480676e-06, + "loss": 3.3319, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.651284130970156e-06, + "loss": 3.3452, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.642914562263367e-06, + "loss": 3.3385, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.634528614752847e-06, + "loss": 3.341, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.626142667242327e-06, + "loss": 3.3411, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.617756719731809e-06, + "loss": 3.3433, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.609370772221287e-06, + "loss": 3.3424, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.600984824710767e-06, + "loss": 3.3654, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.592598877200247e-06, + "loss": 3.3448, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.584212929689727e-06, + "loss": 3.3467, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.575843360982938e-06, + "loss": 3.3475, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.56745741347242e-06, + "loss": 3.3562, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.5590714659619e-06, + "loss": 3.3464, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.550701897255108e-06, + "loss": 3.3512, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.54231594974459e-06, + "loss": 3.3401, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.53393000223407e-06, + "loss": 3.3473, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.52556043352728e-06, + "loss": 3.3373, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.51717448601676e-06, + "loss": 3.3476, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.50878853850624e-06, + "loss": 3.3498, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.50040259099572e-06, + "loss": 3.3457, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.4920166434852e-06, + "loss": 3.3555, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.48363069597468e-06, + "loss": 3.3488, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.47524474846416e-06, + "loss": 3.3479, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.466858800953639e-06, + "loss": 3.3525, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.458489232246851e-06, + "loss": 3.3415, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.450103284736331e-06, + "loss": 3.3426, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.441717337225811e-06, + "loss": 3.3326, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.433331389715291e-06, + "loss": 3.3376, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.424961821008502e-06, + "loss": 3.3384, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.416575873497982e-06, + "loss": 3.3522, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.408189925987463e-06, + "loss": 3.3446, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.399803978476942e-06, + "loss": 3.3393, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.391434409770154e-06, + "loss": 3.3477, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.383048462259634e-06, + "loss": 3.3461, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.374662514749112e-06, + "loss": 3.3379, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.366276567238592e-06, + "loss": 3.3301, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.357906998531805e-06, + "loss": 3.3357, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.349521051021285e-06, + "loss": 3.3539, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.341135103510763e-06, + "loss": 3.3548, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.332749156000245e-06, + "loss": 3.3366, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.324379587293455e-06, + "loss": 3.3379, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.316010018586668e-06, + "loss": 3.3445, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.307624071076146e-06, + "loss": 3.329, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.299238123565626e-06, + "loss": 3.3503, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.290852176055106e-06, + "loss": 3.3342, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.282466228544586e-06, + "loss": 3.3536, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.274080281034066e-06, + "loss": 3.3462, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.265694333523546e-06, + "loss": 3.3349, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.257324764816758e-06, + "loss": 3.3347, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.248938817306237e-06, + "loss": 3.3505, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.240552869795717e-06, + "loss": 3.3266, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.232166922285198e-06, + "loss": 3.3306, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.223797353578409e-06, + "loss": 3.3521, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.215411406067889e-06, + "loss": 3.3432, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.207025458557369e-06, + "loss": 3.3344, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.198639511046849e-06, + "loss": 3.3285, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.19026994234006e-06, + "loss": 3.3397, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.18188399482954e-06, + "loss": 3.3324, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.17349804731902e-06, + "loss": 3.3426, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.165112099808498e-06, + "loss": 3.3368, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.15674253110171e-06, + "loss": 3.3489, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.14835658359119e-06, + "loss": 3.3456, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.13997063608067e-06, + "loss": 3.3506, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.13158468857015e-06, + "loss": 3.3369, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.123215119863361e-06, + "loss": 3.3435, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.114829172352843e-06, + "loss": 3.3439, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.106443224842323e-06, + "loss": 3.341, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.098057277331801e-06, + "loss": 3.3439, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.089687708625013e-06, + "loss": 3.3408, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.081301761114493e-06, + "loss": 3.3429, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.072915813603972e-06, + "loss": 3.3383, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.064546244897184e-06, + "loss": 3.3293, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.056160297386664e-06, + "loss": 3.3314, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.047774349876144e-06, + "loss": 3.3425, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.039388402365624e-06, + "loss": 3.344, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.031002454855104e-06, + "loss": 3.3396, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.022616507344584e-06, + "loss": 3.3378, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.014230559834062e-06, + "loss": 3.3334, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.005844612323544e-06, + "loss": 3.3283, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.997475043616755e-06, + "loss": 3.3323, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.989089096106235e-06, + "loss": 3.3427, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.980703148595715e-06, + "loss": 3.3419, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.972317201085194e-06, + "loss": 3.3466, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.963947632378405e-06, + "loss": 3.3459, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.955561684867887e-06, + "loss": 3.335, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.947175737357365e-06, + "loss": 3.3391, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.938789789846845e-06, + "loss": 3.341, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.930420221140058e-06, + "loss": 3.3456, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.922034273629536e-06, + "loss": 3.3489, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.913648326119016e-06, + "loss": 3.3383, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.905262378608498e-06, + "loss": 3.3306, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.896892809901708e-06, + "loss": 3.3531, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.888506862391187e-06, + "loss": 3.331, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.880120914880668e-06, + "loss": 3.3388, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.871734967370148e-06, + "loss": 3.3396, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.863365398663359e-06, + "loss": 3.3398, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.854979451152839e-06, + "loss": 3.3312, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.84660988244605e-06, + "loss": 3.3423, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.83822393493553e-06, + "loss": 3.3294, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.82983798742501e-06, + "loss": 3.3396, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.82145203991449e-06, + "loss": 3.3399, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.81306609240397e-06, + "loss": 3.3346, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.804680144893451e-06, + "loss": 3.3505, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.79629419738293e-06, + "loss": 3.3575, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.78790824987241e-06, + "loss": 3.342, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.779538681165622e-06, + "loss": 3.3397, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.7711527336551e-06, + "loss": 3.3393, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.76276678614458e-06, + "loss": 3.3353, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.75438083863406e-06, + "loss": 3.3356, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.746011269927273e-06, + "loss": 3.342, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.73762532241675e-06, + "loss": 3.3327, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.729239374906232e-06, + "loss": 3.3372, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.720853427395712e-06, + "loss": 3.3428, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.712483858688923e-06, + "loss": 3.3449, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.704097911178403e-06, + "loss": 3.3349, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.695711963667883e-06, + "loss": 3.3363, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.687326016157363e-06, + "loss": 3.3412, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.678956447450574e-06, + "loss": 3.3421, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.670570499940054e-06, + "loss": 3.3477, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.662184552429534e-06, + "loss": 3.3485, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.653798604919014e-06, + "loss": 3.3307, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.645429036212225e-06, + "loss": 3.3409, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.637043088701704e-06, + "loss": 3.3395, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.628657141191185e-06, + "loss": 3.3402, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.620271193680664e-06, + "loss": 3.3384, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.611901624973876e-06, + "loss": 3.3492, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.603515677463356e-06, + "loss": 3.3385, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.595129729952837e-06, + "loss": 3.3555, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.586743782442315e-06, + "loss": 3.3371, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.578374213735527e-06, + "loss": 3.345, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.5699882662250075e-06, + "loss": 3.338, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.561602318714487e-06, + "loss": 3.333, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.5532163712039665e-06, + "loss": 3.3443, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.544846802497178e-06, + "loss": 3.3357, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.536460854986659e-06, + "loss": 3.3379, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.528074907476137e-06, + "loss": 3.3319, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.519688959965618e-06, + "loss": 3.3347, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.873227834701538, + "eval_runtime": 310.5098, + "eval_samples_per_second": 1228.918, + "eval_steps_per_second": 38.405, + "step": 2594869 + }, + { + "epoch": 0.0, + "learning_rate": 7.51131939125883e-06, + "loss": 3.3391, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.50293344374831e-06, + "loss": 3.3404, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.494547496237789e-06, + "loss": 3.3488, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.486161548727269e-06, + "loss": 3.3384, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.47779198002048e-06, + "loss": 3.355, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.4694060325099594e-06, + "loss": 3.3385, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.46102008499944e-06, + "loss": 3.3399, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.452650516292652e-06, + "loss": 3.3284, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.4442809475858635e-06, + "loss": 3.3463, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.435895000075342e-06, + "loss": 3.3373, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.427509052564823e-06, + "loss": 3.3311, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.4191231050543025e-06, + "loss": 3.3476, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.410737157543783e-06, + "loss": 3.3225, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.4023512100332625e-06, + "loss": 3.3396, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.393981641326474e-06, + "loss": 3.3232, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.385595693815954e-06, + "loss": 3.334, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.377209746305433e-06, + "loss": 3.3289, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.368823798794913e-06, + "loss": 3.3376, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.360437851284394e-06, + "loss": 3.3314, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.352051903773874e-06, + "loss": 3.3562, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.343665956263353e-06, + "loss": 3.3342, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.335280008752833e-06, + "loss": 3.339, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.3269104400460446e-06, + "loss": 3.3366, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.318524492535524e-06, + "loss": 3.349, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.310138545025004e-06, + "loss": 3.3361, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.301768976318215e-06, + "loss": 3.3459, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.293383028807696e-06, + "loss": 3.327, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.284997081297175e-06, + "loss": 3.3361, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.276611133786655e-06, + "loss": 3.3267, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.268241565079867e-06, + "loss": 3.3417, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.259855617569348e-06, + "loss": 3.3396, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.251469670058826e-06, + "loss": 3.3393, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.243083722548307e-06, + "loss": 3.3492, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.234697775037787e-06, + "loss": 3.3365, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.226311827527266e-06, + "loss": 3.3372, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.217925880016746e-06, + "loss": 3.3412, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.209556311309957e-06, + "loss": 3.3345, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.201170363799438e-06, + "loss": 3.332, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.192784416288917e-06, + "loss": 3.3248, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.184398468778397e-06, + "loss": 3.3275, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.176028900071609e-06, + "loss": 3.3285, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.167642952561088e-06, + "loss": 3.3424, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.159257005050568e-06, + "loss": 3.3368, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.150871057540049e-06, + "loss": 3.3281, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.14250148883326e-06, + "loss": 3.3406, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.1341155413227386e-06, + "loss": 3.3337, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.125729593812219e-06, + "loss": 3.3297, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.117343646301699e-06, + "loss": 3.3251, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.108974077594911e-06, + "loss": 3.3217, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.10058813008439e-06, + "loss": 3.3417, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.092202182573871e-06, + "loss": 3.3459, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.083816235063351e-06, + "loss": 3.33, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.075446666356561e-06, + "loss": 3.3299, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.067060718846042e-06, + "loss": 3.3365, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.0586747713355215e-06, + "loss": 3.3198, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.050288823825002e-06, + "loss": 3.3398, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.041919255118212e-06, + "loss": 3.3247, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.033533307607692e-06, + "loss": 3.341, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.025147360097173e-06, + "loss": 3.3401, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.016761412586652e-06, + "loss": 3.3271, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.008391843879864e-06, + "loss": 3.3248, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 7.000005896369344e-06, + "loss": 3.3417, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.991619948858824e-06, + "loss": 3.3168, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.983234001348303e-06, + "loss": 3.3254, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.9748644326415144e-06, + "loss": 3.3406, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.966478485130995e-06, + "loss": 3.3367, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.958092537620475e-06, + "loss": 3.3262, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.949706590109954e-06, + "loss": 3.3201, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.941337021403166e-06, + "loss": 3.3269, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.932951073892646e-06, + "loss": 3.3237, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.924565126382125e-06, + "loss": 3.3349, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.916179178871606e-06, + "loss": 3.3253, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.9078096101648175e-06, + "loss": 3.3408, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.899423662654297e-06, + "loss": 3.3356, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.8910377151437765e-06, + "loss": 3.3385, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.8826517676332565e-06, + "loss": 3.329, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.874282198926468e-06, + "loss": 3.335, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.865896251415947e-06, + "loss": 3.3357, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.857510303905427e-06, + "loss": 3.3299, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.849124356394908e-06, + "loss": 3.3375, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.84075478768812e-06, + "loss": 3.3343, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.832368840177599e-06, + "loss": 3.3298, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.823982892667079e-06, + "loss": 3.3319, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.815596945156559e-06, + "loss": 3.3196, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.807227376449771e-06, + "loss": 3.3266, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.798841428939249e-06, + "loss": 3.3284, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.79045548142873e-06, + "loss": 3.337, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.782085912721942e-06, + "loss": 3.3278, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.773699965211421e-06, + "loss": 3.3322, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.765314017700901e-06, + "loss": 3.3248, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.756928070190381e-06, + "loss": 3.3184, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.7485585014835925e-06, + "loss": 3.3206, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.740172553973072e-06, + "loss": 3.331, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.731786606462552e-06, + "loss": 3.3397, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.723400658952032e-06, + "loss": 3.3387, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.715031090245244e-06, + "loss": 3.3332, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.706645142734723e-06, + "loss": 3.3294, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.698259195224203e-06, + "loss": 3.3294, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.689873247713684e-06, + "loss": 3.331, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.681503679006894e-06, + "loss": 3.3379, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.673117731496374e-06, + "loss": 3.3384, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.6647317839858546e-06, + "loss": 3.3316, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.6563458364753345e-06, + "loss": 3.3216, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.647976267768545e-06, + "loss": 3.3419, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.639590320258025e-06, + "loss": 3.3233, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.631204372747506e-06, + "loss": 3.3326, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.622818425236984e-06, + "loss": 3.3291, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.614448856530196e-06, + "loss": 3.3293, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.606062909019677e-06, + "loss": 3.3245, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.597676961509157e-06, + "loss": 3.3373, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.589291013998636e-06, + "loss": 3.3176, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.5809214452918475e-06, + "loss": 3.3273, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.572535497781327e-06, + "loss": 3.334, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.564149550270808e-06, + "loss": 3.3234, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.555763602760287e-06, + "loss": 3.3437, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.547394034053499e-06, + "loss": 3.346, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.539008086542979e-06, + "loss": 3.3352, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.530622139032458e-06, + "loss": 3.3292, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.522236191521938e-06, + "loss": 3.3307, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.51386662281515e-06, + "loss": 3.328, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.5054806753046304e-06, + "loss": 3.3209, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.497094727794109e-06, + "loss": 3.3361, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.4887087802835895e-06, + "loss": 3.3216, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.480339211576801e-06, + "loss": 3.3302, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.471953264066281e-06, + "loss": 3.3363, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.46356731655576e-06, + "loss": 3.3342, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.455181369045241e-06, + "loss": 3.3257, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.446811800338453e-06, + "loss": 3.3293, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.438425852827931e-06, + "loss": 3.3335, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.430039905317412e-06, + "loss": 3.3315, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.421653957806892e-06, + "loss": 3.3321, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.413284389100103e-06, + "loss": 3.3409, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.404898441589582e-06, + "loss": 3.3194, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.396512494079062e-06, + "loss": 3.3314, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.388126546568543e-06, + "loss": 3.3345, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.379756977861755e-06, + "loss": 3.329, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.371371030351234e-06, + "loss": 3.3265, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.362985082840714e-06, + "loss": 3.3418, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.3546155141339255e-06, + "loss": 3.3311, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.346229566623405e-06, + "loss": 3.3472, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.3378436191128846e-06, + "loss": 3.3288, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.329457671602365e-06, + "loss": 3.3339, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.321088102895577e-06, + "loss": 3.3315, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.312702155385056e-06, + "loss": 3.3248, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.304316207874536e-06, + "loss": 3.3307, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.295930260364016e-06, + "loss": 3.3304, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.287560691657228e-06, + "loss": 3.3266, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.279174744146707e-06, + "loss": 3.3213, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.2707887966361876e-06, + "loss": 3.3247, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.872431755065918, + "eval_runtime": 310.1185, + "eval_samples_per_second": 1230.468, + "eval_steps_per_second": 38.453, + "step": 2671189 + }, + { + "epoch": 1.0, + "learning_rate": 6.2624028491256675e-06, + "loss": 3.3325, + "step": 2671616 + }, + { + "epoch": 1.0, + "learning_rate": 6.2540332804188775e-06, + "loss": 3.3293, + "step": 2672128 + }, + { + "epoch": 1.0, + "learning_rate": 6.245647332908358e-06, + "loss": 3.3394, + "step": 2672640 + }, + { + "epoch": 1.0, + "learning_rate": 6.237261385397838e-06, + "loss": 3.3273, + "step": 2673152 + }, + { + "epoch": 1.0, + "learning_rate": 6.228875437887318e-06, + "loss": 3.3505, + "step": 2673664 + }, + { + "epoch": 1.0, + "learning_rate": 6.22050586918053e-06, + "loss": 3.3271, + "step": 2674176 + }, + { + "epoch": 1.0, + "learning_rate": 6.212119921670009e-06, + "loss": 3.3301, + "step": 2674688 + }, + { + "epoch": 1.0, + "learning_rate": 6.203733974159489e-06, + "loss": 3.3184, + "step": 2675200 + }, + { + "epoch": 1.0, + "learning_rate": 6.19534802664897e-06, + "loss": 3.3328, + "step": 2675712 + }, + { + "epoch": 1.0, + "learning_rate": 6.1869784579421805e-06, + "loss": 3.3302, + "step": 2676224 + }, + { + "epoch": 1.0, + "learning_rate": 6.1785925104316604e-06, + "loss": 3.3237, + "step": 2676736 + }, + { + "epoch": 1.0, + "learning_rate": 6.17020656292114e-06, + "loss": 3.3324, + "step": 2677248 + }, + { + "epoch": 1.0, + "learning_rate": 6.16182061541062e-06, + "loss": 3.314, + "step": 2677760 + }, + { + "epoch": 1.0, + "learning_rate": 6.1534346679001e-06, + "loss": 3.3302, + "step": 2678272 + }, + { + "epoch": 1.0, + "learning_rate": 6.145065099193312e-06, + "loss": 3.3214, + "step": 2678784 + }, + { + "epoch": 1.0, + "learning_rate": 6.136679151682791e-06, + "loss": 3.3226, + "step": 2679296 + }, + { + "epoch": 1.0, + "learning_rate": 6.128293204172271e-06, + "loss": 3.3175, + "step": 2679808 + }, + { + "epoch": 1.0, + "learning_rate": 6.119907256661751e-06, + "loss": 3.3252, + "step": 2680320 + }, + { + "epoch": 1.0, + "learning_rate": 6.111521309151231e-06, + "loss": 3.3261, + "step": 2680832 + }, + { + "epoch": 1.0, + "learning_rate": 6.103135361640711e-06, + "loss": 3.3448, + "step": 2681344 + }, + { + "epoch": 1.0, + "learning_rate": 6.094749414130191e-06, + "loss": 3.3274, + "step": 2681856 + }, + { + "epoch": 1.0, + "learning_rate": 6.086363466619671e-06, + "loss": 3.3351, + "step": 2682368 + }, + { + "epoch": 1.0, + "learning_rate": 6.077993897912882e-06, + "loss": 3.3266, + "step": 2682880 + }, + { + "epoch": 1.0, + "learning_rate": 6.0696079504023615e-06, + "loss": 3.3392, + "step": 2683392 + }, + { + "epoch": 1.0, + "learning_rate": 6.061222002891842e-06, + "loss": 3.3253, + "step": 2683904 + }, + { + "epoch": 1.0, + "learning_rate": 6.0528360553813214e-06, + "loss": 3.335, + "step": 2684416 + }, + { + "epoch": 1.0, + "learning_rate": 6.044466486674533e-06, + "loss": 3.3258, + "step": 2684928 + }, + { + "epoch": 1.0, + "learning_rate": 6.036080539164013e-06, + "loss": 3.3249, + "step": 2685440 + }, + { + "epoch": 1.0, + "learning_rate": 6.027694591653493e-06, + "loss": 3.317, + "step": 2685952 + }, + { + "epoch": 1.01, + "learning_rate": 6.019325022946705e-06, + "loss": 3.332, + "step": 2686464 + }, + { + "epoch": 1.01, + "learning_rate": 6.010939075436185e-06, + "loss": 3.3344, + "step": 2686976 + }, + { + "epoch": 1.01, + "learning_rate": 6.0025531279256645e-06, + "loss": 3.3276, + "step": 2687488 + }, + { + "epoch": 1.01, + "learning_rate": 5.994167180415144e-06, + "loss": 3.341, + "step": 2688000 + }, + { + "epoch": 1.01, + "learning_rate": 5.9857812329046244e-06, + "loss": 3.3301, + "step": 2688512 + }, + { + "epoch": 1.01, + "learning_rate": 5.9773952853941036e-06, + "loss": 3.3215, + "step": 2689024 + }, + { + "epoch": 1.01, + "learning_rate": 5.969009337883584e-06, + "loss": 3.3346, + "step": 2689536 + }, + { + "epoch": 1.01, + "learning_rate": 5.960639769176795e-06, + "loss": 3.3269, + "step": 2690048 + }, + { + "epoch": 1.01, + "learning_rate": 5.952253821666275e-06, + "loss": 3.3189, + "step": 2690560 + }, + { + "epoch": 1.01, + "learning_rate": 5.943867874155755e-06, + "loss": 3.3171, + "step": 2691072 + }, + { + "epoch": 1.01, + "learning_rate": 5.935481926645234e-06, + "loss": 3.3191, + "step": 2691584 + }, + { + "epoch": 1.01, + "learning_rate": 5.927112357938446e-06, + "loss": 3.3251, + "step": 2692096 + }, + { + "epoch": 1.01, + "learning_rate": 5.918726410427926e-06, + "loss": 3.33, + "step": 2692608 + }, + { + "epoch": 1.01, + "learning_rate": 5.910340462917406e-06, + "loss": 3.33, + "step": 2693120 + }, + { + "epoch": 1.01, + "learning_rate": 5.901954515406886e-06, + "loss": 3.3158, + "step": 2693632 + }, + { + "epoch": 1.01, + "learning_rate": 5.893584946700097e-06, + "loss": 3.3343, + "step": 2694144 + }, + { + "epoch": 1.01, + "learning_rate": 5.885198999189577e-06, + "loss": 3.3268, + "step": 2694656 + }, + { + "epoch": 1.01, + "learning_rate": 5.876813051679056e-06, + "loss": 3.3222, + "step": 2695168 + }, + { + "epoch": 1.01, + "learning_rate": 5.868427104168537e-06, + "loss": 3.3143, + "step": 2695680 + }, + { + "epoch": 1.01, + "learning_rate": 5.860057535461748e-06, + "loss": 3.3114, + "step": 2696192 + }, + { + "epoch": 1.01, + "learning_rate": 5.851671587951228e-06, + "loss": 3.3385, + "step": 2696704 + }, + { + "epoch": 1.01, + "learning_rate": 5.843285640440708e-06, + "loss": 3.3356, + "step": 2697216 + }, + { + "epoch": 1.01, + "learning_rate": 5.834899692930188e-06, + "loss": 3.3227, + "step": 2697728 + }, + { + "epoch": 1.01, + "learning_rate": 5.8265301242233995e-06, + "loss": 3.3226, + "step": 2698240 + }, + { + "epoch": 1.01, + "learning_rate": 5.8181441767128794e-06, + "loss": 3.323, + "step": 2698752 + }, + { + "epoch": 1.01, + "learning_rate": 5.809758229202359e-06, + "loss": 3.3108, + "step": 2699264 + }, + { + "epoch": 1.01, + "learning_rate": 5.8013722816918385e-06, + "loss": 3.3287, + "step": 2699776 + }, + { + "epoch": 1.01, + "learning_rate": 5.79300271298505e-06, + "loss": 3.3187, + "step": 2700288 + }, + { + "epoch": 1.01, + "learning_rate": 5.78461676547453e-06, + "loss": 3.3259, + "step": 2700800 + }, + { + "epoch": 1.01, + "learning_rate": 5.77623081796401e-06, + "loss": 3.3363, + "step": 2701312 + }, + { + "epoch": 1.01, + "learning_rate": 5.76784487045349e-06, + "loss": 3.3202, + "step": 2701824 + }, + { + "epoch": 1.01, + "learning_rate": 5.759475301746702e-06, + "loss": 3.3126, + "step": 2702336 + }, + { + "epoch": 1.01, + "learning_rate": 5.751089354236181e-06, + "loss": 3.3357, + "step": 2702848 + }, + { + "epoch": 1.01, + "learning_rate": 5.7427034067256615e-06, + "loss": 3.3066, + "step": 2703360 + }, + { + "epoch": 1.01, + "learning_rate": 5.734317459215141e-06, + "loss": 3.3145, + "step": 2703872 + }, + { + "epoch": 1.01, + "learning_rate": 5.725947890508353e-06, + "loss": 3.3354, + "step": 2704384 + }, + { + "epoch": 1.01, + "learning_rate": 5.717561942997832e-06, + "loss": 3.3293, + "step": 2704896 + }, + { + "epoch": 1.01, + "learning_rate": 5.709175995487312e-06, + "loss": 3.3183, + "step": 2705408 + }, + { + "epoch": 1.01, + "learning_rate": 5.700790047976792e-06, + "loss": 3.315, + "step": 2705920 + }, + { + "epoch": 1.01, + "learning_rate": 5.692420479270003e-06, + "loss": 3.3132, + "step": 2706432 + }, + { + "epoch": 1.01, + "learning_rate": 5.684034531759484e-06, + "loss": 3.314, + "step": 2706944 + }, + { + "epoch": 1.01, + "learning_rate": 5.675648584248963e-06, + "loss": 3.3295, + "step": 2707456 + }, + { + "epoch": 1.01, + "learning_rate": 5.667262636738444e-06, + "loss": 3.3137, + "step": 2707968 + }, + { + "epoch": 1.01, + "learning_rate": 5.6588930680316545e-06, + "loss": 3.3332, + "step": 2708480 + }, + { + "epoch": 1.01, + "learning_rate": 5.650507120521134e-06, + "loss": 3.3255, + "step": 2708992 + }, + { + "epoch": 1.01, + "learning_rate": 5.642121173010614e-06, + "loss": 3.3337, + "step": 2709504 + }, + { + "epoch": 1.01, + "learning_rate": 5.633735225500094e-06, + "loss": 3.3198, + "step": 2710016 + }, + { + "epoch": 1.01, + "learning_rate": 5.625365656793306e-06, + "loss": 3.3193, + "step": 2710528 + }, + { + "epoch": 1.01, + "learning_rate": 5.616979709282785e-06, + "loss": 3.329, + "step": 2711040 + }, + { + "epoch": 1.01, + "learning_rate": 5.608593761772266e-06, + "loss": 3.3196, + "step": 2711552 + }, + { + "epoch": 1.01, + "learning_rate": 5.600207814261745e-06, + "loss": 3.3314, + "step": 2712064 + }, + { + "epoch": 1.01, + "learning_rate": 5.591838245554957e-06, + "loss": 3.323, + "step": 2712576 + }, + { + "epoch": 1.01, + "learning_rate": 5.5834522980444366e-06, + "loss": 3.3195, + "step": 2713088 + }, + { + "epoch": 1.01, + "learning_rate": 5.5750663505339165e-06, + "loss": 3.3243, + "step": 2713600 + }, + { + "epoch": 1.01, + "learning_rate": 5.566696781827128e-06, + "loss": 3.3093, + "step": 2714112 + }, + { + "epoch": 1.01, + "learning_rate": 5.558310834316608e-06, + "loss": 3.3198, + "step": 2714624 + }, + { + "epoch": 1.01, + "learning_rate": 5.549924886806088e-06, + "loss": 3.3241, + "step": 2715136 + }, + { + "epoch": 1.01, + "learning_rate": 5.541538939295567e-06, + "loss": 3.328, + "step": 2715648 + }, + { + "epoch": 1.01, + "learning_rate": 5.533152991785048e-06, + "loss": 3.3174, + "step": 2716160 + }, + { + "epoch": 1.01, + "learning_rate": 5.524783423078259e-06, + "loss": 3.3218, + "step": 2716672 + }, + { + "epoch": 1.02, + "learning_rate": 5.516397475567739e-06, + "loss": 3.3139, + "step": 2717184 + }, + { + "epoch": 1.02, + "learning_rate": 5.508011528057219e-06, + "loss": 3.3133, + "step": 2717696 + }, + { + "epoch": 1.02, + "learning_rate": 5.49964195935043e-06, + "loss": 3.3126, + "step": 2718208 + }, + { + "epoch": 1.02, + "learning_rate": 5.4912560118399094e-06, + "loss": 3.3215, + "step": 2718720 + }, + { + "epoch": 1.02, + "learning_rate": 5.48287006432939e-06, + "loss": 3.3348, + "step": 2719232 + }, + { + "epoch": 1.02, + "learning_rate": 5.474484116818869e-06, + "loss": 3.3304, + "step": 2719744 + }, + { + "epoch": 1.02, + "learning_rate": 5.466114548112081e-06, + "loss": 3.325, + "step": 2720256 + }, + { + "epoch": 1.02, + "learning_rate": 5.457728600601561e-06, + "loss": 3.3146, + "step": 2720768 + }, + { + "epoch": 1.02, + "learning_rate": 5.449342653091041e-06, + "loss": 3.3207, + "step": 2721280 + }, + { + "epoch": 1.02, + "learning_rate": 5.440956705580521e-06, + "loss": 3.3215, + "step": 2721792 + }, + { + "epoch": 1.02, + "learning_rate": 5.432587136873732e-06, + "loss": 3.3263, + "step": 2722304 + }, + { + "epoch": 1.02, + "learning_rate": 5.4242011893632124e-06, + "loss": 3.3288, + "step": 2722816 + }, + { + "epoch": 1.02, + "learning_rate": 5.4158152418526916e-06, + "loss": 3.3226, + "step": 2723328 + }, + { + "epoch": 1.02, + "learning_rate": 5.407429294342172e-06, + "loss": 3.3119, + "step": 2723840 + }, + { + "epoch": 1.02, + "learning_rate": 5.399059725635383e-06, + "loss": 3.3372, + "step": 2724352 + }, + { + "epoch": 1.02, + "learning_rate": 5.390673778124863e-06, + "loss": 3.3142, + "step": 2724864 + }, + { + "epoch": 1.02, + "learning_rate": 5.382287830614343e-06, + "loss": 3.3239, + "step": 2725376 + }, + { + "epoch": 1.02, + "learning_rate": 5.373901883103823e-06, + "loss": 3.314, + "step": 2725888 + }, + { + "epoch": 1.02, + "learning_rate": 5.365532314397035e-06, + "loss": 3.3204, + "step": 2726400 + }, + { + "epoch": 1.02, + "learning_rate": 5.357146366886514e-06, + "loss": 3.3135, + "step": 2726912 + }, + { + "epoch": 1.02, + "learning_rate": 5.3487604193759946e-06, + "loss": 3.3263, + "step": 2727424 + }, + { + "epoch": 1.02, + "learning_rate": 5.340374471865474e-06, + "loss": 3.3149, + "step": 2727936 + }, + { + "epoch": 1.02, + "learning_rate": 5.332004903158685e-06, + "loss": 3.3184, + "step": 2728448 + }, + { + "epoch": 1.02, + "learning_rate": 5.323618955648165e-06, + "loss": 3.3231, + "step": 2728960 + }, + { + "epoch": 1.02, + "learning_rate": 5.315233008137645e-06, + "loss": 3.3167, + "step": 2729472 + }, + { + "epoch": 1.02, + "learning_rate": 5.306847060627125e-06, + "loss": 3.3312, + "step": 2729984 + }, + { + "epoch": 1.02, + "learning_rate": 5.298477491920337e-06, + "loss": 3.3402, + "step": 2730496 + }, + { + "epoch": 1.02, + "learning_rate": 5.290091544409816e-06, + "loss": 3.3268, + "step": 2731008 + }, + { + "epoch": 1.02, + "learning_rate": 5.281705596899296e-06, + "loss": 3.3202, + "step": 2731520 + }, + { + "epoch": 1.02, + "learning_rate": 5.273319649388776e-06, + "loss": 3.3213, + "step": 2732032 + }, + { + "epoch": 1.02, + "learning_rate": 5.2649500806819875e-06, + "loss": 3.3172, + "step": 2732544 + }, + { + "epoch": 1.02, + "learning_rate": 5.2565641331714674e-06, + "loss": 3.316, + "step": 2733056 + }, + { + "epoch": 1.02, + "learning_rate": 5.248178185660947e-06, + "loss": 3.3256, + "step": 2733568 + }, + { + "epoch": 1.02, + "learning_rate": 5.2397922381504265e-06, + "loss": 3.3082, + "step": 2734080 + }, + { + "epoch": 1.02, + "learning_rate": 5.231422669443638e-06, + "loss": 3.3235, + "step": 2734592 + }, + { + "epoch": 1.02, + "learning_rate": 5.223036721933118e-06, + "loss": 3.3231, + "step": 2735104 + }, + { + "epoch": 1.02, + "learning_rate": 5.214650774422598e-06, + "loss": 3.3243, + "step": 2735616 + }, + { + "epoch": 1.02, + "learning_rate": 5.206264826912078e-06, + "loss": 3.3196, + "step": 2736128 + }, + { + "epoch": 1.02, + "learning_rate": 5.19789525820529e-06, + "loss": 3.32, + "step": 2736640 + }, + { + "epoch": 1.02, + "learning_rate": 5.18950931069477e-06, + "loss": 3.3223, + "step": 2737152 + }, + { + "epoch": 1.02, + "learning_rate": 5.1811233631842496e-06, + "loss": 3.3257, + "step": 2737664 + }, + { + "epoch": 1.02, + "learning_rate": 5.1727374156737295e-06, + "loss": 3.322, + "step": 2738176 + }, + { + "epoch": 1.02, + "learning_rate": 5.164367846966941e-06, + "loss": 3.3335, + "step": 2738688 + }, + { + "epoch": 1.02, + "learning_rate": 5.15598189945642e-06, + "loss": 3.3125, + "step": 2739200 + }, + { + "epoch": 1.02, + "learning_rate": 5.1475959519459e-06, + "loss": 3.3273, + "step": 2739712 + }, + { + "epoch": 1.02, + "learning_rate": 5.13921000443538e-06, + "loss": 3.3209, + "step": 2740224 + }, + { + "epoch": 1.02, + "learning_rate": 5.130840435728591e-06, + "loss": 3.3218, + "step": 2740736 + }, + { + "epoch": 1.02, + "learning_rate": 5.122454488218072e-06, + "loss": 3.3193, + "step": 2741248 + }, + { + "epoch": 1.02, + "learning_rate": 5.114068540707551e-06, + "loss": 3.3328, + "step": 2741760 + }, + { + "epoch": 1.02, + "learning_rate": 5.105682593197032e-06, + "loss": 3.3207, + "step": 2742272 + }, + { + "epoch": 1.02, + "learning_rate": 5.0973130244902425e-06, + "loss": 3.341, + "step": 2742784 + }, + { + "epoch": 1.02, + "learning_rate": 5.088927076979723e-06, + "loss": 3.3209, + "step": 2743296 + }, + { + "epoch": 1.02, + "learning_rate": 5.080541129469202e-06, + "loss": 3.3275, + "step": 2743808 + }, + { + "epoch": 1.02, + "learning_rate": 5.072171560762414e-06, + "loss": 3.3184, + "step": 2744320 + }, + { + "epoch": 1.02, + "learning_rate": 5.063785613251894e-06, + "loss": 3.321, + "step": 2744832 + }, + { + "epoch": 1.02, + "learning_rate": 5.055399665741373e-06, + "loss": 3.3176, + "step": 2745344 + }, + { + "epoch": 1.02, + "learning_rate": 5.047013718230854e-06, + "loss": 3.3241, + "step": 2745856 + }, + { + "epoch": 1.02, + "learning_rate": 5.038644149524065e-06, + "loss": 3.318, + "step": 2746368 + }, + { + "epoch": 1.02, + "learning_rate": 5.030258202013545e-06, + "loss": 3.3116, + "step": 2746880 + }, + { + "epoch": 1.02, + "learning_rate": 5.021872254503025e-06, + "loss": 3.3184, + "step": 2747392 + }, + { + "epoch": 1.03, + "eval_loss": 3.873126983642578, + "eval_runtime": 326.0869, + "eval_samples_per_second": 1170.213, + "eval_steps_per_second": 36.57, + "step": 2747509 + }, + { + "epoch": 0.0, + "learning_rate": 5.0134863069925045e-06, + "loss": 3.3211, + "step": 2747904 + }, + { + "epoch": 0.0, + "learning_rate": 5.0051003594819845e-06, + "loss": 3.3212, + "step": 2748416 + }, + { + "epoch": 0.0, + "learning_rate": 4.9967144119714644e-06, + "loss": 3.3282, + "step": 2748928 + }, + { + "epoch": 0.0, + "learning_rate": 4.988328464460944e-06, + "loss": 3.3224, + "step": 2749440 + }, + { + "epoch": 0.0, + "learning_rate": 4.979958895754155e-06, + "loss": 3.3364, + "step": 2749952 + }, + { + "epoch": 0.0, + "learning_rate": 4.971572948243636e-06, + "loss": 3.3223, + "step": 2750464 + }, + { + "epoch": 0.0, + "learning_rate": 4.963187000733115e-06, + "loss": 3.3213, + "step": 2750976 + }, + { + "epoch": 0.0, + "learning_rate": 4.954801053222596e-06, + "loss": 3.3086, + "step": 2751488 + }, + { + "epoch": 0.0, + "learning_rate": 4.946431484515807e-06, + "loss": 3.3236, + "step": 2752000 + }, + { + "epoch": 0.0, + "learning_rate": 4.938061915809018e-06, + "loss": 3.3199, + "step": 2752512 + }, + { + "epoch": 0.0, + "learning_rate": 4.929675968298498e-06, + "loss": 3.3184, + "step": 2753024 + }, + { + "epoch": 0.0, + "learning_rate": 4.921290020787978e-06, + "loss": 3.3216, + "step": 2753536 + }, + { + "epoch": 0.0, + "learning_rate": 4.912904073277458e-06, + "loss": 3.3093, + "step": 2754048 + }, + { + "epoch": 0.0, + "learning_rate": 4.904518125766937e-06, + "loss": 3.3181, + "step": 2754560 + }, + { + "epoch": 0.0, + "learning_rate": 4.896148557060149e-06, + "loss": 3.3126, + "step": 2755072 + }, + { + "epoch": 0.0, + "learning_rate": 4.887762609549629e-06, + "loss": 3.3123, + "step": 2755584 + }, + { + "epoch": 0.0, + "learning_rate": 4.879376662039109e-06, + "loss": 3.31, + "step": 2756096 + }, + { + "epoch": 0.0, + "learning_rate": 4.870990714528589e-06, + "loss": 3.3193, + "step": 2756608 + }, + { + "epoch": 0.0, + "learning_rate": 4.862604767018069e-06, + "loss": 3.3151, + "step": 2757120 + }, + { + "epoch": 0.0, + "learning_rate": 4.854218819507549e-06, + "loss": 3.334, + "step": 2757632 + }, + { + "epoch": 0.0, + "learning_rate": 4.845832871997028e-06, + "loss": 3.3181, + "step": 2758144 + }, + { + "epoch": 0.0, + "learning_rate": 4.837446924486509e-06, + "loss": 3.3262, + "step": 2758656 + }, + { + "epoch": 0.0, + "learning_rate": 4.8290773557797194e-06, + "loss": 3.3185, + "step": 2759168 + }, + { + "epoch": 0.0, + "learning_rate": 4.820691408269199e-06, + "loss": 3.3255, + "step": 2759680 + }, + { + "epoch": 0.0, + "learning_rate": 4.812305460758679e-06, + "loss": 3.3184, + "step": 2760192 + }, + { + "epoch": 0.0, + "learning_rate": 4.80391951324816e-06, + "loss": 3.3284, + "step": 2760704 + }, + { + "epoch": 0.0, + "learning_rate": 4.795549944541371e-06, + "loss": 3.314, + "step": 2761216 + }, + { + "epoch": 0.0, + "learning_rate": 4.787163997030851e-06, + "loss": 3.3172, + "step": 2761728 + }, + { + "epoch": 0.0, + "learning_rate": 4.778778049520331e-06, + "loss": 3.3081, + "step": 2762240 + }, + { + "epoch": 0.0, + "learning_rate": 4.7704084808135425e-06, + "loss": 3.3201, + "step": 2762752 + }, + { + "epoch": 0.01, + "learning_rate": 4.762022533303022e-06, + "loss": 3.3275, + "step": 2763264 + }, + { + "epoch": 0.01, + "learning_rate": 4.7536365857925015e-06, + "loss": 3.3203, + "step": 2763776 + }, + { + "epoch": 0.01, + "learning_rate": 4.7452506382819815e-06, + "loss": 3.3304, + "step": 2764288 + }, + { + "epoch": 0.01, + "learning_rate": 4.7368646907714615e-06, + "loss": 3.3195, + "step": 2764800 + }, + { + "epoch": 0.01, + "learning_rate": 4.728478743260941e-06, + "loss": 3.3153, + "step": 2765312 + }, + { + "epoch": 0.01, + "learning_rate": 4.720092795750421e-06, + "loss": 3.3254, + "step": 2765824 + }, + { + "epoch": 0.01, + "learning_rate": 4.711723227043633e-06, + "loss": 3.3218, + "step": 2766336 + }, + { + "epoch": 0.01, + "learning_rate": 4.703337279533113e-06, + "loss": 3.3114, + "step": 2766848 + }, + { + "epoch": 0.01, + "learning_rate": 4.694951332022592e-06, + "loss": 3.3082, + "step": 2767360 + }, + { + "epoch": 0.01, + "learning_rate": 4.686565384512073e-06, + "loss": 3.3097, + "step": 2767872 + }, + { + "epoch": 0.01, + "learning_rate": 4.678195815805284e-06, + "loss": 3.315, + "step": 2768384 + }, + { + "epoch": 0.01, + "learning_rate": 4.669809868294764e-06, + "loss": 3.3231, + "step": 2768896 + }, + { + "epoch": 0.01, + "learning_rate": 4.6614239207842436e-06, + "loss": 3.3203, + "step": 2769408 + }, + { + "epoch": 0.01, + "learning_rate": 4.6530379732737235e-06, + "loss": 3.3103, + "step": 2769920 + }, + { + "epoch": 0.01, + "learning_rate": 4.644668404566935e-06, + "loss": 3.3175, + "step": 2770432 + }, + { + "epoch": 0.01, + "learning_rate": 4.636282457056415e-06, + "loss": 3.3174, + "step": 2770944 + }, + { + "epoch": 0.01, + "learning_rate": 4.627896509545895e-06, + "loss": 3.315, + "step": 2771456 + }, + { + "epoch": 0.01, + "learning_rate": 4.619510562035374e-06, + "loss": 3.3079, + "step": 2771968 + }, + { + "epoch": 0.01, + "learning_rate": 4.611140993328586e-06, + "loss": 3.296, + "step": 2772480 + }, + { + "epoch": 0.01, + "learning_rate": 4.602755045818066e-06, + "loss": 3.334, + "step": 2772992 + }, + { + "epoch": 0.01, + "learning_rate": 4.594369098307546e-06, + "loss": 3.3232, + "step": 2773504 + }, + { + "epoch": 0.01, + "learning_rate": 4.585983150797026e-06, + "loss": 3.3192, + "step": 2774016 + }, + { + "epoch": 0.01, + "learning_rate": 4.577613582090237e-06, + "loss": 3.3153, + "step": 2774528 + }, + { + "epoch": 0.01, + "learning_rate": 4.569244013383448e-06, + "loss": 3.3093, + "step": 2775040 + }, + { + "epoch": 0.01, + "learning_rate": 4.560858065872928e-06, + "loss": 3.3033, + "step": 2775552 + }, + { + "epoch": 0.01, + "learning_rate": 4.552472118362408e-06, + "loss": 3.3171, + "step": 2776064 + }, + { + "epoch": 0.01, + "learning_rate": 4.544086170851888e-06, + "loss": 3.315, + "step": 2776576 + }, + { + "epoch": 0.01, + "learning_rate": 4.535700223341368e-06, + "loss": 3.3146, + "step": 2777088 + }, + { + "epoch": 0.01, + "learning_rate": 4.527314275830848e-06, + "loss": 3.3307, + "step": 2777600 + }, + { + "epoch": 0.01, + "learning_rate": 4.518928328320328e-06, + "loss": 3.3092, + "step": 2778112 + }, + { + "epoch": 0.01, + "learning_rate": 4.510542380809808e-06, + "loss": 3.3057, + "step": 2778624 + }, + { + "epoch": 0.01, + "learning_rate": 4.5021728121030194e-06, + "loss": 3.3272, + "step": 2779136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4937868645924986e-06, + "loss": 3.3026, + "step": 2779648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4854009170819785e-06, + "loss": 3.3044, + "step": 2780160 + }, + { + "epoch": 0.01, + "learning_rate": 4.47703134837519e-06, + "loss": 3.3254, + "step": 2780672 + }, + { + "epoch": 0.01, + "learning_rate": 4.468661779668402e-06, + "loss": 3.3176, + "step": 2781184 + }, + { + "epoch": 0.01, + "learning_rate": 4.460275832157882e-06, + "loss": 3.3096, + "step": 2781696 + }, + { + "epoch": 0.01, + "learning_rate": 4.451889884647361e-06, + "loss": 3.3076, + "step": 2782208 + }, + { + "epoch": 0.01, + "learning_rate": 4.443503937136842e-06, + "loss": 3.3038, + "step": 2782720 + }, + { + "epoch": 0.01, + "learning_rate": 4.435117989626321e-06, + "loss": 3.3053, + "step": 2783232 + }, + { + "epoch": 0.01, + "learning_rate": 4.4267320421158016e-06, + "loss": 3.3207, + "step": 2783744 + }, + { + "epoch": 0.01, + "learning_rate": 4.418346094605281e-06, + "loss": 3.3036, + "step": 2784256 + }, + { + "epoch": 0.01, + "learning_rate": 4.409960147094761e-06, + "loss": 3.323, + "step": 2784768 + }, + { + "epoch": 0.01, + "learning_rate": 4.401590578387972e-06, + "loss": 3.3174, + "step": 2785280 + }, + { + "epoch": 0.01, + "learning_rate": 4.393204630877451e-06, + "loss": 3.3303, + "step": 2785792 + }, + { + "epoch": 0.01, + "learning_rate": 4.384818683366932e-06, + "loss": 3.3116, + "step": 2786304 + }, + { + "epoch": 0.01, + "learning_rate": 4.376432735856411e-06, + "loss": 3.3106, + "step": 2786816 + }, + { + "epoch": 0.01, + "learning_rate": 4.368063167149623e-06, + "loss": 3.3202, + "step": 2787328 + }, + { + "epoch": 0.01, + "learning_rate": 4.359677219639103e-06, + "loss": 3.3064, + "step": 2787840 + }, + { + "epoch": 0.01, + "learning_rate": 4.351291272128583e-06, + "loss": 3.3268, + "step": 2788352 + }, + { + "epoch": 0.01, + "learning_rate": 4.342905324618063e-06, + "loss": 3.3137, + "step": 2788864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3345357559112744e-06, + "loss": 3.3129, + "step": 2789376 + }, + { + "epoch": 0.01, + "learning_rate": 4.326149808400754e-06, + "loss": 3.3148, + "step": 2789888 + }, + { + "epoch": 0.01, + "learning_rate": 4.3177638608902335e-06, + "loss": 3.3029, + "step": 2790400 + }, + { + "epoch": 0.01, + "learning_rate": 4.309377913379714e-06, + "loss": 3.3056, + "step": 2790912 + }, + { + "epoch": 0.01, + "learning_rate": 4.301008344672925e-06, + "loss": 3.3132, + "step": 2791424 + }, + { + "epoch": 0.01, + "learning_rate": 4.292622397162405e-06, + "loss": 3.3207, + "step": 2791936 + }, + { + "epoch": 0.01, + "learning_rate": 4.284236449651885e-06, + "loss": 3.3065, + "step": 2792448 + }, + { + "epoch": 0.01, + "learning_rate": 4.275850502141365e-06, + "loss": 3.3161, + "step": 2792960 + }, + { + "epoch": 0.02, + "learning_rate": 4.267480933434577e-06, + "loss": 3.3055, + "step": 2793472 + }, + { + "epoch": 0.02, + "learning_rate": 4.2590949859240565e-06, + "loss": 3.3062, + "step": 2793984 + }, + { + "epoch": 0.02, + "learning_rate": 4.2507090384135365e-06, + "loss": 3.3012, + "step": 2794496 + }, + { + "epoch": 0.02, + "learning_rate": 4.242323090903016e-06, + "loss": 3.3094, + "step": 2795008 + }, + { + "epoch": 0.02, + "learning_rate": 4.233953522196227e-06, + "loss": 3.3245, + "step": 2795520 + }, + { + "epoch": 0.02, + "learning_rate": 4.225567574685707e-06, + "loss": 3.3205, + "step": 2796032 + }, + { + "epoch": 0.02, + "learning_rate": 4.217181627175187e-06, + "loss": 3.3188, + "step": 2796544 + }, + { + "epoch": 0.02, + "learning_rate": 4.208795679664667e-06, + "loss": 3.3078, + "step": 2797056 + }, + { + "epoch": 0.02, + "learning_rate": 4.200426110957879e-06, + "loss": 3.3141, + "step": 2797568 + }, + { + "epoch": 0.02, + "learning_rate": 4.192040163447358e-06, + "loss": 3.3103, + "step": 2798080 + }, + { + "epoch": 0.02, + "learning_rate": 4.183654215936839e-06, + "loss": 3.3213, + "step": 2798592 + }, + { + "epoch": 0.02, + "learning_rate": 4.175268268426319e-06, + "loss": 3.3168, + "step": 2799104 + }, + { + "epoch": 0.02, + "learning_rate": 4.16689869971953e-06, + "loss": 3.3144, + "step": 2799616 + }, + { + "epoch": 0.02, + "learning_rate": 4.158512752209009e-06, + "loss": 3.3049, + "step": 2800128 + }, + { + "epoch": 0.02, + "learning_rate": 4.150126804698489e-06, + "loss": 3.3279, + "step": 2800640 + }, + { + "epoch": 0.02, + "learning_rate": 4.141757235991701e-06, + "loss": 3.3047, + "step": 2801152 + }, + { + "epoch": 0.02, + "learning_rate": 4.13337128848118e-06, + "loss": 3.3145, + "step": 2801664 + }, + { + "epoch": 0.02, + "learning_rate": 4.124985340970661e-06, + "loss": 3.3083, + "step": 2802176 + }, + { + "epoch": 0.02, + "learning_rate": 4.11659939346014e-06, + "loss": 3.3128, + "step": 2802688 + }, + { + "epoch": 0.02, + "learning_rate": 4.108229824753352e-06, + "loss": 3.3035, + "step": 2803200 + }, + { + "epoch": 0.02, + "learning_rate": 4.0998438772428316e-06, + "loss": 3.3196, + "step": 2803712 + }, + { + "epoch": 0.02, + "learning_rate": 4.0914579297323115e-06, + "loss": 3.3023, + "step": 2804224 + }, + { + "epoch": 0.02, + "learning_rate": 4.0830719822217915e-06, + "loss": 3.314, + "step": 2804736 + }, + { + "epoch": 0.02, + "learning_rate": 4.074702413515003e-06, + "loss": 3.3142, + "step": 2805248 + }, + { + "epoch": 0.02, + "learning_rate": 4.066316466004483e-06, + "loss": 3.3116, + "step": 2805760 + }, + { + "epoch": 0.02, + "learning_rate": 4.057930518493962e-06, + "loss": 3.3194, + "step": 2806272 + }, + { + "epoch": 0.02, + "learning_rate": 4.049544570983443e-06, + "loss": 3.3292, + "step": 2806784 + }, + { + "epoch": 0.02, + "learning_rate": 4.041175002276654e-06, + "loss": 3.3157, + "step": 2807296 + }, + { + "epoch": 0.02, + "learning_rate": 4.032789054766134e-06, + "loss": 3.3162, + "step": 2807808 + }, + { + "epoch": 0.02, + "learning_rate": 4.024403107255614e-06, + "loss": 3.314, + "step": 2808320 + }, + { + "epoch": 0.02, + "learning_rate": 4.016017159745094e-06, + "loss": 3.3091, + "step": 2808832 + }, + { + "epoch": 0.02, + "learning_rate": 4.007647591038305e-06, + "loss": 3.3063, + "step": 2809344 + }, + { + "epoch": 0.02, + "learning_rate": 3.999261643527785e-06, + "loss": 3.3203, + "step": 2809856 + }, + { + "epoch": 0.02, + "learning_rate": 3.990875696017265e-06, + "loss": 3.2975, + "step": 2810368 + }, + { + "epoch": 0.02, + "learning_rate": 3.982489748506744e-06, + "loss": 3.3168, + "step": 2810880 + }, + { + "epoch": 0.02, + "learning_rate": 3.974120179799956e-06, + "loss": 3.3116, + "step": 2811392 + }, + { + "epoch": 0.02, + "learning_rate": 3.965734232289436e-06, + "loss": 3.3185, + "step": 2811904 + }, + { + "epoch": 0.02, + "learning_rate": 3.957348284778916e-06, + "loss": 3.3104, + "step": 2812416 + }, + { + "epoch": 0.02, + "learning_rate": 3.948962337268396e-06, + "loss": 3.3129, + "step": 2812928 + }, + { + "epoch": 0.02, + "learning_rate": 3.9405927685616074e-06, + "loss": 3.3093, + "step": 2813440 + }, + { + "epoch": 0.02, + "learning_rate": 3.9322068210510866e-06, + "loss": 3.3213, + "step": 2813952 + }, + { + "epoch": 0.02, + "learning_rate": 3.9238208735405665e-06, + "loss": 3.3135, + "step": 2814464 + }, + { + "epoch": 0.02, + "learning_rate": 3.9154349260300465e-06, + "loss": 3.3257, + "step": 2814976 + }, + { + "epoch": 0.02, + "learning_rate": 3.907065357323258e-06, + "loss": 3.3022, + "step": 2815488 + }, + { + "epoch": 0.02, + "learning_rate": 3.898679409812738e-06, + "loss": 3.3176, + "step": 2816000 + }, + { + "epoch": 0.02, + "learning_rate": 3.890293462302218e-06, + "loss": 3.3163, + "step": 2816512 + }, + { + "epoch": 0.02, + "learning_rate": 3.881907514791698e-06, + "loss": 3.3132, + "step": 2817024 + }, + { + "epoch": 0.02, + "learning_rate": 3.873537946084909e-06, + "loss": 3.3094, + "step": 2817536 + }, + { + "epoch": 0.02, + "learning_rate": 3.8651519985743896e-06, + "loss": 3.323, + "step": 2818048 + }, + { + "epoch": 0.02, + "learning_rate": 3.856766051063869e-06, + "loss": 3.3129, + "step": 2818560 + }, + { + "epoch": 0.02, + "learning_rate": 3.848380103553349e-06, + "loss": 3.335, + "step": 2819072 + }, + { + "epoch": 0.02, + "learning_rate": 3.84001053484656e-06, + "loss": 3.3088, + "step": 2819584 + }, + { + "epoch": 0.02, + "learning_rate": 3.83162458733604e-06, + "loss": 3.319, + "step": 2820096 + }, + { + "epoch": 0.02, + "learning_rate": 3.82323863982552e-06, + "loss": 3.3101, + "step": 2820608 + }, + { + "epoch": 0.02, + "learning_rate": 3.814852692315e-06, + "loss": 3.3115, + "step": 2821120 + }, + { + "epoch": 0.02, + "learning_rate": 3.8064831236082113e-06, + "loss": 3.3162, + "step": 2821632 + }, + { + "epoch": 0.02, + "learning_rate": 3.798097176097691e-06, + "loss": 3.3103, + "step": 2822144 + }, + { + "epoch": 0.02, + "learning_rate": 3.7897112285871713e-06, + "loss": 3.3137, + "step": 2822656 + }, + { + "epoch": 0.02, + "learning_rate": 3.781325281076651e-06, + "loss": 3.3003, + "step": 2823168 + }, + { + "epoch": 0.02, + "learning_rate": 3.772955712369863e-06, + "loss": 3.3125, + "step": 2823680 + }, + { + "epoch": 0.03, + "eval_loss": 3.8731698989868164, + "eval_runtime": 303.7832, + "eval_samples_per_second": 1256.13, + "eval_steps_per_second": 39.255, + "step": 2823829 + }, + { + "epoch": 1.0, + "learning_rate": 3.7645697648593424e-06, + "loss": 3.3155, + "step": 2824192 + }, + { + "epoch": 1.0, + "learning_rate": 3.756183817348822e-06, + "loss": 3.3133, + "step": 2824704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7477978698383023e-06, + "loss": 3.3175, + "step": 2825216 + }, + { + "epoch": 1.0, + "learning_rate": 3.739428301131513e-06, + "loss": 3.3178, + "step": 2825728 + }, + { + "epoch": 1.0, + "learning_rate": 3.7310423536209935e-06, + "loss": 3.3257, + "step": 2826240 + }, + { + "epoch": 1.0, + "learning_rate": 3.722656406110473e-06, + "loss": 3.3163, + "step": 2826752 + }, + { + "epoch": 1.0, + "learning_rate": 3.7142868374036846e-06, + "loss": 3.3103, + "step": 2827264 + }, + { + "epoch": 1.0, + "learning_rate": 3.705900889893164e-06, + "loss": 3.3032, + "step": 2827776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6975149423826445e-06, + "loss": 3.3134, + "step": 2828288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6891289948721245e-06, + "loss": 3.3122, + "step": 2828800 + }, + { + "epoch": 1.0, + "learning_rate": 3.680743047361604e-06, + "loss": 3.3135, + "step": 2829312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6723570998510844e-06, + "loss": 3.3076, + "step": 2829824 + }, + { + "epoch": 1.0, + "learning_rate": 3.663971152340564e-06, + "loss": 3.3049, + "step": 2830336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6555852048300443e-06, + "loss": 3.3056, + "step": 2830848 + }, + { + "epoch": 1.0, + "learning_rate": 3.647215636123255e-06, + "loss": 3.3065, + "step": 2831360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6388460674164668e-06, + "loss": 3.3016, + "step": 2831872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6304601199059463e-06, + "loss": 3.3045, + "step": 2832384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6220741723954267e-06, + "loss": 3.3098, + "step": 2832896 + }, + { + "epoch": 1.0, + "learning_rate": 3.613688224884906e-06, + "loss": 3.3068, + "step": 2833408 + }, + { + "epoch": 1.0, + "learning_rate": 3.605302277374386e-06, + "loss": 3.326, + "step": 2833920 + }, + { + "epoch": 1.0, + "learning_rate": 3.596916329863866e-06, + "loss": 3.3154, + "step": 2834432 + }, + { + "epoch": 1.0, + "learning_rate": 3.588530382353346e-06, + "loss": 3.3185, + "step": 2834944 + }, + { + "epoch": 1.0, + "learning_rate": 3.580144434842826e-06, + "loss": 3.3083, + "step": 2835456 + }, + { + "epoch": 1.0, + "learning_rate": 3.5717748661360372e-06, + "loss": 3.3164, + "step": 2835968 + }, + { + "epoch": 1.0, + "learning_rate": 3.5633889186255176e-06, + "loss": 3.3107, + "step": 2836480 + }, + { + "epoch": 1.0, + "learning_rate": 3.555002971114997e-06, + "loss": 3.3224, + "step": 2836992 + }, + { + "epoch": 1.0, + "learning_rate": 3.5466170236044767e-06, + "loss": 3.3083, + "step": 2837504 + }, + { + "epoch": 1.0, + "learning_rate": 3.5382474548976883e-06, + "loss": 3.3072, + "step": 2838016 + }, + { + "epoch": 1.0, + "learning_rate": 3.529861507387168e-06, + "loss": 3.3033, + "step": 2838528 + }, + { + "epoch": 1.0, + "learning_rate": 3.5214919386803795e-06, + "loss": 3.3129, + "step": 2839040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5131059911698594e-06, + "loss": 3.3145, + "step": 2839552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5047200436593394e-06, + "loss": 3.3135, + "step": 2840064 + }, + { + "epoch": 1.01, + "learning_rate": 3.4963340961488194e-06, + "loss": 3.3201, + "step": 2840576 + }, + { + "epoch": 1.01, + "learning_rate": 3.4879481486382993e-06, + "loss": 3.3146, + "step": 2841088 + }, + { + "epoch": 1.01, + "learning_rate": 3.4795622011277793e-06, + "loss": 3.3065, + "step": 2841600 + }, + { + "epoch": 1.01, + "learning_rate": 3.471176253617259e-06, + "loss": 3.3203, + "step": 2842112 + }, + { + "epoch": 1.01, + "learning_rate": 3.462790306106739e-06, + "loss": 3.3125, + "step": 2842624 + }, + { + "epoch": 1.01, + "learning_rate": 3.45442073739995e-06, + "loss": 3.3037, + "step": 2843136 + }, + { + "epoch": 1.01, + "learning_rate": 3.4460347898894303e-06, + "loss": 3.3018, + "step": 2843648 + }, + { + "epoch": 1.01, + "learning_rate": 3.43764884237891e-06, + "loss": 3.2997, + "step": 2844160 + }, + { + "epoch": 1.01, + "learning_rate": 3.4292792736721215e-06, + "loss": 3.3026, + "step": 2844672 + }, + { + "epoch": 1.01, + "learning_rate": 3.420893326161601e-06, + "loss": 3.3187, + "step": 2845184 + }, + { + "epoch": 1.01, + "learning_rate": 3.4125073786510814e-06, + "loss": 3.3104, + "step": 2845696 + }, + { + "epoch": 1.01, + "learning_rate": 3.404121431140561e-06, + "loss": 3.3033, + "step": 2846208 + }, + { + "epoch": 1.01, + "learning_rate": 3.3957518624337726e-06, + "loss": 3.312, + "step": 2846720 + }, + { + "epoch": 1.01, + "learning_rate": 3.3873659149232526e-06, + "loss": 3.3074, + "step": 2847232 + }, + { + "epoch": 1.01, + "learning_rate": 3.378979967412732e-06, + "loss": 3.3073, + "step": 2847744 + }, + { + "epoch": 1.01, + "learning_rate": 3.3705940199022125e-06, + "loss": 3.297, + "step": 2848256 + }, + { + "epoch": 1.01, + "learning_rate": 3.3622244511954233e-06, + "loss": 3.2856, + "step": 2848768 + }, + { + "epoch": 1.01, + "learning_rate": 3.3538385036849036e-06, + "loss": 3.3289, + "step": 2849280 + }, + { + "epoch": 1.01, + "learning_rate": 3.345452556174383e-06, + "loss": 3.3141, + "step": 2849792 + }, + { + "epoch": 1.01, + "learning_rate": 3.3370666086638635e-06, + "loss": 3.314, + "step": 2850304 + }, + { + "epoch": 1.01, + "learning_rate": 3.3286970399570743e-06, + "loss": 3.2997, + "step": 2850816 + }, + { + "epoch": 1.01, + "learning_rate": 3.3203110924465543e-06, + "loss": 3.3081, + "step": 2851328 + }, + { + "epoch": 1.01, + "learning_rate": 3.3119251449360342e-06, + "loss": 3.2954, + "step": 2851840 + }, + { + "epoch": 1.01, + "learning_rate": 3.303539197425514e-06, + "loss": 3.3066, + "step": 2852352 + }, + { + "epoch": 1.01, + "learning_rate": 3.295169628718726e-06, + "loss": 3.3062, + "step": 2852864 + }, + { + "epoch": 1.01, + "learning_rate": 3.2867836812082054e-06, + "loss": 3.3047, + "step": 2853376 + }, + { + "epoch": 1.01, + "learning_rate": 3.2783977336976857e-06, + "loss": 3.3203, + "step": 2853888 + }, + { + "epoch": 1.01, + "learning_rate": 3.2700117861871653e-06, + "loss": 3.3025, + "step": 2854400 + }, + { + "epoch": 1.01, + "learning_rate": 3.261642217480377e-06, + "loss": 3.2964, + "step": 2854912 + }, + { + "epoch": 1.01, + "learning_rate": 3.2532562699698565e-06, + "loss": 3.3205, + "step": 2855424 + }, + { + "epoch": 1.01, + "learning_rate": 3.244870322459336e-06, + "loss": 3.2916, + "step": 2855936 + }, + { + "epoch": 1.01, + "learning_rate": 3.2364843749488164e-06, + "loss": 3.2952, + "step": 2856448 + }, + { + "epoch": 1.01, + "learning_rate": 3.2281148062420276e-06, + "loss": 3.3139, + "step": 2856960 + }, + { + "epoch": 1.01, + "learning_rate": 3.219728858731508e-06, + "loss": 3.3154, + "step": 2857472 + }, + { + "epoch": 1.01, + "learning_rate": 3.2113429112209875e-06, + "loss": 3.2997, + "step": 2857984 + }, + { + "epoch": 1.01, + "learning_rate": 3.202956963710468e-06, + "loss": 3.3036, + "step": 2858496 + }, + { + "epoch": 1.01, + "learning_rate": 3.1945873950036787e-06, + "loss": 3.2921, + "step": 2859008 + }, + { + "epoch": 1.01, + "learning_rate": 3.186201447493159e-06, + "loss": 3.2996, + "step": 2859520 + }, + { + "epoch": 1.01, + "learning_rate": 3.1778154999826386e-06, + "loss": 3.3109, + "step": 2860032 + }, + { + "epoch": 1.01, + "learning_rate": 3.169429552472118e-06, + "loss": 3.2973, + "step": 2860544 + }, + { + "epoch": 1.01, + "learning_rate": 3.1610599837653297e-06, + "loss": 3.3143, + "step": 2861056 + }, + { + "epoch": 1.01, + "learning_rate": 3.1526740362548093e-06, + "loss": 3.309, + "step": 2861568 + }, + { + "epoch": 1.01, + "learning_rate": 3.1442880887442897e-06, + "loss": 3.3211, + "step": 2862080 + }, + { + "epoch": 1.01, + "learning_rate": 3.1359021412337696e-06, + "loss": 3.3009, + "step": 2862592 + }, + { + "epoch": 1.01, + "learning_rate": 3.1275325725269812e-06, + "loss": 3.3069, + "step": 2863104 + }, + { + "epoch": 1.01, + "learning_rate": 3.1191466250164608e-06, + "loss": 3.311, + "step": 2863616 + }, + { + "epoch": 1.01, + "learning_rate": 3.1107606775059407e-06, + "loss": 3.2992, + "step": 2864128 + }, + { + "epoch": 1.01, + "learning_rate": 3.1023747299954207e-06, + "loss": 3.3147, + "step": 2864640 + }, + { + "epoch": 1.01, + "learning_rate": 3.094005161288632e-06, + "loss": 3.3066, + "step": 2865152 + }, + { + "epoch": 1.01, + "learning_rate": 3.085619213778112e-06, + "loss": 3.3076, + "step": 2865664 + }, + { + "epoch": 1.01, + "learning_rate": 3.077233266267592e-06, + "loss": 3.3066, + "step": 2866176 + }, + { + "epoch": 1.01, + "learning_rate": 3.0688473187570718e-06, + "loss": 3.2942, + "step": 2866688 + }, + { + "epoch": 1.01, + "learning_rate": 3.060477750050283e-06, + "loss": 3.2957, + "step": 2867200 + }, + { + "epoch": 1.01, + "learning_rate": 3.052091802539763e-06, + "loss": 3.3054, + "step": 2867712 + }, + { + "epoch": 1.01, + "learning_rate": 3.043705855029243e-06, + "loss": 3.3131, + "step": 2868224 + }, + { + "epoch": 1.01, + "learning_rate": 3.035319907518723e-06, + "loss": 3.2981, + "step": 2868736 + }, + { + "epoch": 1.01, + "learning_rate": 3.026950338811934e-06, + "loss": 3.3064, + "step": 2869248 + }, + { + "epoch": 1.02, + "learning_rate": 3.018564391301414e-06, + "loss": 3.2979, + "step": 2869760 + }, + { + "epoch": 1.02, + "learning_rate": 3.010178443790894e-06, + "loss": 3.2986, + "step": 2870272 + }, + { + "epoch": 1.02, + "learning_rate": 3.001808875084105e-06, + "loss": 3.2934, + "step": 2870784 + }, + { + "epoch": 1.02, + "learning_rate": 2.993422927573585e-06, + "loss": 3.3058, + "step": 2871296 + }, + { + "epoch": 1.02, + "learning_rate": 2.985036980063065e-06, + "loss": 3.3164, + "step": 2871808 + }, + { + "epoch": 1.02, + "learning_rate": 2.976651032552545e-06, + "loss": 3.3103, + "step": 2872320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9682814638457563e-06, + "loss": 3.3101, + "step": 2872832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9598955163352362e-06, + "loss": 3.2986, + "step": 2873344 + }, + { + "epoch": 1.02, + "learning_rate": 2.951509568824716e-06, + "loss": 3.3043, + "step": 2873856 + }, + { + "epoch": 1.02, + "learning_rate": 2.943123621314196e-06, + "loss": 3.3036, + "step": 2874368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9347540526074074e-06, + "loss": 3.3132, + "step": 2874880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9263681050968873e-06, + "loss": 3.3078, + "step": 2875392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9179821575863673e-06, + "loss": 3.3084, + "step": 2875904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9095962100758472e-06, + "loss": 3.2997, + "step": 2876416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9012266413690584e-06, + "loss": 3.3181, + "step": 2876928 + }, + { + "epoch": 1.02, + "learning_rate": 2.8928406938585384e-06, + "loss": 3.2971, + "step": 2877440 + }, + { + "epoch": 1.02, + "learning_rate": 2.8844547463480183e-06, + "loss": 3.3071, + "step": 2877952 + }, + { + "epoch": 1.02, + "learning_rate": 2.876068798837498e-06, + "loss": 3.2971, + "step": 2878464 + }, + { + "epoch": 1.02, + "learning_rate": 2.8676992301307095e-06, + "loss": 3.3083, + "step": 2878976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8593132826201895e-06, + "loss": 3.2978, + "step": 2879488 + }, + { + "epoch": 1.02, + "learning_rate": 2.8509273351096694e-06, + "loss": 3.307, + "step": 2880000 + }, + { + "epoch": 1.02, + "learning_rate": 2.8425413875991494e-06, + "loss": 3.2938, + "step": 2880512 + }, + { + "epoch": 1.02, + "learning_rate": 2.8341718188923606e-06, + "loss": 3.3043, + "step": 2881024 + }, + { + "epoch": 1.02, + "learning_rate": 2.8257858713818406e-06, + "loss": 3.3042, + "step": 2881536 + }, + { + "epoch": 1.02, + "learning_rate": 2.8173999238713205e-06, + "loss": 3.3016, + "step": 2882048 + }, + { + "epoch": 1.02, + "learning_rate": 2.8090139763608e-06, + "loss": 3.31, + "step": 2882560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8006444076540117e-06, + "loss": 3.3205, + "step": 2883072 + }, + { + "epoch": 1.02, + "learning_rate": 2.792258460143491e-06, + "loss": 3.3063, + "step": 2883584 + }, + { + "epoch": 1.02, + "learning_rate": 2.783872512632971e-06, + "loss": 3.3104, + "step": 2884096 + }, + { + "epoch": 1.02, + "learning_rate": 2.775486565122451e-06, + "loss": 3.3035, + "step": 2884608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7671169964156628e-06, + "loss": 3.3001, + "step": 2885120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7587310489051427e-06, + "loss": 3.3029, + "step": 2885632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7503451013946227e-06, + "loss": 3.3106, + "step": 2886144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7419591538841026e-06, + "loss": 3.2883, + "step": 2886656 + }, + { + "epoch": 1.02, + "learning_rate": 2.733605963981045e-06, + "loss": 3.3069, + "step": 2887168 + }, + { + "epoch": 1.02, + "learning_rate": 2.725220016470525e-06, + "loss": 3.3042, + "step": 2887680 + }, + { + "epoch": 1.02, + "learning_rate": 2.716834068960005e-06, + "loss": 3.3074, + "step": 2888192 + }, + { + "epoch": 1.02, + "learning_rate": 2.708448121449485e-06, + "loss": 3.3059, + "step": 2888704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7000621739389645e-06, + "loss": 3.3015, + "step": 2889216 + }, + { + "epoch": 1.02, + "learning_rate": 2.6916762264284445e-06, + "loss": 3.3027, + "step": 2889728 + }, + { + "epoch": 1.02, + "learning_rate": 2.683290278917925e-06, + "loss": 3.3131, + "step": 2890240 + }, + { + "epoch": 1.02, + "learning_rate": 2.6749043314074048e-06, + "loss": 3.3089, + "step": 2890752 + }, + { + "epoch": 1.02, + "learning_rate": 2.666534762700616e-06, + "loss": 3.3171, + "step": 2891264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6581651939938272e-06, + "loss": 3.2948, + "step": 2891776 + }, + { + "epoch": 1.02, + "learning_rate": 2.649779246483307e-06, + "loss": 3.3072, + "step": 2892288 + }, + { + "epoch": 1.02, + "learning_rate": 2.641393298972787e-06, + "loss": 3.3085, + "step": 2892800 + }, + { + "epoch": 1.02, + "learning_rate": 2.633007351462267e-06, + "loss": 3.3041, + "step": 2893312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6246214039517466e-06, + "loss": 3.3038, + "step": 2893824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6162354564412266e-06, + "loss": 3.3127, + "step": 2894336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6078495089307065e-06, + "loss": 3.305, + "step": 2894848 + }, + { + "epoch": 1.02, + "learning_rate": 2.5994635614201865e-06, + "loss": 3.3257, + "step": 2895360 + }, + { + "epoch": 1.02, + "learning_rate": 2.591093992713398e-06, + "loss": 3.3033, + "step": 2895872 + }, + { + "epoch": 1.02, + "learning_rate": 2.582708045202878e-06, + "loss": 3.308, + "step": 2896384 + }, + { + "epoch": 1.02, + "learning_rate": 2.574322097692358e-06, + "loss": 3.3006, + "step": 2896896 + }, + { + "epoch": 1.02, + "learning_rate": 2.5659361501818376e-06, + "loss": 3.3099, + "step": 2897408 + }, + { + "epoch": 1.02, + "learning_rate": 2.557566581475049e-06, + "loss": 3.3008, + "step": 2897920 + }, + { + "epoch": 1.02, + "learning_rate": 2.5491806339645287e-06, + "loss": 3.3042, + "step": 2898432 + }, + { + "epoch": 1.02, + "learning_rate": 2.5407946864540087e-06, + "loss": 3.3074, + "step": 2898944 + }, + { + "epoch": 1.02, + "learning_rate": 2.53242511774722e-06, + "loss": 3.287, + "step": 2899456 + }, + { + "epoch": 1.02, + "learning_rate": 2.5240391702367e-06, + "loss": 3.304, + "step": 2899968 + }, + { + "epoch": 1.03, + "eval_loss": 3.8726887702941895, + "eval_runtime": 309.4338, + "eval_samples_per_second": 1233.191, + "eval_steps_per_second": 38.538, + "step": 2900149 + }, + { + "epoch": 0.0, + "learning_rate": 2.51565322272618e-06, + "loss": 3.3103, + "step": 2900480 + }, + { + "epoch": 0.0, + "learning_rate": 2.5072672752156598e-06, + "loss": 3.3068, + "step": 2900992 + }, + { + "epoch": 0.0, + "learning_rate": 2.4988813277051397e-06, + "loss": 3.3079, + "step": 2901504 + }, + { + "epoch": 0.0, + "learning_rate": 2.4904953801946197e-06, + "loss": 3.3095, + "step": 2902016 + }, + { + "epoch": 0.0, + "learning_rate": 2.4821421902915626e-06, + "loss": 3.3207, + "step": 2902528 + }, + { + "epoch": 0.0, + "learning_rate": 2.4737562427810425e-06, + "loss": 3.3031, + "step": 2903040 + }, + { + "epoch": 0.0, + "learning_rate": 2.465370295270522e-06, + "loss": 3.3077, + "step": 2903552 + }, + { + "epoch": 0.0, + "learning_rate": 2.456984347760002e-06, + "loss": 3.2924, + "step": 2904064 + }, + { + "epoch": 0.0, + "learning_rate": 2.448598400249482e-06, + "loss": 3.3058, + "step": 2904576 + }, + { + "epoch": 0.0, + "learning_rate": 2.440228831542693e-06, + "loss": 3.3052, + "step": 2905088 + }, + { + "epoch": 0.0, + "learning_rate": 2.431842884032173e-06, + "loss": 3.3054, + "step": 2905600 + }, + { + "epoch": 0.0, + "learning_rate": 2.423456936521653e-06, + "loss": 3.302, + "step": 2906112 + }, + { + "epoch": 0.0, + "learning_rate": 2.415070989011133e-06, + "loss": 3.2936, + "step": 2906624 + }, + { + "epoch": 0.0, + "learning_rate": 2.406685041500613e-06, + "loss": 3.3002, + "step": 2907136 + }, + { + "epoch": 0.0, + "learning_rate": 2.398299093990093e-06, + "loss": 3.301, + "step": 2907648 + }, + { + "epoch": 0.0, + "learning_rate": 2.389929525283304e-06, + "loss": 3.2917, + "step": 2908160 + }, + { + "epoch": 0.0, + "learning_rate": 2.381543577772784e-06, + "loss": 3.297, + "step": 2908672 + }, + { + "epoch": 0.0, + "learning_rate": 2.373157630262264e-06, + "loss": 3.2987, + "step": 2909184 + }, + { + "epoch": 0.0, + "learning_rate": 2.364771682751744e-06, + "loss": 3.3035, + "step": 2909696 + }, + { + "epoch": 0.0, + "learning_rate": 2.356385735241224e-06, + "loss": 3.3135, + "step": 2910208 + }, + { + "epoch": 0.0, + "learning_rate": 2.3479997877307035e-06, + "loss": 3.3045, + "step": 2910720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3396138402201835e-06, + "loss": 3.312, + "step": 2911232 + }, + { + "epoch": 0.0, + "learning_rate": 2.3312278927096634e-06, + "loss": 3.3005, + "step": 2911744 + }, + { + "epoch": 0.0, + "learning_rate": 2.3228583240028747e-06, + "loss": 3.306, + "step": 2912256 + }, + { + "epoch": 0.0, + "learning_rate": 2.3144723764923546e-06, + "loss": 3.3039, + "step": 2912768 + }, + { + "epoch": 0.0, + "learning_rate": 2.306086428981835e-06, + "loss": 3.3128, + "step": 2913280 + }, + { + "epoch": 0.0, + "learning_rate": 2.297700481471315e-06, + "loss": 3.299, + "step": 2913792 + }, + { + "epoch": 0.0, + "learning_rate": 2.289330912764526e-06, + "loss": 3.3011, + "step": 2914304 + }, + { + "epoch": 0.0, + "learning_rate": 2.280944965254006e-06, + "loss": 3.2947, + "step": 2914816 + }, + { + "epoch": 0.0, + "learning_rate": 2.2725753965472173e-06, + "loss": 3.3025, + "step": 2915328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2641894490366973e-06, + "loss": 3.3044, + "step": 2915840 + }, + { + "epoch": 0.01, + "learning_rate": 2.255803501526177e-06, + "loss": 3.3119, + "step": 2916352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2474175540156568e-06, + "loss": 3.3094, + "step": 2916864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2390316065051367e-06, + "loss": 3.3067, + "step": 2917376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2306456589946167e-06, + "loss": 3.3002, + "step": 2917888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2222597114840966e-06, + "loss": 3.3053, + "step": 2918400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2138737639735766e-06, + "loss": 3.3065, + "step": 2918912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2055041952667882e-06, + "loss": 3.2999, + "step": 2919424 + }, + { + "epoch": 0.01, + "learning_rate": 2.1971182477562678e-06, + "loss": 3.2945, + "step": 2919936 + }, + { + "epoch": 0.01, + "learning_rate": 2.1887323002457477e-06, + "loss": 3.2898, + "step": 2920448 + }, + { + "epoch": 0.01, + "learning_rate": 2.1803463527352277e-06, + "loss": 3.2965, + "step": 2920960 + }, + { + "epoch": 0.01, + "learning_rate": 2.171976784028439e-06, + "loss": 3.3071, + "step": 2921472 + }, + { + "epoch": 0.01, + "learning_rate": 2.163590836517919e-06, + "loss": 3.3027, + "step": 2921984 + }, + { + "epoch": 0.01, + "learning_rate": 2.155204889007399e-06, + "loss": 3.2961, + "step": 2922496 + }, + { + "epoch": 0.01, + "learning_rate": 2.14683532030061e-06, + "loss": 3.301, + "step": 2923008 + }, + { + "epoch": 0.01, + "learning_rate": 2.13844937279009e-06, + "loss": 3.3042, + "step": 2923520 + }, + { + "epoch": 0.01, + "learning_rate": 2.13006342527957e-06, + "loss": 3.2979, + "step": 2924032 + }, + { + "epoch": 0.01, + "learning_rate": 2.12167747776905e-06, + "loss": 3.29, + "step": 2924544 + }, + { + "epoch": 0.01, + "learning_rate": 2.113307909062261e-06, + "loss": 3.2768, + "step": 2925056 + }, + { + "epoch": 0.01, + "learning_rate": 2.104921961551741e-06, + "loss": 3.3184, + "step": 2925568 + }, + { + "epoch": 0.01, + "learning_rate": 2.096536014041221e-06, + "loss": 3.3031, + "step": 2926080 + }, + { + "epoch": 0.01, + "learning_rate": 2.088150066530701e-06, + "loss": 3.3091, + "step": 2926592 + }, + { + "epoch": 0.01, + "learning_rate": 2.079780497823912e-06, + "loss": 3.2974, + "step": 2927104 + }, + { + "epoch": 0.01, + "learning_rate": 2.071394550313392e-06, + "loss": 3.2949, + "step": 2927616 + }, + { + "epoch": 0.01, + "learning_rate": 2.063008602802872e-06, + "loss": 3.2898, + "step": 2928128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0546226552923516e-06, + "loss": 3.2986, + "step": 2928640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0462530865855633e-06, + "loss": 3.3041, + "step": 2929152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0378671390750432e-06, + "loss": 3.2929, + "step": 2929664 + }, + { + "epoch": 0.01, + "learning_rate": 2.029481191564523e-06, + "loss": 3.3168, + "step": 2930176 + }, + { + "epoch": 0.01, + "learning_rate": 2.021095244054003e-06, + "loss": 3.2921, + "step": 2930688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0127256753472143e-06, + "loss": 3.2892, + "step": 2931200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0043397278366943e-06, + "loss": 3.3119, + "step": 2931712 + }, + { + "epoch": 0.01, + "learning_rate": 1.9959537803261743e-06, + "loss": 3.2844, + "step": 2932224 + }, + { + "epoch": 0.01, + "learning_rate": 1.9875678328156542e-06, + "loss": 3.2848, + "step": 2932736 + }, + { + "epoch": 0.01, + "learning_rate": 1.9791982641088654e-06, + "loss": 3.3101, + "step": 2933248 + }, + { + "epoch": 0.01, + "learning_rate": 1.9708123165983454e-06, + "loss": 3.3066, + "step": 2933760 + }, + { + "epoch": 0.01, + "learning_rate": 1.962426369087825e-06, + "loss": 3.2886, + "step": 2934272 + }, + { + "epoch": 0.01, + "learning_rate": 1.954040421577305e-06, + "loss": 3.2973, + "step": 2934784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9456708528705165e-06, + "loss": 3.2828, + "step": 2935296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9372849053599965e-06, + "loss": 3.2954, + "step": 2935808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9288989578494764e-06, + "loss": 3.2999, + "step": 2936320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9205130103389564e-06, + "loss": 3.2896, + "step": 2936832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9121434416321676e-06, + "loss": 3.3055, + "step": 2937344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9037574941216475e-06, + "loss": 3.303, + "step": 2937856 + }, + { + "epoch": 0.01, + "learning_rate": 1.8953715466111275e-06, + "loss": 3.3115, + "step": 2938368 + }, + { + "epoch": 0.01, + "learning_rate": 1.886985599100607e-06, + "loss": 3.2938, + "step": 2938880 + }, + { + "epoch": 0.01, + "learning_rate": 1.8786160303938187e-06, + "loss": 3.2976, + "step": 2939392 + }, + { + "epoch": 0.01, + "learning_rate": 1.8702300828832984e-06, + "loss": 3.3039, + "step": 2939904 + }, + { + "epoch": 0.01, + "learning_rate": 1.8618441353727784e-06, + "loss": 3.2914, + "step": 2940416 + }, + { + "epoch": 0.01, + "learning_rate": 1.8534581878622583e-06, + "loss": 3.305, + "step": 2940928 + }, + { + "epoch": 0.01, + "learning_rate": 1.8450886191554695e-06, + "loss": 3.3018, + "step": 2941440 + }, + { + "epoch": 0.01, + "learning_rate": 1.8367026716449495e-06, + "loss": 3.2948, + "step": 2941952 + }, + { + "epoch": 0.01, + "learning_rate": 1.8283167241344297e-06, + "loss": 3.3038, + "step": 2942464 + }, + { + "epoch": 0.01, + "learning_rate": 1.8199307766239092e-06, + "loss": 3.2858, + "step": 2942976 + }, + { + "epoch": 0.01, + "learning_rate": 1.8115612079171208e-06, + "loss": 3.2882, + "step": 2943488 + }, + { + "epoch": 0.01, + "learning_rate": 1.8031752604066004e-06, + "loss": 3.2968, + "step": 2944000 + }, + { + "epoch": 0.01, + "learning_rate": 1.7947893128960803e-06, + "loss": 3.303, + "step": 2944512 + }, + { + "epoch": 0.01, + "learning_rate": 1.7864033653855605e-06, + "loss": 3.2935, + "step": 2945024 + }, + { + "epoch": 0.01, + "learning_rate": 1.7780337966787717e-06, + "loss": 3.2975, + "step": 2945536 + }, + { + "epoch": 0.02, + "learning_rate": 1.7696478491682517e-06, + "loss": 3.2869, + "step": 2946048 + }, + { + "epoch": 0.02, + "learning_rate": 1.7612619016577316e-06, + "loss": 3.2942, + "step": 2946560 + }, + { + "epoch": 0.02, + "learning_rate": 1.7528759541472116e-06, + "loss": 3.2852, + "step": 2947072 + }, + { + "epoch": 0.02, + "learning_rate": 1.744506385440423e-06, + "loss": 3.2951, + "step": 2947584 + }, + { + "epoch": 0.02, + "learning_rate": 1.736120437929903e-06, + "loss": 3.3118, + "step": 2948096 + }, + { + "epoch": 0.02, + "learning_rate": 1.7277344904193825e-06, + "loss": 3.2998, + "step": 2948608 + }, + { + "epoch": 0.02, + "learning_rate": 1.7193485429088624e-06, + "loss": 3.3014, + "step": 2949120 + }, + { + "epoch": 0.02, + "learning_rate": 1.7109789742020737e-06, + "loss": 3.2931, + "step": 2949632 + }, + { + "epoch": 0.02, + "learning_rate": 1.7025930266915538e-06, + "loss": 3.2953, + "step": 2950144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6942070791810338e-06, + "loss": 3.294, + "step": 2950656 + }, + { + "epoch": 0.02, + "learning_rate": 1.685837510474245e-06, + "loss": 3.3044, + "step": 2951168 + }, + { + "epoch": 0.02, + "learning_rate": 1.677451562963725e-06, + "loss": 3.3002, + "step": 2951680 + }, + { + "epoch": 0.02, + "learning_rate": 1.669065615453205e-06, + "loss": 3.3056, + "step": 2952192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6606796679426849e-06, + "loss": 3.2886, + "step": 2952704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6523100992358963e-06, + "loss": 3.3074, + "step": 2953216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6439241517253762e-06, + "loss": 3.2927, + "step": 2953728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6355382042148558e-06, + "loss": 3.3019, + "step": 2954240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6271522567043357e-06, + "loss": 3.2865, + "step": 2954752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6187826879975472e-06, + "loss": 3.3021, + "step": 2955264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6103967404870271e-06, + "loss": 3.2872, + "step": 2955776 + }, + { + "epoch": 0.02, + "learning_rate": 1.602010792976507e-06, + "loss": 3.2997, + "step": 2956288 + }, + { + "epoch": 0.02, + "learning_rate": 1.593624845465987e-06, + "loss": 3.2854, + "step": 2956800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5852552767591982e-06, + "loss": 3.3013, + "step": 2957312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5768693292486782e-06, + "loss": 3.2933, + "step": 2957824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5684833817381581e-06, + "loss": 3.2936, + "step": 2958336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5600974342276379e-06, + "loss": 3.3061, + "step": 2958848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5517278655208493e-06, + "loss": 3.3101, + "step": 2959360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5433419180103293e-06, + "loss": 3.3036, + "step": 2959872 + }, + { + "epoch": 0.02, + "learning_rate": 1.534955970499809e-06, + "loss": 3.3013, + "step": 2960384 + }, + { + "epoch": 0.02, + "learning_rate": 1.526570022989289e-06, + "loss": 3.2955, + "step": 2960896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5182004542825004e-06, + "loss": 3.2917, + "step": 2961408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5098145067719804e-06, + "loss": 3.2939, + "step": 2961920 + }, + { + "epoch": 0.02, + "learning_rate": 1.50142855926146e-06, + "loss": 3.2996, + "step": 2962432 + }, + { + "epoch": 0.02, + "learning_rate": 1.49304261175094e-06, + "loss": 3.2822, + "step": 2962944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4846730430441513e-06, + "loss": 3.299, + "step": 2963456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4762870955336314e-06, + "loss": 3.2991, + "step": 2963968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4679011480231114e-06, + "loss": 3.3007, + "step": 2964480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4595152005125911e-06, + "loss": 3.2971, + "step": 2964992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4511456318058026e-06, + "loss": 3.2987, + "step": 2965504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4427596842952823e-06, + "loss": 3.2932, + "step": 2966016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4343737367847623e-06, + "loss": 3.3065, + "step": 2966528 + }, + { + "epoch": 0.02, + "learning_rate": 1.4259877892742422e-06, + "loss": 3.3024, + "step": 2967040 + }, + { + "epoch": 0.02, + "learning_rate": 1.4176182205674536e-06, + "loss": 3.3034, + "step": 2967552 + }, + { + "epoch": 0.02, + "learning_rate": 1.4092322730569334e-06, + "loss": 3.2909, + "step": 2968064 + }, + { + "epoch": 0.02, + "learning_rate": 1.4008463255464133e-06, + "loss": 3.3028, + "step": 2968576 + }, + { + "epoch": 0.02, + "learning_rate": 1.392460378035893e-06, + "loss": 3.3, + "step": 2969088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3840908093291047e-06, + "loss": 3.2924, + "step": 2969600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3757048618185845e-06, + "loss": 3.2962, + "step": 2970112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3673189143080644e-06, + "loss": 3.3025, + "step": 2970624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3589329667975444e-06, + "loss": 3.3007, + "step": 2971136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3505633980907556e-06, + "loss": 3.3164, + "step": 2971648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3421774505802355e-06, + "loss": 3.2931, + "step": 2972160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3337915030697155e-06, + "loss": 3.3023, + "step": 2972672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3254055555591955e-06, + "loss": 3.2947, + "step": 2973184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3170359868524067e-06, + "loss": 3.3024, + "step": 2973696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3086500393418866e-06, + "loss": 3.2936, + "step": 2974208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3002640918313664e-06, + "loss": 3.2919, + "step": 2974720 + }, + { + "epoch": 0.02, + "learning_rate": 1.291894523124578e-06, + "loss": 3.3005, + "step": 2975232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2835085756140578e-06, + "loss": 3.2799, + "step": 2975744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2751226281035377e-06, + "loss": 3.2998, + "step": 2976256 + }, + { + "epoch": 0.03, + "eval_loss": 3.8713090419769287, + "eval_runtime": 304.7543, + "eval_samples_per_second": 1252.127, + "eval_steps_per_second": 39.13, + "step": 2976469 + }, + { + "epoch": 1.0, + "learning_rate": 1.2667366805930175e-06, + "loss": 3.2995, + "step": 2976768 + }, + { + "epoch": 1.0, + "learning_rate": 1.2583671118862289e-06, + "loss": 3.2964, + "step": 2977280 + }, + { + "epoch": 1.0, + "learning_rate": 1.2499811643757088e-06, + "loss": 3.3009, + "step": 2977792 + }, + { + "epoch": 1.0, + "learning_rate": 1.2415952168651888e-06, + "loss": 3.3022, + "step": 2978304 + }, + { + "epoch": 1.0, + "learning_rate": 1.2332092693546687e-06, + "loss": 3.3082, + "step": 2978816 + }, + { + "epoch": 1.0, + "learning_rate": 1.22483970064788e-06, + "loss": 3.2981, + "step": 2979328 + }, + { + "epoch": 1.0, + "learning_rate": 1.21645375313736e-06, + "loss": 3.3011, + "step": 2979840 + }, + { + "epoch": 1.0, + "learning_rate": 1.2080678056268399e-06, + "loss": 3.291, + "step": 2980352 + }, + { + "epoch": 1.0, + "learning_rate": 1.1996818581163198e-06, + "loss": 3.295, + "step": 2980864 + }, + { + "epoch": 1.0, + "learning_rate": 1.191312289409531e-06, + "loss": 3.2996, + "step": 2981376 + }, + { + "epoch": 1.0, + "learning_rate": 1.182926341899011e-06, + "loss": 3.2956, + "step": 2981888 + }, + { + "epoch": 1.0, + "learning_rate": 1.1745403943884907e-06, + "loss": 3.292, + "step": 2982400 + }, + { + "epoch": 1.0, + "learning_rate": 1.1661544468779707e-06, + "loss": 3.2956, + "step": 2982912 + }, + { + "epoch": 1.0, + "learning_rate": 1.1577848781711821e-06, + "loss": 3.2863, + "step": 2983424 + }, + { + "epoch": 1.0, + "learning_rate": 1.149398930660662e-06, + "loss": 3.2901, + "step": 2983936 + }, + { + "epoch": 1.0, + "learning_rate": 1.141012983150142e-06, + "loss": 3.2873, + "step": 2984448 + }, + { + "epoch": 1.0, + "learning_rate": 1.1326270356396218e-06, + "loss": 3.2852, + "step": 2984960 + }, + { + "epoch": 1.0, + "learning_rate": 1.1242574669328332e-06, + "loss": 3.2965, + "step": 2985472 + }, + { + "epoch": 1.0, + "learning_rate": 1.1158715194223132e-06, + "loss": 3.2887, + "step": 2985984 + }, + { + "epoch": 1.0, + "learning_rate": 1.1074855719117931e-06, + "loss": 3.3096, + "step": 2986496 + }, + { + "epoch": 1.0, + "learning_rate": 1.0990996244012729e-06, + "loss": 3.3007, + "step": 2987008 + }, + { + "epoch": 1.0, + "learning_rate": 1.0907300556944843e-06, + "loss": 3.3049, + "step": 2987520 + }, + { + "epoch": 1.0, + "learning_rate": 1.082344108183964e-06, + "loss": 3.2915, + "step": 2988032 + }, + { + "epoch": 1.0, + "learning_rate": 1.073958160673444e-06, + "loss": 3.2979, + "step": 2988544 + }, + { + "epoch": 1.0, + "learning_rate": 1.065572213162924e-06, + "loss": 3.2992, + "step": 2989056 + }, + { + "epoch": 1.0, + "learning_rate": 1.0572026444561354e-06, + "loss": 3.3064, + "step": 2989568 + }, + { + "epoch": 1.0, + "learning_rate": 1.0488166969456151e-06, + "loss": 3.2906, + "step": 2990080 + }, + { + "epoch": 1.0, + "learning_rate": 1.040430749435095e-06, + "loss": 3.2959, + "step": 2990592 + }, + { + "epoch": 1.0, + "learning_rate": 1.032044801924575e-06, + "loss": 3.286, + "step": 2991104 + }, + { + "epoch": 1.0, + "learning_rate": 1.023691612021518e-06, + "loss": 3.295, + "step": 2991616 + }, + { + "epoch": 1.01, + "learning_rate": 1.0153056645109977e-06, + "loss": 3.2943, + "step": 2992128 + }, + { + "epoch": 1.01, + "learning_rate": 1.0069197170004776e-06, + "loss": 3.3061, + "step": 2992640 + }, + { + "epoch": 1.01, + "learning_rate": 9.985337694899576e-07, + "loss": 3.2998, + "step": 2993152 + }, + { + "epoch": 1.01, + "learning_rate": 9.901478219794373e-07, + "loss": 3.3041, + "step": 2993664 + }, + { + "epoch": 1.01, + "learning_rate": 9.817618744689175e-07, + "loss": 3.2937, + "step": 2994176 + }, + { + "epoch": 1.01, + "learning_rate": 9.733759269583972e-07, + "loss": 3.2963, + "step": 2994688 + }, + { + "epoch": 1.01, + "learning_rate": 9.649899794478772e-07, + "loss": 3.3006, + "step": 2995200 + }, + { + "epoch": 1.01, + "learning_rate": 9.566204107410884e-07, + "loss": 3.2924, + "step": 2995712 + }, + { + "epoch": 1.01, + "learning_rate": 9.482344632305685e-07, + "loss": 3.2868, + "step": 2996224 + }, + { + "epoch": 1.01, + "learning_rate": 9.398485157200482e-07, + "loss": 3.2817, + "step": 2996736 + }, + { + "epoch": 1.01, + "learning_rate": 9.314625682095282e-07, + "loss": 3.2902, + "step": 2997248 + }, + { + "epoch": 1.01, + "learning_rate": 9.230929995027395e-07, + "loss": 3.2941, + "step": 2997760 + }, + { + "epoch": 1.01, + "learning_rate": 9.147070519922194e-07, + "loss": 3.2957, + "step": 2998272 + }, + { + "epoch": 1.01, + "learning_rate": 9.063211044816994e-07, + "loss": 3.2914, + "step": 2998784 + }, + { + "epoch": 1.01, + "learning_rate": 8.979351569711792e-07, + "loss": 3.2924, + "step": 2999296 + }, + { + "epoch": 1.01, + "learning_rate": 8.895655882643907e-07, + "loss": 3.2974, + "step": 2999808 + }, + { + "epoch": 1.01, + "learning_rate": 8.811796407538705e-07, + "loss": 3.2936, + "step": 3000320 + }, + { + "epoch": 1.01, + "learning_rate": 8.727936932433505e-07, + "loss": 3.2811, + "step": 3000832 + }, + { + "epoch": 1.01, + "learning_rate": 8.644241245365618e-07, + "loss": 3.27, + "step": 3001344 + }, + { + "epoch": 1.01, + "learning_rate": 8.560381770260417e-07, + "loss": 3.3078, + "step": 3001856 + }, + { + "epoch": 1.01, + "learning_rate": 8.476522295155215e-07, + "loss": 3.2962, + "step": 3002368 + }, + { + "epoch": 1.01, + "learning_rate": 8.392662820050014e-07, + "loss": 3.3047, + "step": 3002880 + }, + { + "epoch": 1.01, + "learning_rate": 8.308967132982128e-07, + "loss": 3.2867, + "step": 3003392 + }, + { + "epoch": 1.01, + "learning_rate": 8.225107657876927e-07, + "loss": 3.2892, + "step": 3003904 + }, + { + "epoch": 1.01, + "learning_rate": 8.141248182771727e-07, + "loss": 3.2813, + "step": 3004416 + }, + { + "epoch": 1.01, + "learning_rate": 8.057388707666525e-07, + "loss": 3.2901, + "step": 3004928 + }, + { + "epoch": 1.01, + "learning_rate": 7.97369302059864e-07, + "loss": 3.2993, + "step": 3005440 + }, + { + "epoch": 1.01, + "learning_rate": 7.889833545493438e-07, + "loss": 3.2827, + "step": 3005952 + }, + { + "epoch": 1.01, + "learning_rate": 7.805974070388237e-07, + "loss": 3.3093, + "step": 3006464 + }, + { + "epoch": 1.01, + "learning_rate": 7.722114595283036e-07, + "loss": 3.2926, + "step": 3006976 + }, + { + "epoch": 1.01, + "learning_rate": 7.638418908215149e-07, + "loss": 3.2783, + "step": 3007488 + }, + { + "epoch": 1.01, + "learning_rate": 7.554723221147264e-07, + "loss": 3.3023, + "step": 3008000 + }, + { + "epoch": 1.01, + "learning_rate": 7.470863746042062e-07, + "loss": 3.2784, + "step": 3008512 + }, + { + "epoch": 1.01, + "learning_rate": 7.387004270936862e-07, + "loss": 3.2785, + "step": 3009024 + }, + { + "epoch": 1.01, + "learning_rate": 7.30314479583166e-07, + "loss": 3.3022, + "step": 3009536 + }, + { + "epoch": 1.01, + "learning_rate": 7.21928532072646e-07, + "loss": 3.2982, + "step": 3010048 + }, + { + "epoch": 1.01, + "learning_rate": 7.135425845621258e-07, + "loss": 3.2798, + "step": 3010560 + }, + { + "epoch": 1.01, + "learning_rate": 7.051566370516057e-07, + "loss": 3.288, + "step": 3011072 + }, + { + "epoch": 1.01, + "learning_rate": 6.967706895410856e-07, + "loss": 3.2777, + "step": 3011584 + }, + { + "epoch": 1.01, + "learning_rate": 6.884011208342969e-07, + "loss": 3.2858, + "step": 3012096 + }, + { + "epoch": 1.01, + "learning_rate": 6.800151733237769e-07, + "loss": 3.2913, + "step": 3012608 + }, + { + "epoch": 1.01, + "learning_rate": 6.716292258132569e-07, + "loss": 3.2862, + "step": 3013120 + }, + { + "epoch": 1.01, + "learning_rate": 6.632432783027367e-07, + "loss": 3.2994, + "step": 3013632 + }, + { + "epoch": 1.01, + "learning_rate": 6.54873709595948e-07, + "loss": 3.2927, + "step": 3014144 + }, + { + "epoch": 1.01, + "learning_rate": 6.46487762085428e-07, + "loss": 3.3036, + "step": 3014656 + }, + { + "epoch": 1.01, + "learning_rate": 6.381018145749078e-07, + "loss": 3.2879, + "step": 3015168 + }, + { + "epoch": 1.01, + "learning_rate": 6.297158670643877e-07, + "loss": 3.2934, + "step": 3015680 + }, + { + "epoch": 1.01, + "learning_rate": 6.213462983575991e-07, + "loss": 3.2952, + "step": 3016192 + }, + { + "epoch": 1.01, + "learning_rate": 6.12960350847079e-07, + "loss": 3.2854, + "step": 3016704 + }, + { + "epoch": 1.01, + "learning_rate": 6.045744033365589e-07, + "loss": 3.3001, + "step": 3017216 + }, + { + "epoch": 1.01, + "learning_rate": 5.961884558260388e-07, + "loss": 3.293, + "step": 3017728 + }, + { + "epoch": 1.01, + "learning_rate": 5.878188871192502e-07, + "loss": 3.2874, + "step": 3018240 + }, + { + "epoch": 1.01, + "learning_rate": 5.7943293960873e-07, + "loss": 3.2976, + "step": 3018752 + }, + { + "epoch": 1.01, + "learning_rate": 5.710469920982099e-07, + "loss": 3.2753, + "step": 3019264 + }, + { + "epoch": 1.01, + "learning_rate": 5.626610445876898e-07, + "loss": 3.2808, + "step": 3019776 + }, + { + "epoch": 1.01, + "learning_rate": 5.542914758809012e-07, + "loss": 3.2927, + "step": 3020288 + }, + { + "epoch": 1.01, + "learning_rate": 5.459055283703811e-07, + "loss": 3.2973, + "step": 3020800 + }, + { + "epoch": 1.01, + "learning_rate": 5.375195808598611e-07, + "loss": 3.2875, + "step": 3021312 + }, + { + "epoch": 1.01, + "learning_rate": 5.291336333493409e-07, + "loss": 3.2917, + "step": 3021824 + }, + { + "epoch": 1.02, + "learning_rate": 5.207640646425523e-07, + "loss": 3.2755, + "step": 3022336 + }, + { + "epoch": 1.02, + "learning_rate": 5.123781171320322e-07, + "loss": 3.2822, + "step": 3022848 + }, + { + "epoch": 1.02, + "learning_rate": 5.03992169621512e-07, + "loss": 3.2817, + "step": 3023360 + }, + { + "epoch": 1.02, + "learning_rate": 4.956062221109919e-07, + "loss": 3.2888, + "step": 3023872 + }, + { + "epoch": 1.02, + "learning_rate": 4.872366534042033e-07, + "loss": 3.3029, + "step": 3024384 + }, + { + "epoch": 1.02, + "learning_rate": 4.788507058936832e-07, + "loss": 3.2919, + "step": 3024896 + }, + { + "epoch": 1.02, + "learning_rate": 4.704647583831631e-07, + "loss": 3.2931, + "step": 3025408 + }, + { + "epoch": 1.02, + "learning_rate": 4.620788108726431e-07, + "loss": 3.2866, + "step": 3025920 + }, + { + "epoch": 1.02, + "learning_rate": 4.5370924216585435e-07, + "loss": 3.2909, + "step": 3026432 + }, + { + "epoch": 1.02, + "learning_rate": 4.4532329465533436e-07, + "loss": 3.286, + "step": 3026944 + }, + { + "epoch": 1.02, + "learning_rate": 4.369373471448142e-07, + "loss": 3.2985, + "step": 3027456 + }, + { + "epoch": 1.02, + "learning_rate": 4.285513996342941e-07, + "loss": 3.2933, + "step": 3027968 + }, + { + "epoch": 1.02, + "learning_rate": 4.201818309275055e-07, + "loss": 3.3006, + "step": 3028480 + }, + { + "epoch": 1.02, + "learning_rate": 4.117958834169854e-07, + "loss": 3.2825, + "step": 3028992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0340993590646524e-07, + "loss": 3.2965, + "step": 3029504 + }, + { + "epoch": 1.02, + "learning_rate": 3.9504036719967667e-07, + "loss": 3.2888, + "step": 3030016 + }, + { + "epoch": 1.02, + "learning_rate": 3.866544196891565e-07, + "loss": 3.2911, + "step": 3030528 + }, + { + "epoch": 1.02, + "learning_rate": 3.782684721786364e-07, + "loss": 3.2807, + "step": 3031040 + }, + { + "epoch": 1.02, + "learning_rate": 3.698825246681163e-07, + "loss": 3.2965, + "step": 3031552 + }, + { + "epoch": 1.02, + "learning_rate": 3.615129559613277e-07, + "loss": 3.2813, + "step": 3032064 + }, + { + "epoch": 1.02, + "learning_rate": 3.531270084508076e-07, + "loss": 3.2907, + "step": 3032576 + }, + { + "epoch": 1.02, + "learning_rate": 3.4475743974401897e-07, + "loss": 3.2775, + "step": 3033088 + }, + { + "epoch": 1.02, + "learning_rate": 3.3637149223349887e-07, + "loss": 3.2952, + "step": 3033600 + }, + { + "epoch": 1.02, + "learning_rate": 3.279855447229788e-07, + "loss": 3.2882, + "step": 3034112 + }, + { + "epoch": 1.02, + "learning_rate": 3.195995972124586e-07, + "loss": 3.2841, + "step": 3034624 + }, + { + "epoch": 1.02, + "learning_rate": 3.112136497019386e-07, + "loss": 3.2991, + "step": 3035136 + }, + { + "epoch": 1.02, + "learning_rate": 3.0282770219141843e-07, + "loss": 3.3059, + "step": 3035648 + }, + { + "epoch": 1.02, + "learning_rate": 2.9444175468089833e-07, + "loss": 3.2996, + "step": 3036160 + }, + { + "epoch": 1.02, + "learning_rate": 2.860721859741097e-07, + "loss": 3.2936, + "step": 3036672 + }, + { + "epoch": 1.02, + "learning_rate": 2.776862384635896e-07, + "loss": 3.2886, + "step": 3037184 + }, + { + "epoch": 1.02, + "learning_rate": 2.69316669756801e-07, + "loss": 3.2851, + "step": 3037696 + }, + { + "epoch": 1.02, + "learning_rate": 2.609307222462809e-07, + "loss": 3.2883, + "step": 3038208 + }, + { + "epoch": 1.02, + "learning_rate": 2.525447747357608e-07, + "loss": 3.2904, + "step": 3038720 + }, + { + "epoch": 1.02, + "learning_rate": 2.441588272252407e-07, + "loss": 3.277, + "step": 3039232 + }, + { + "epoch": 1.02, + "learning_rate": 2.3577287971472054e-07, + "loss": 3.2936, + "step": 3039744 + }, + { + "epoch": 1.02, + "learning_rate": 2.2738693220420047e-07, + "loss": 3.2932, + "step": 3040256 + }, + { + "epoch": 1.02, + "learning_rate": 2.1900098469368034e-07, + "loss": 3.291, + "step": 3040768 + }, + { + "epoch": 1.02, + "learning_rate": 2.1061503718316022e-07, + "loss": 3.2912, + "step": 3041280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0224546847637162e-07, + "loss": 3.2895, + "step": 3041792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9385952096585152e-07, + "loss": 3.2875, + "step": 3042304 + }, + { + "epoch": 1.02, + "learning_rate": 1.854735734553314e-07, + "loss": 3.2981, + "step": 3042816 + }, + { + "epoch": 1.02, + "learning_rate": 1.770876259448113e-07, + "loss": 3.2958, + "step": 3043328 + }, + { + "epoch": 1.02, + "learning_rate": 1.6871805723802267e-07, + "loss": 3.297, + "step": 3043840 + }, + { + "epoch": 1.02, + "learning_rate": 1.6033210972750258e-07, + "loss": 3.2795, + "step": 3044352 + }, + { + "epoch": 1.02, + "learning_rate": 1.5194616221698245e-07, + "loss": 3.2993, + "step": 3044864 + }, + { + "epoch": 1.02, + "learning_rate": 1.4356021470646236e-07, + "loss": 3.2901, + "step": 3045376 + }, + { + "epoch": 1.02, + "learning_rate": 1.3519064599967373e-07, + "loss": 3.29, + "step": 3045888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2680469848915363e-07, + "loss": 3.2899, + "step": 3046400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1841875097863353e-07, + "loss": 3.2898, + "step": 3046912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1003280346811341e-07, + "loss": 3.2965, + "step": 3047424 + }, + { + "epoch": 1.02, + "learning_rate": 1.0166323476132481e-07, + "loss": 3.3119, + "step": 3047936 + }, + { + "epoch": 1.02, + "learning_rate": 9.32772872508047e-08, + "loss": 3.288, + "step": 3048448 + }, + { + "epoch": 1.02, + "learning_rate": 8.489133974028459e-08, + "loss": 3.2948, + "step": 3048960 + }, + { + "epoch": 1.02, + "learning_rate": 7.650539222976448e-08, + "loss": 3.2942, + "step": 3049472 + }, + { + "epoch": 1.02, + "learning_rate": 6.813582352297587e-08, + "loss": 3.2933, + "step": 3049984 + }, + { + "epoch": 1.02, + "learning_rate": 5.974987601245575e-08, + "loss": 3.2861, + "step": 3050496 + }, + { + "epoch": 1.02, + "learning_rate": 5.136392850193566e-08, + "loss": 3.2873, + "step": 3051008 + }, + { + "epoch": 1.02, + "learning_rate": 4.299435979514703e-08, + "loss": 3.2936, + "step": 3051520 + }, + { + "epoch": 1.02, + "learning_rate": 3.460841228462692e-08, + "loss": 3.2742, + "step": 3052032 + }, + { + "epoch": 1.02, + "learning_rate": 2.622246477410682e-08, + "loss": 3.293, + "step": 3052544 + }, + { + "epoch": 1.02, + "eval_loss": 3.8701395988464355, + "eval_runtime": 303.7029, + "eval_samples_per_second": 1256.462, + "eval_steps_per_second": 39.265, + "step": 3052726 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 2.0840542840305377e+18, + "trial_name": null, + "trial_params": null +}