diff --git "a/checkpoint-1373750/trainer_state.json" "b/checkpoint-1373750/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1373750/trainer_state.json" @@ -0,0 +1,16267 @@ +{ + "best_metric": 3.890789031982422, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/transformer/1/checkpoints/checkpoint-839510", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1373750, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 11.0824, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8357, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1776, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9577, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8117, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6911, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6043, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5303, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4703, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4005, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.354, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3111, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2777, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2148, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1736, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1441, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1033, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0755, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0564, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0223, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0076, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9809, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9507, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.945, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9172, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8919, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8786, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8688, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8318, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8239, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8015, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7918, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7918, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7701, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7594, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 4.7484, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.738, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7262, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.7095, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.7031, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 4.6845, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6799, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6555, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6641, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6574, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6453, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6271, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6255, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6206, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.6036, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5919, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5862, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5943, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5637, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5854, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.548, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5559, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5481, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5443, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 4.5348, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5278, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5124, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5213, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.5041, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5092, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5016, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4919, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4755, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.488, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4791, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4651, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 4.4686, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4595, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.46, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4631, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4547, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4447, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4288, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4387, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4332, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4354, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4298, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4169, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.3997, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4053, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4058, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4077, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4014, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3956, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3852, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3817, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3799, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3888, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922041807879253e-05, + "loss": 4.378, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921203213128201e-05, + "loss": 4.3555, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3608, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3656, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.368, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3607, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3556, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3521, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3469, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3519, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3502, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912820541378427e-05, + "loss": 4.3302, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911981946627375e-05, + "loss": 4.3418, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3199, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3278, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3257, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3211, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3224, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3097, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3059, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.311, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3248, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.2966, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.2922, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.2948, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.3067, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.2965, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2979, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2916, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.295, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2834, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2836, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.28, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2881, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2679, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.279, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2736, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2632, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2739, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.267, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2717, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2684, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2514, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2485, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2536, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2617, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2626, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2537, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818040007521146e-05, + "loss": 4.2441, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2434, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2469, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2431, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878452897508653e-05, + "loss": 4.2396, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877614302757601e-05, + "loss": 4.2554, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876775708006549e-05, + "loss": 4.2401, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875937113255497e-05, + "loss": 4.2308, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875098518504445e-05, + "loss": 4.2284, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.246391296386719, + "eval_runtime": 573.4963, + "eval_samples_per_second": 665.377, + "eval_steps_per_second": 20.794, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.874259923753393e-05, + "loss": 4.237, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.2313, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2205, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.22, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.2119, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2105, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2065, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.2064, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2131, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2106, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2062, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2099, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.2015, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.196, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1918, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.169, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1883, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.1877, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1868, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.1985, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1812, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1841, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1819, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1796, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.174, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1703, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1778, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1616, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1672, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1552, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1584, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1713, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1624, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1619, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1592, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.159, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1585, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1557, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1541, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.143, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1512, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1342, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1475, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.8382134525011416e-05, + "loss": 4.1511, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1465, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1391, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1404, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834860711377307e-05, + "loss": 4.1448, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.123, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1278, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1266, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.831507970253472e-05, + "loss": 4.1417, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.1182, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.1401, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1116, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.828155229129637e-05, + "loss": 4.1243, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1217, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1271, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1183, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.122, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1095, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1183, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.1112, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214497468819674e-05, + "loss": 4.1159, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1114, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.1088, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.0931, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.818097005758132e-05, + "loss": 4.1164, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.817258411007081e-05, + "loss": 4.1034, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816419816256029e-05, + "loss": 4.0988, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.815581221504977e-05, + "loss": 4.1055, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814744264634298e-05, + "loss": 4.1006, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.813905669883246e-05, + "loss": 4.1031, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813067075132194e-05, + "loss": 4.1119, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812228480381141e-05, + "loss": 4.106, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811391523510463e-05, + "loss": 4.0991, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810552928759411e-05, + "loss": 4.0882, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809714334008359e-05, + "loss": 4.096, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808875739257306e-05, + "loss": 4.0982, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808038782386628e-05, + "loss": 4.106, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.0956, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.8063615928845243e-05, + "loss": 4.091, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.8055229981334717e-05, + "loss": 4.0749, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804686041262793e-05, + "loss": 4.0824, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803847446511741e-05, + "loss": 4.0839, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.8030088517606886e-05, + "loss": 4.0866, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.8021702570096366e-05, + "loss": 4.0924, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0848, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800494705387906e-05, + "loss": 4.077, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.7996561106368535e-05, + "loss": 4.0826, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.0748, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.0845, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797141964264071e-05, + "loss": 4.0818, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.7963050073933926e-05, + "loss": 4.0634, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.7954664126423406e-05, + "loss": 4.0645, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.7946278178912886e-05, + "loss": 4.074, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793789223140236e-05, + "loss": 4.0835, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792950628389184e-05, + "loss": 4.0693, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792112033638132e-05, + "loss": 4.0763, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.79127343888708e-05, + "loss": 4.0691, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790436482016401e-05, + "loss": 4.0655, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789597887265349e-05, + "loss": 4.0743, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788759292514297e-05, + "loss": 4.072, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.7879223356436184e-05, + "loss": 4.0564, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870837408925664e-05, + "loss": 4.071, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.7862451461415144e-05, + "loss": 4.053, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7854065513904624e-05, + "loss": 4.0558, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.0643, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.0531, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.0594, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.0521, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781215215515575e-05, + "loss": 4.048, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780376620764523e-05, + "loss": 4.0531, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779538026013471e-05, + "loss": 4.0684, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778699431262419e-05, + "loss": 4.046, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.77786247439174e-05, + "loss": 4.0471, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777023879640689e-05, + "loss": 4.0454, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.0536, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.0514, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.774509733267906e-05, + "loss": 4.0505, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773671138516854e-05, + "loss": 4.0502, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772832543765802e-05, + "loss": 4.0523, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.77199394901475e-05, + "loss": 4.0454, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771155354263698e-05, + "loss": 4.0409, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0435, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0533, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0365, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.7678026131398626e-05, + "loss": 4.0386, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.7669640183888106e-05, + "loss": 4.0511, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.7661254236377586e-05, + "loss": 4.0298, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.765286828886707e-05, + "loss": 4.0439, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764449872016028e-05, + "loss": 4.0387, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.763611277264976e-05, + "loss": 4.048, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762772682513924e-05, + "loss": 4.042, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761934087762872e-05, + "loss": 4.0284, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761097130892193e-05, + "loss": 4.0277, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760258536141141e-05, + "loss": 4.0317, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759419941390089e-05, + "loss": 4.0422, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.758581346639037e-05, + "loss": 4.0448, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757744389768358e-05, + "loss": 4.0402, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.756905795017306e-05, + "loss": 4.025, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756067200266254e-05, + "loss": 4.0297, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755228605515202e-05, + "loss": 4.0341, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.7543916486445236e-05, + "loss": 4.0318, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.7535546917738445e-05, + "loss": 4.0291, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.7527160970227925e-05, + "loss": 4.0469, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.7518775022717405e-05, + "loss": 4.0252, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.7510389075206885e-05, + "loss": 4.0279, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.7502003127696365e-05, + "loss": 4.022, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.075600624084473, + "eval_runtime": 570.4712, + "eval_samples_per_second": 668.905, + "eval_steps_per_second": 20.904, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493633558989574e-05, + "loss": 4.0351, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485247611479054e-05, + "loss": 4.0279, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476861663968534e-05, + "loss": 4.0191, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468475716458014e-05, + "loss": 4.0191, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460089768947494e-05, + "loss": 4.013, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451703821436974e-05, + "loss": 4.0139, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443317873926453e-05, + "loss": 4.0128, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434931926415933e-05, + "loss": 4.0116, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426545978905413e-05, + "loss": 4.0156, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741817641019862e-05, + "loss": 4.0157, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.74097904626881e-05, + "loss": 4.017, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740140451517758e-05, + "loss": 4.0175, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739303494647079e-05, + "loss": 4.0093, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738464899896027e-05, + "loss": 4.0044, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737626305144975e-05, + "loss": 4.0081, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736787710393923e-05, + "loss": 3.9822, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735949115642871e-05, + "loss": 4.0059, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.73511052089182e-05, + "loss": 4.0025, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734271926140768e-05, + "loss": 4.001, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733433331389716e-05, + "loss": 4.0182, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 4.001, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.0063, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 4.0037, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0003, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 3.9959, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 3.9928, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 4.0014, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726726211261673e-05, + "loss": 3.9882, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725887616510621e-05, + "loss": 3.9925, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725049021759568e-05, + "loss": 3.9803, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724210427008517e-05, + "loss": 3.9895, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 4.0007, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225348753867856e-05, + "loss": 3.9874, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.995, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9894, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720020729014003e-05, + "loss": 3.9924, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191821342629505e-05, + "loss": 3.996, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.991, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175049447608465e-05, + "loss": 3.9885, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716669625770541e-05, + "loss": 3.9779, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715831031019489e-05, + "loss": 3.9883, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714992436268437e-05, + "loss": 3.9725, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714153841517385e-05, + "loss": 3.9911, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 3.9852, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.9888, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9783, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108011003935505e-05, + "loss": 3.9781, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709962505642498e-05, + "loss": 3.9875, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709123910891446e-05, + "loss": 3.9669, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708285316140394e-05, + "loss": 3.9731, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707446721389342e-05, + "loss": 3.9674, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9873, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705771169767611e-05, + "loss": 3.9665, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704932575016559e-05, + "loss": 3.9866, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040939802655074e-05, + "loss": 3.9595, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9693, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9739, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9731, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9702, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.9829, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.953, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698227092768889e-05, + "loss": 3.968, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697388498017837e-05, + "loss": 3.9634, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9721, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9619, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9649, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9495, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.9685, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9613, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9582, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9611, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9592, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.9589, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.9735, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.9676, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9615, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9513, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848144903931765e-05, + "loss": 3.955, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9623, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.9674, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.9572, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681461749269342e-05, + "loss": 3.9596, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.68062315451829e-05, + "loss": 3.9397, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.9513, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.945, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9527, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9602, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676431818643403e-05, + "loss": 3.9528, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9433, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674754629141298e-05, + "loss": 3.9515, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673916034390246e-05, + "loss": 3.9439, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9551, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.9507, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9356, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9373, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9426, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.954, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680507847740024e-05, + "loss": 3.9426, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672121900229504e-05, + "loss": 3.9526, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663735952718984e-05, + "loss": 3.9386, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665535000520846e-05, + "loss": 3.939, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664696405769794e-05, + "loss": 3.9455, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663859448899115e-05, + "loss": 3.9475, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.9332, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9498, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661343664645959e-05, + "loss": 3.9244, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9286, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659668113024229e-05, + "loss": 3.9428, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658829518273176e-05, + "loss": 3.9275, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657990923522124e-05, + "loss": 3.9407, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657152328771072e-05, + "loss": 3.9305, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9237, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655476777149341e-05, + "loss": 3.9303, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654638182398289e-05, + "loss": 3.948, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653799587647237e-05, + "loss": 3.9274, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652960992896185e-05, + "loss": 3.9294, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652122398145134e-05, + "loss": 3.9228, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512854412744546e-05, + "loss": 3.9305, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504468465234026e-05, + "loss": 3.9372, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496082517723506e-05, + "loss": 3.9316, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487696570212986e-05, + "loss": 3.9294, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.931, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.9278, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462538727681426e-05, + "loss": 3.9262, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.9272, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445783211464115e-05, + "loss": 3.9332, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437413642757324e-05, + "loss": 3.9207, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429027695246804e-05, + "loss": 3.9232, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642064174773629e-05, + "loss": 3.9372, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641225580022577e-05, + "loss": 3.9151, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640388623151898e-05, + "loss": 3.9278, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639550028400846e-05, + "loss": 3.9257, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638711433649794e-05, + "loss": 3.9351, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637872838898742e-05, + "loss": 3.9287, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9217, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636197287277011e-05, + "loss": 3.9134, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635358692525959e-05, + "loss": 3.9188, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634520097774907e-05, + "loss": 3.928, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633681503023855e-05, + "loss": 3.934, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632844546153176e-05, + "loss": 3.9302, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320059514021244e-05, + "loss": 3.9167, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311673566510724e-05, + "loss": 3.9169, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303287619000204e-05, + "loss": 3.9291, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294918050293413e-05, + "loss": 3.9187, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286532102782893e-05, + "loss": 3.9215, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278146155272373e-05, + "loss": 3.9342, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626976020776185e-05, + "loss": 3.9167, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.921, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625300469154454e-05, + "loss": 3.9165, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.0014214515686035, + "eval_runtime": 576.5609, + "eval_samples_per_second": 661.84, + "eval_steps_per_second": 20.683, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624461874403402e-05, + "loss": 3.9251, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.62362327965235e-05, + "loss": 3.9205, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622784684901298e-05, + "loss": 3.913, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621946090150246e-05, + "loss": 3.912, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621107495399194e-05, + "loss": 3.9093, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620268900648142e-05, + "loss": 3.9074, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.61943030589709e-05, + "loss": 3.9098, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618591711146038e-05, + "loss": 3.9057, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617754754275359e-05, + "loss": 3.9106, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616917797404681e-05, + "loss": 3.916, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616079202653629e-05, + "loss": 3.9092, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615240607902577e-05, + "loss": 3.9123, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614402013151524e-05, + "loss": 3.9077, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613563418400472e-05, + "loss": 3.9039, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.61272482364942e-05, + "loss": 3.9023, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611886228898368e-05, + "loss": 3.8804, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611047634147316e-05, + "loss": 3.902, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610209039396265e-05, + "loss": 3.9015, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.6093720825255856e-05, + "loss": 3.9003, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085334877745336e-05, + "loss": 3.9146, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.6076948930234816e-05, + "loss": 3.9004, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.6068562982724296e-05, + "loss": 3.9096, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.6060193414017505e-05, + "loss": 3.8996, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.6051807466506985e-05, + "loss": 3.8986, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.6043421518996465e-05, + "loss": 3.8971, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.6035035571485945e-05, + "loss": 3.8989, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.6026666002779154e-05, + "loss": 3.8995, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018280055268634e-05, + "loss": 3.8908, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009894107758114e-05, + "loss": 3.8925, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.60015081602476e-05, + "loss": 3.8818, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599313859154081e-05, + "loss": 3.8911, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598475264403029e-05, + "loss": 3.9008, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597636669651977e-05, + "loss": 3.8937, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596798074900925e-05, + "loss": 3.8958, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.595961118030246e-05, + "loss": 3.8945, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.595122523279194e-05, + "loss": 3.8965, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594283928528142e-05, + "loss": 3.8951, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.59344533377709e-05, + "loss": 3.8995, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592606739026038e-05, + "loss": 3.8915, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591769782155359e-05, + "loss": 3.8837, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590931187404307e-05, + "loss": 3.8944, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.5900925926532554e-05, + "loss": 3.876, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.5892539979022034e-05, + "loss": 3.8995, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.5884154031511514e-05, + "loss": 3.8936, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587578446280472e-05, + "loss": 3.893, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.58673985152942e-05, + "loss": 3.8829, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585901256778368e-05, + "loss": 3.8864, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585062662027316e-05, + "loss": 3.8969, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584224067276264e-05, + "loss": 3.8723, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583387110405585e-05, + "loss": 3.8802, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582548515654533e-05, + "loss": 3.8809, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581709920903481e-05, + "loss": 3.8917, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580871326152429e-05, + "loss": 3.8718, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580032731401377e-05, + "loss": 3.8944, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579195774530699e-05, + "loss": 3.8715, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.578357179779647e-05, + "loss": 3.872, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577518585028595e-05, + "loss": 3.8885, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576679990277543e-05, + "loss": 3.8771, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.5758430334068637e-05, + "loss": 3.8875, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.5750044386558117e-05, + "loss": 3.8938, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.5741658439047596e-05, + "loss": 3.8677, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.5733272491537076e-05, + "loss": 3.875, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572488654402655e-05, + "loss": 3.8793, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.5716516975319765e-05, + "loss": 3.8817, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.5708131027809245e-05, + "loss": 3.8713, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.5699745080298725e-05, + "loss": 3.8764, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.5691359132788205e-05, + "loss": 3.8602, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568298956408142e-05, + "loss": 3.8837, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.56746036165709e-05, + "loss": 3.8715, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.5666217669060374e-05, + "loss": 3.8708, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.5657831721549854e-05, + "loss": 3.8747, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564946215284307e-05, + "loss": 3.8746, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564107620533255e-05, + "loss": 3.8723, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563269025782202e-05, + "loss": 3.8819, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.56243043103115e-05, + "loss": 3.884, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561593474160472e-05, + "loss": 3.8761, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.56075487940942e-05, + "loss": 3.8668, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559916284658368e-05, + "loss": 3.8707, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559077689907316e-05, + "loss": 3.8729, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.5582407330366375e-05, + "loss": 3.8844, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557402138285585e-05, + "loss": 3.8736, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556563543534533e-05, + "loss": 3.8698, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.555724948783481e-05, + "loss": 3.8599, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548879919128024e-05, + "loss": 3.8667, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.55404939716175e-05, + "loss": 3.8628, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553210802410698e-05, + "loss": 3.8676, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552372207659646e-05, + "loss": 3.8696, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551533612908594e-05, + "loss": 3.8709, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550696656037915e-05, + "loss": 3.8631, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549858061286863e-05, + "loss": 3.8718, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549019466535811e-05, + "loss": 3.8617, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548180871784759e-05, + "loss": 3.8682, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.54734391491408e-05, + "loss": 3.8666, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546505320163028e-05, + "loss": 3.8546, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545666725411976e-05, + "loss": 3.8534, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544828130660924e-05, + "loss": 3.8658, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543991173790245e-05, + "loss": 3.8655, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543152579039193e-05, + "loss": 3.8694, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542313984288141e-05, + "loss": 3.8683, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541475389537089e-05, + "loss": 3.8581, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.5406384326664106e-05, + "loss": 3.8565, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.5397998379153586e-05, + "loss": 3.8659, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389612431643066e-05, + "loss": 3.8646, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.5381226484132546e-05, + "loss": 3.8536, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.5372856915425755e-05, + "loss": 3.8709, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.5364470967915235e-05, + "loss": 3.8439, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.5356085020404715e-05, + "loss": 3.8508, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347699072894195e-05, + "loss": 3.8654, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.5339313125383675e-05, + "loss": 3.8494, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.5330943556676884e-05, + "loss": 3.8604, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.5322557609166364e-05, + "loss": 3.8488, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.5314171661655844e-05, + "loss": 3.8442, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.5305785714145324e-05, + "loss": 3.853, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529741614543854e-05, + "loss": 3.871, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528903019792802e-05, + "loss": 3.8536, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.52806442504175e-05, + "loss": 3.8504, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527225830290698e-05, + "loss": 3.8467, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526388873420019e-05, + "loss": 3.8522, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.525550278668967e-05, + "loss": 3.8584, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.524711683917915e-05, + "loss": 3.8564, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.523873089166863e-05, + "loss": 3.8484, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523036132296184e-05, + "loss": 3.8575, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522197537545132e-05, + "loss": 3.8508, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.52135894279408e-05, + "loss": 3.8502, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520520348043028e-05, + "loss": 3.8495, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519681753291976e-05, + "loss": 3.8577, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.5188447964212974e-05, + "loss": 3.8467, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.5180062016702454e-05, + "loss": 3.8469, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.5171676069191934e-05, + "loss": 3.8592, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.5163290121681414e-05, + "loss": 3.8393, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515492055297462e-05, + "loss": 3.852, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.51465346054641e-05, + "loss": 3.8547, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513814865795358e-05, + "loss": 3.8581, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.512976271044306e-05, + "loss": 3.8516, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512139314173627e-05, + "loss": 3.8495, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511300719422575e-05, + "loss": 3.8392, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510462124671523e-05, + "loss": 3.8452, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509623529920471e-05, + "loss": 3.8533, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508786573049793e-05, + "loss": 3.8593, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507947978298741e-05, + "loss": 3.8562, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507109383547689e-05, + "loss": 3.8456, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506270788796637e-05, + "loss": 3.8417, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.5054338319259576e-05, + "loss": 3.854, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.5045952371749056e-05, + "loss": 3.8451, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.5037582803042265e-05, + "loss": 3.8483, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.5029196855531745e-05, + "loss": 3.8611, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.5020810908021225e-05, + "loss": 3.847, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.5012424960510705e-05, + "loss": 3.8461, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.5004039013000185e-05, + "loss": 3.845, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.961009979248047, + "eval_runtime": 576.4742, + "eval_samples_per_second": 661.939, + "eval_steps_per_second": 20.686, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.49956694442934e-05, + "loss": 3.8559, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498728349678288e-05, + "loss": 3.8471, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497889754927236e-05, + "loss": 3.8407, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497051160176184e-05, + "loss": 3.8385, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496212565425132e-05, + "loss": 3.8413, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.49537397067408e-05, + "loss": 3.8362, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945353759230274e-05, + "loss": 3.8388, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936967811719754e-05, + "loss": 3.8316, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492859824301297e-05, + "loss": 3.8416, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492022867430618e-05, + "loss": 3.8484, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491184272679566e-05, + "loss": 3.8351, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490345677928514e-05, + "loss": 3.8367, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489507083177462e-05, + "loss": 3.8389, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.48866848842641e-05, + "loss": 3.8363, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487829893675358e-05, + "loss": 3.8345, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486991298924306e-05, + "loss": 3.811, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486152704173254e-05, + "loss": 3.8291, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485315747302575e-05, + "loss": 3.8317, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484477152551523e-05, + "loss": 3.829, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483638557800471e-05, + "loss": 3.8511, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482799963049419e-05, + "loss": 3.8278, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481961368298367e-05, + "loss": 3.841, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481124411427688e-05, + "loss": 3.8286, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480285816676636e-05, + "loss": 3.8352, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794472219255837e-05, + "loss": 3.8242, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478610265054905e-05, + "loss": 3.8299, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477771670303853e-05, + "loss": 3.8313, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476933075552801e-05, + "loss": 3.825, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476094480801749e-05, + "loss": 3.8242, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.47525752393107e-05, + "loss": 3.8164, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474418929180018e-05, + "loss": 3.8199, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473580334428966e-05, + "loss": 3.8317, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472741739677914e-05, + "loss": 3.8277, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471903144926862e-05, + "loss": 3.8309, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471066188056183e-05, + "loss": 3.8267, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470227593305131e-05, + "loss": 3.8313, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469388998554079e-05, + "loss": 3.8275, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468550403803028e-05, + "loss": 3.8315, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677134469323486e-05, + "loss": 3.8265, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668748521812966e-05, + "loss": 3.8165, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660362574302446e-05, + "loss": 3.8322, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651993005595655e-05, + "loss": 3.8088, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643607058085135e-05, + "loss": 3.83, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635221110574615e-05, + "loss": 3.8255, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626835163064095e-05, + "loss": 3.8335, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618449215553575e-05, + "loss": 3.8178, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610079646846784e-05, + "loss": 3.8172, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601693699336264e-05, + "loss": 3.8322, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593307751825744e-05, + "loss": 3.8099, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584921804315224e-05, + "loss": 3.8119, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457655223560844e-05, + "loss": 3.8197, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456816628809792e-05, + "loss": 3.8215, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.45597803405874e-05, + "loss": 3.8117, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455139439307688e-05, + "loss": 3.8257, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454302482437009e-05, + "loss": 3.8098, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453463887685957e-05, + "loss": 3.8088, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452625292934905e-05, + "loss": 3.8234, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451786698183853e-05, + "loss": 3.8091, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450949741313174e-05, + "loss": 3.8285, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450111146562122e-05, + "loss": 3.831, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44927255181107e-05, + "loss": 3.8025, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448433957060018e-05, + "loss": 3.809, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475970001893393e-05, + "loss": 3.8163, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446758405438287e-05, + "loss": 3.823, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445919810687235e-05, + "loss": 3.8083, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445081215936183e-05, + "loss": 3.8099, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444244259065504e-05, + "loss": 3.8008, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443405664314452e-05, + "loss": 3.8173, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425670695634e-05, + "loss": 3.8095, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441728474812348e-05, + "loss": 3.8076, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440891517941669e-05, + "loss": 3.8122, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440052923190617e-05, + "loss": 3.809, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439214328439565e-05, + "loss": 3.8091, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438375733688513e-05, + "loss": 3.822, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437538776817835e-05, + "loss": 3.8187, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436700182066783e-05, + "loss": 3.8142, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435861587315731e-05, + "loss": 3.8088, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435022992564679e-05, + "loss": 3.8125, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341860356939996e-05, + "loss": 3.8066, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333474409429476e-05, + "loss": 3.8273, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325088461918956e-05, + "loss": 3.8098, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316702514408436e-05, + "loss": 3.8092, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308332945701645e-05, + "loss": 3.7966, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299946998191125e-05, + "loss": 3.8098, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291561050680605e-05, + "loss": 3.7992, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428319148197382e-05, + "loss": 3.8131, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.42748055344633e-05, + "loss": 3.8066, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426641958695278e-05, + "loss": 3.8106, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425803363944226e-05, + "loss": 3.8034, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424966407073547e-05, + "loss": 3.8135, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424127812322495e-05, + "loss": 3.7996, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423289217571443e-05, + "loss": 3.808, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422450622820391e-05, + "loss": 3.8097, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421613665949712e-05, + "loss": 3.7923, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.42077507119866e-05, + "loss": 3.7952, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419936476447608e-05, + "loss": 3.8087, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419097881696556e-05, + "loss": 3.8021, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182609248258774e-05, + "loss": 3.8177, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174223300748254e-05, + "loss": 3.8067, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165837353237734e-05, + "loss": 3.7949, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157451405727214e-05, + "loss": 3.7991, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4149081837020423e-05, + "loss": 3.8073, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.41406958895099e-05, + "loss": 3.806, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413230994199938e-05, + "loss": 3.7963, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412392399448886e-05, + "loss": 3.8102, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411555442578207e-05, + "loss": 3.787, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410716847827155e-05, + "loss": 3.7949, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409878253076103e-05, + "loss": 3.8069, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409039658325051e-05, + "loss": 3.7853, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408202701454373e-05, + "loss": 3.8046, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407364106703321e-05, + "loss": 3.7994, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406525511952269e-05, + "loss": 3.7811, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405686917201217e-05, + "loss": 3.7953, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404848322450165e-05, + "loss": 3.8115, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404009727699113e-05, + "loss": 3.7939, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.40317113294806e-05, + "loss": 3.7956, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402332538197008e-05, + "loss": 3.7918, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149558132633e-05, + "loss": 3.7926, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400656986575277e-05, + "loss": 3.8036, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399818391824225e-05, + "loss": 3.7982, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398979797073173e-05, + "loss": 3.7922, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981428402024946e-05, + "loss": 3.7962, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3973042454514426e-05, + "loss": 3.7958, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964656507003906e-05, + "loss": 3.794, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956270559493386e-05, + "loss": 3.7952, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.39479009907866e-05, + "loss": 3.7991, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939515043276075e-05, + "loss": 3.7866, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931129095765555e-05, + "loss": 3.7956, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922743148255035e-05, + "loss": 3.8, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914373579548244e-05, + "loss": 3.7868, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905987632037724e-05, + "loss": 3.7929, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897601684527204e-05, + "loss": 3.7994, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889215737016684e-05, + "loss": 3.7981, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.38808461683099e-05, + "loss": 3.7991, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387246022079938e-05, + "loss": 3.7944, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386407427328886e-05, + "loss": 3.7834, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855704704582075e-05, + "loss": 3.7894, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384731875707155e-05, + "loss": 3.7963, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383893280956103e-05, + "loss": 3.8034, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383054686205051e-05, + "loss": 3.8015, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382217729334372e-05, + "loss": 3.7932, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.38137913458332e-05, + "loss": 3.7854, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380540539832268e-05, + "loss": 3.7992, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379701945081216e-05, + "loss": 3.7861, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378864988210537e-05, + "loss": 3.7929, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378026393459485e-05, + "loss": 3.808, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377187798708433e-05, + "loss": 3.7941, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376349203957381e-05, + "loss": 3.7867, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375510609206329e-05, + "loss": 3.7923, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.935844898223877, + "eval_runtime": 589.1896, + "eval_samples_per_second": 647.654, + "eval_steps_per_second": 20.24, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.37467365233565e-05, + "loss": 3.803, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373835057584598e-05, + "loss": 3.7966, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372996462833546e-05, + "loss": 3.7844, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372157868082494e-05, + "loss": 3.7837, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371319273331442e-05, + "loss": 3.7891, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.37048067858039e-05, + "loss": 3.7846, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369642083829338e-05, + "loss": 3.7853, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368803489078286e-05, + "loss": 3.7736, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367966532207607e-05, + "loss": 3.7894, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367129575336929e-05, + "loss": 3.7992, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366290980585877e-05, + "loss": 3.7785, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365452385834825e-05, + "loss": 3.7829, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364613791083773e-05, + "loss": 3.7873, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363775196332721e-05, + "loss": 3.7808, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.3629366015816687e-05, + "loss": 3.7842, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.3620980068306167e-05, + "loss": 3.7593, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.3612594120795647e-05, + "loss": 3.774, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.3604224552088856e-05, + "loss": 3.7793, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.3595838604578336e-05, + "loss": 3.7772, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.3587452657067816e-05, + "loss": 3.7992, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.3579066709557295e-05, + "loss": 3.7754, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357069714085051e-05, + "loss": 3.7895, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356231119333999e-05, + "loss": 3.7783, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355392524582947e-05, + "loss": 3.7815, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354553929831895e-05, + "loss": 3.7697, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353716972961216e-05, + "loss": 3.7769, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352878378210164e-05, + "loss": 3.78, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.352039783459112e-05, + "loss": 3.7759, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.35120118870806e-05, + "loss": 3.7715, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350364231837381e-05, + "loss": 3.7681, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349525637086329e-05, + "loss": 3.7637, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348687042335277e-05, + "loss": 3.7835, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347848447584225e-05, + "loss": 3.7802, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.3470114907135465e-05, + "loss": 3.7771, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.3461728959624945e-05, + "loss": 3.7762, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.3453343012114425e-05, + "loss": 3.7791, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.3444957064603905e-05, + "loss": 3.7813, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436587495897114e-05, + "loss": 3.7762, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3428201548386594e-05, + "loss": 3.7766, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.3419815600876074e-05, + "loss": 3.7659, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411429653365554e-05, + "loss": 3.7804, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.340306008465876e-05, + "loss": 3.7615, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339467413714824e-05, + "loss": 3.7812, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338628818963772e-05, + "loss": 3.7727, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.33779022421272e-05, + "loss": 3.7814, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336953267342042e-05, + "loss": 3.7693, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.33611467259099e-05, + "loss": 3.767, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335276077839938e-05, + "loss": 3.7837, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334437483088885e-05, + "loss": 3.7574, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333600526218207e-05, + "loss": 3.7664, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332761931467155e-05, + "loss": 3.7689, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331923336716103e-05, + "loss": 3.7694, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.33108474196505e-05, + "loss": 3.7639, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.3302477850943717e-05, + "loss": 3.773, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3294091903433197e-05, + "loss": 3.7627, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285705955922677e-05, + "loss": 3.7595, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3277320008412156e-05, + "loss": 3.7735, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326895043970537e-05, + "loss": 3.763, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326056449219485e-05, + "loss": 3.777, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.3252178544684325e-05, + "loss": 3.7804, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324380897597754e-05, + "loss": 3.7569, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323542302846702e-05, + "loss": 3.7582, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.32270370809565e-05, + "loss": 3.7639, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.3218651133445974e-05, + "loss": 3.7788, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321028156473919e-05, + "loss": 3.7607, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320189561722867e-05, + "loss": 3.7631, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319350966971815e-05, + "loss": 3.7511, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185123722207623e-05, + "loss": 3.77, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317675415350084e-05, + "loss": 3.7597, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.3168368205990326e-05, + "loss": 3.7605, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.31599822584798e-05, + "loss": 3.7631, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315159631096928e-05, + "loss": 3.7643, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3143226742262495e-05, + "loss": 3.7614, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.3134840794751975e-05, + "loss": 3.772, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312645484724145e-05, + "loss": 3.7733, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311806889973093e-05, + "loss": 3.7665, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109699331024144e-05, + "loss": 3.7598, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310131338351362e-05, + "loss": 3.7678, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.30929274360031e-05, + "loss": 3.7579, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308454148849258e-05, + "loss": 3.7759, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307617191978579e-05, + "loss": 3.76, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306778597227527e-05, + "loss": 3.7649, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305940002476475e-05, + "loss": 3.749, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305101407725423e-05, + "loss": 3.7631, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304264450854745e-05, + "loss": 3.7488, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303425856103692e-05, + "loss": 3.7642, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.30258726135264e-05, + "loss": 3.7599, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.301748666601588e-05, + "loss": 3.7608, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300911709730909e-05, + "loss": 3.7605, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300073114979857e-05, + "loss": 3.7708, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299234520228805e-05, + "loss": 3.7466, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298395925477753e-05, + "loss": 3.7601, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297558968607075e-05, + "loss": 3.7637, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.2967203738560227e-05, + "loss": 3.747, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.2958817791049707e-05, + "loss": 3.7496, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.2950431843539186e-05, + "loss": 3.7632, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.2942062274832396e-05, + "loss": 3.7539, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293369270612561e-05, + "loss": 3.7758, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292530675861509e-05, + "loss": 3.7577, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.2916920811104565e-05, + "loss": 3.7487, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.2908534863594045e-05, + "loss": 3.7513, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.2900148916083525e-05, + "loss": 3.7618, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.2891762968573004e-05, + "loss": 3.7608, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.2883377021062484e-05, + "loss": 3.75, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287499107355197e-05, + "loss": 3.7622, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286662150484518e-05, + "loss": 3.7418, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285823555733466e-05, + "loss": 3.7485, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284984960982414e-05, + "loss": 3.7588, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284146366231362e-05, + "loss": 3.7436, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283309409360683e-05, + "loss": 3.7572, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282470814609631e-05, + "loss": 3.7578, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281632219858579e-05, + "loss": 3.7319, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280793625107527e-05, + "loss": 3.7522, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279956668236848e-05, + "loss": 3.7644, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279118073485796e-05, + "loss": 3.7541, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278279478734744e-05, + "loss": 3.7454, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277440883983692e-05, + "loss": 3.7448, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2766039271130134e-05, + "loss": 3.7486, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.2757653323619614e-05, + "loss": 3.7578, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.2749267376109094e-05, + "loss": 3.7556, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.2740881428598574e-05, + "loss": 3.7459, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273251185989178e-05, + "loss": 3.7508, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272412591238126e-05, + "loss": 3.7485, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.271575634367447e-05, + "loss": 3.7532, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270737039616395e-05, + "loss": 3.7466, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269898444865343e-05, + "loss": 3.7527, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.269059850114291e-05, + "loss": 3.745, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268221255363239e-05, + "loss": 3.7546, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267382660612187e-05, + "loss": 3.7532, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266544065861136e-05, + "loss": 3.7406, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265705471110084e-05, + "loss": 3.7493, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264868514239405e-05, + "loss": 3.7568, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264029919488353e-05, + "loss": 3.7546, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263191324737301e-05, + "loss": 3.754, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262352729986249e-05, + "loss": 3.751, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.2615157731155696e-05, + "loss": 3.7383, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.2606771783645176e-05, + "loss": 3.7432, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.2598385836134656e-05, + "loss": 3.7492, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.2589999888624136e-05, + "loss": 3.7647, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.2581630319917345e-05, + "loss": 3.7561, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.2573244372406825e-05, + "loss": 3.7463, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256485842489631e-05, + "loss": 3.746, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255648885618952e-05, + "loss": 3.751, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.2548102908679e-05, + "loss": 3.7458, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253971696116848e-05, + "loss": 3.7479, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253133101365796e-05, + "loss": 3.7648, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252294506614744e-05, + "loss": 3.7498, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251455911863692e-05, + "loss": 3.7411, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.25061731711264e-05, + "loss": 3.7472, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.919569969177246, + "eval_runtime": 596.2815, + "eval_samples_per_second": 639.951, + "eval_steps_per_second": 19.999, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249780360241961e-05, + "loss": 3.7592, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248941765490909e-05, + "loss": 3.7504, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248103170739857e-05, + "loss": 3.7445, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247264575988805e-05, + "loss": 3.7429, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246425981237753e-05, + "loss": 3.7435, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245587386486701e-05, + "loss": 3.7387, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244748791735649e-05, + "loss": 3.7434, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243910196984597e-05, + "loss": 3.7309, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243073240113918e-05, + "loss": 3.7451, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422362832432395e-05, + "loss": 3.7573, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413976884921875e-05, + "loss": 3.7384, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240559093741135e-05, + "loss": 3.7386, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239720498990083e-05, + "loss": 3.7462, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238881904239031e-05, + "loss": 3.738, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238043309487979e-05, + "loss": 3.7448, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237204714736927e-05, + "loss": 3.7175, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236366119985875e-05, + "loss": 3.7286, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355291631151963e-05, + "loss": 3.7378, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346905683641443e-05, + "loss": 3.7325, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233851973613092e-05, + "loss": 3.7582, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.23301337886204e-05, + "loss": 3.7342, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232176421991361e-05, + "loss": 3.7497, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231339465120682e-05, + "loss": 3.7324, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.23050087036963e-05, + "loss": 3.7392, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229662275618578e-05, + "loss": 3.7278, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228823680867526e-05, + "loss": 3.7369, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227986723996847e-05, + "loss": 3.7386, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227148129245796e-05, + "loss": 3.7312, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226309534494744e-05, + "loss": 3.7348, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225470939743692e-05, + "loss": 3.7239, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.22463234499264e-05, + "loss": 3.72, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223793750241588e-05, + "loss": 3.741, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222955155490536e-05, + "loss": 3.7382, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222116560739484e-05, + "loss": 3.7389, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212796038688046e-05, + "loss": 3.7301, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204410091177526e-05, + "loss": 3.7425, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2196040522470735e-05, + "loss": 3.7362, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187654574960215e-05, + "loss": 3.7387, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179268627449695e-05, + "loss": 3.733, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170882679939175e-05, + "loss": 3.728, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162496732428655e-05, + "loss": 3.74, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215412716372187e-05, + "loss": 3.7177, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214574121621135e-05, + "loss": 3.7414, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213735526870083e-05, + "loss": 3.7328, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212896932119031e-05, + "loss": 3.7398, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212058337367979e-05, + "loss": 3.7301, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211219742616927e-05, + "loss": 3.7261, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210382785746248e-05, + "loss": 3.7429, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209544190995196e-05, + "loss": 3.7197, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208705596244144e-05, + "loss": 3.7224, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207867001493092e-05, + "loss": 3.7283, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.20702840674204e-05, + "loss": 3.7287, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206189811990988e-05, + "loss": 3.7262, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205351217239936e-05, + "loss": 3.7274, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204512622488884e-05, + "loss": 3.7219, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036756656182055e-05, + "loss": 3.7252, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028370708671535e-05, + "loss": 3.7307, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201998476116101e-05, + "loss": 3.7256, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201159881365049e-05, + "loss": 3.7361, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003229244943704e-05, + "loss": 3.7398, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994843297433184e-05, + "loss": 3.7188, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198645734992266e-05, + "loss": 3.7179, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197807140241214e-05, + "loss": 3.7212, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196970183370535e-05, + "loss": 3.7414, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196131588619483e-05, + "loss": 3.7236, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195292993868431e-05, + "loss": 3.7212, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194454399117379e-05, + "loss": 3.7132, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193617442246701e-05, + "loss": 3.726, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192778847495648e-05, + "loss": 3.7222, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191940252744596e-05, + "loss": 3.7217, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191101657993544e-05, + "loss": 3.7238, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190264701122866e-05, + "loss": 3.7239, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189426106371813e-05, + "loss": 3.7244, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188587511620761e-05, + "loss": 3.7297, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187748916869709e-05, + "loss": 3.7343, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1869135978794036e-05, + "loss": 3.7274, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860750031283516e-05, + "loss": 3.723, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1852364083772996e-05, + "loss": 3.7253, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184397813626248e-05, + "loss": 3.72, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835592188751956e-05, + "loss": 3.7381, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827206241241436e-05, + "loss": 3.7241, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818820293730916e-05, + "loss": 3.7266, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1810434346220396e-05, + "loss": 3.7098, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1802064777513605e-05, + "loss": 3.7254, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793678830003085e-05, + "loss": 3.7084, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1785292882492565e-05, + "loss": 3.7266, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776906934982045e-05, + "loss": 3.7215, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768520987471525e-05, + "loss": 3.724, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760135039961005e-05, + "loss": 3.7205, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751749092450484e-05, + "loss": 3.7301, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743363144939964e-05, + "loss": 3.711, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173499357623318e-05, + "loss": 3.7223, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172660762872266e-05, + "loss": 3.725, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171823806001587e-05, + "loss": 3.7086, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170985211250535e-05, + "loss": 3.7114, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170146616499483e-05, + "loss": 3.7209, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169308021748431e-05, + "loss": 3.7143, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168469426997379e-05, + "loss": 3.7396, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676324701267e-05, + "loss": 3.7186, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166793875375648e-05, + "loss": 3.7131, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165955280624596e-05, + "loss": 3.7149, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165116685873544e-05, + "loss": 3.7221, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164278091122492e-05, + "loss": 3.7253, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634394963714405e-05, + "loss": 3.7131, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1626009016203885e-05, + "loss": 3.7224, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617639447497094e-05, + "loss": 3.7066, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609253499986574e-05, + "loss": 3.7077, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600867552476054e-05, + "loss": 3.7176, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592481604965534e-05, + "loss": 3.7092, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158411203625874e-05, + "loss": 3.7167, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157572608874822e-05, + "loss": 3.7206, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15673401412377e-05, + "loss": 3.6945, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155895419372718e-05, + "loss": 3.7128, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155058462502039e-05, + "loss": 3.7302, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154219867750987e-05, + "loss": 3.719, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153381272999936e-05, + "loss": 3.7034, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152542678248884e-05, + "loss": 3.7076, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151704083497832e-05, + "loss": 3.7113, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150867126627153e-05, + "loss": 3.7193, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150028531876101e-05, + "loss": 3.7193, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149189937125049e-05, + "loss": 3.7083, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148351342373997e-05, + "loss": 3.7127, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147512747622944e-05, + "loss": 3.7146, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466757907522656e-05, + "loss": 3.713, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458371960012136e-05, + "loss": 3.7101, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144998601250161e-05, + "loss": 3.7162, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441600064991096e-05, + "loss": 3.7106, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433214117480576e-05, + "loss": 3.7169, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424828169970056e-05, + "loss": 3.7157, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416442222459536e-05, + "loss": 3.7015, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1408056274949016e-05, + "loss": 3.7124, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139970308504596e-05, + "loss": 3.7166, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139131713753544e-05, + "loss": 3.7195, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382931190024914e-05, + "loss": 3.7145, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374545242514394e-05, + "loss": 3.7157, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366159295003874e-05, + "loss": 3.7028, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357773347493354e-05, + "loss": 3.7037, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349387399982834e-05, + "loss": 3.7136, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134101783127604e-05, + "loss": 3.7276, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133263188376553e-05, + "loss": 3.7208, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132424593625501e-05, + "loss": 3.7111, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131585998874449e-05, + "loss": 3.7063, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.13074904200377e-05, + "loss": 3.7149, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129910447252718e-05, + "loss": 3.7096, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129071852501666e-05, + "loss": 3.71, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128233257750614e-05, + "loss": 3.729, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127394662999562e-05, + "loss": 3.7164, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.12655606824851e-05, + "loss": 3.7045, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125717473497458e-05, + "loss": 3.7144, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.910735845565796, + "eval_runtime": 583.8202, + "eval_samples_per_second": 653.61, + "eval_steps_per_second": 20.426, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.124880516626779e-05, + "loss": 3.7207, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.124041921875727e-05, + "loss": 3.7168, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123203327124675e-05, + "loss": 3.7113, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122364732373623e-05, + "loss": 3.7066, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215277755029444e-05, + "loss": 3.7043, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206891807518923e-05, + "loss": 3.709, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1198505860008403e-05, + "loss": 3.7055, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119011991249788e-05, + "loss": 3.6968, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118173396498736e-05, + "loss": 3.7073, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117336439628057e-05, + "loss": 3.7196, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116497844877005e-05, + "loss": 3.7035, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115659250125953e-05, + "loss": 3.7011, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114820655374901e-05, + "loss": 3.7167, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113982060623849e-05, + "loss": 3.6986, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113143465872797e-05, + "loss": 3.7129, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112306509002118e-05, + "loss": 3.6837, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111467914251067e-05, + "loss": 3.6876, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110629319500015e-05, + "loss": 3.7057, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109790724748963e-05, + "loss": 3.6957, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.10895212999791e-05, + "loss": 3.7232, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108113535246858e-05, + "loss": 3.7004, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107274940495806e-05, + "loss": 3.7096, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106437983625127e-05, + "loss": 3.6985, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105599388874075e-05, + "loss": 3.7072, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104760794123023e-05, + "loss": 3.6912, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103922199371971e-05, + "loss": 3.7021, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103085242501292e-05, + "loss": 3.7051, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1022466477502406e-05, + "loss": 3.7013, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1014080529991886e-05, + "loss": 3.695, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005694582481366e-05, + "loss": 3.693, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997308634970846e-05, + "loss": 3.6841, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0988922687460326e-05, + "loss": 3.7059, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.0980536739949806e-05, + "loss": 3.7026, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0972150792439286e-05, + "loss": 3.7023, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963781223732495e-05, + "loss": 3.6995, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0955395276221975e-05, + "loss": 3.7081, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.0947025707515184e-05, + "loss": 3.701, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.0938639760004664e-05, + "loss": 3.6995, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930253812494144e-05, + "loss": 3.6972, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921867864983624e-05, + "loss": 3.6996, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0913481917473104e-05, + "loss": 3.6986, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090511234876632e-05, + "loss": 3.6872, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.08967264012558e-05, + "loss": 3.7083, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088834045374528e-05, + "loss": 3.6967, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087995450623476e-05, + "loss": 3.7061, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087158493752797e-05, + "loss": 3.6977, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086319899001745e-05, + "loss": 3.6866, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085481304250693e-05, + "loss": 3.7089, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084642709499641e-05, + "loss": 3.6874, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083805752628962e-05, + "loss": 3.6915, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.08296715787791e-05, + "loss": 3.6874, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082128563126858e-05, + "loss": 3.6976, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081289968375806e-05, + "loss": 3.6926, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080451373624754e-05, + "loss": 3.6929, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.0796127788737024e-05, + "loss": 3.69, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.0787741841226504e-05, + "loss": 3.6897, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.0779355893715984e-05, + "loss": 3.6953, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077100270381292e-05, + "loss": 3.6943, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.07626167563024e-05, + "loss": 3.7034, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075423080879188e-05, + "loss": 3.7025, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074584486128136e-05, + "loss": 3.6876, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073745891377084e-05, + "loss": 3.6818, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072907296626032e-05, + "loss": 3.6913, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.07206870187498e-05, + "loss": 3.7043, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071230107123928e-05, + "loss": 3.691, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070393150253249e-05, + "loss": 3.6846, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069554555502198e-05, + "loss": 3.6826, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068715960751146e-05, + "loss": 3.6933, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678790038804667e-05, + "loss": 3.6848, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.692, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.6915, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653632196273106e-05, + "loss": 3.6875, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064524624876258e-05, + "loss": 3.6914, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636876680055796e-05, + "loss": 3.6987, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0628490732545275e-05, + "loss": 3.6994, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620104785034755e-05, + "loss": 3.6922, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061171883752423e-05, + "loss": 3.6898, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0603349268817444e-05, + "loss": 3.692, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059496332130693e-05, + "loss": 3.6882, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0586577373796404e-05, + "loss": 3.7021, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578191426285884e-05, + "loss": 3.6951, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569805478775364e-05, + "loss": 3.6954, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0561419531264844e-05, + "loss": 3.6752, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055304996255805e-05, + "loss": 3.6911, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054466401504753e-05, + "loss": 3.6772, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053627806753701e-05, + "loss": 3.6906, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052789212002649e-05, + "loss": 3.6913, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.05195225513197e-05, + "loss": 3.6896, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051113660380918e-05, + "loss": 3.6919, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050275065629867e-05, + "loss": 3.693, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049436470878815e-05, + "loss": 3.6798, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048599514008136e-05, + "loss": 3.69, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047760919257084e-05, + "loss": 3.6916, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046922324506032e-05, + "loss": 3.68, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.04608372975498e-05, + "loss": 3.679, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045245135003928e-05, + "loss": 3.6814, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044408178133249e-05, + "loss": 3.6867, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043569583382197e-05, + "loss": 3.7051, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042730988631145e-05, + "loss": 3.6843, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041892393880093e-05, + "loss": 3.6835, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041053799129041e-05, + "loss": 3.681, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040215204377989e-05, + "loss": 3.693, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039376609626937e-05, + "loss": 3.6879, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.0385380148758853e-05, + "loss": 3.6815, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037701058005206e-05, + "loss": 3.692, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036864101134527e-05, + "loss": 3.6739, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036025506383475e-05, + "loss": 3.6739, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035186911632423e-05, + "loss": 3.6871, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034348316881371e-05, + "loss": 3.6781, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033511360010692e-05, + "loss": 3.6868, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.03267276525964e-05, + "loss": 3.686, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031834170508588e-05, + "loss": 3.6601, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030995575757536e-05, + "loss": 3.6829, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301586188868576e-05, + "loss": 3.697, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293200241358056e-05, + "loss": 3.687, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.6736, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.0276428346337016e-05, + "loss": 3.6752, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.0268042398826496e-05, + "loss": 3.6768, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.0259672830119705e-05, + "loss": 3.689, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.686, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242900935098665e-05, + "loss": 3.677, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234514987588145e-05, + "loss": 3.6781, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0226145418881354e-05, + "loss": 3.6873, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217759471370834e-05, + "loss": 3.6816, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209373523860314e-05, + "loss": 3.6765, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0200987576349794e-05, + "loss": 3.6869, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019261800764301e-05, + "loss": 3.6796, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018423206013249e-05, + "loss": 3.6795, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017584611262197e-05, + "loss": 3.6909, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016746016511145e-05, + "loss": 3.667, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015909059640466e-05, + "loss": 3.6823, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015070464889414e-05, + "loss": 3.689, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014231870138362e-05, + "loss": 3.6848, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.01339327538731e-05, + "loss": 3.6818, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012554680636258e-05, + "loss": 3.6868, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011716085885206e-05, + "loss": 3.6721, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010879129014527e-05, + "loss": 3.6724, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010040534263475e-05, + "loss": 3.6832, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009201939512423e-05, + "loss": 3.692, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008363344761371e-05, + "loss": 3.6921, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007524750010319e-05, + "loss": 3.6793, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.0066877931396404e-05, + "loss": 3.6746, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.0058491983885883e-05, + "loss": 3.6864, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.0050106036375363e-05, + "loss": 3.6763, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.0041720088864837e-05, + "loss": 3.6813, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003335052015805e-05, + "loss": 3.6936, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002496457264753e-05, + "loss": 3.6873, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0016578625137006e-05, + "loss": 3.6726, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0008192677626486e-05, + "loss": 3.6831, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.9037013053894043, + "eval_runtime": 583.4529, + "eval_samples_per_second": 654.022, + "eval_steps_per_second": 20.439, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999806730115966e-05, + "loss": 3.6862, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991420782605445e-05, + "loss": 3.6903, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998303483509493e-05, + "loss": 3.6778, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997464888758441e-05, + "loss": 3.6789, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996627931887762e-05, + "loss": 3.6708, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.99578933713671e-05, + "loss": 3.6777, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994950742385658e-05, + "loss": 3.6791, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994112147634606e-05, + "loss": 3.6604, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993275190763927e-05, + "loss": 3.6743, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992436596012875e-05, + "loss": 3.6909, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991598001261823e-05, + "loss": 3.6749, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990759406510771e-05, + "loss": 3.6696, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989920811759719e-05, + "loss": 3.6834, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989082217008667e-05, + "loss": 3.6673, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988243622257615e-05, + "loss": 3.6808, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874066653869366e-05, + "loss": 3.6555, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865680706358846e-05, + "loss": 3.6569, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857294758848326e-05, + "loss": 3.6759, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848908811337806e-05, + "loss": 3.664, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840522863827286e-05, + "loss": 3.6901, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832136916316766e-05, + "loss": 3.6732, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823750968806246e-05, + "loss": 3.6788, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815381400099455e-05, + "loss": 3.6678, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806995452588935e-05, + "loss": 3.6783, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9798609505078415e-05, + "loss": 3.6628, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790223557567895e-05, + "loss": 3.6705, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781853988861104e-05, + "loss": 3.6687, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773468041350584e-05, + "loss": 3.6734, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976508209384007e-05, + "loss": 3.6675, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975669614632955e-05, + "loss": 3.6617, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748310198819023e-05, + "loss": 3.6563, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973994063011224e-05, + "loss": 3.6738, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973155468260172e-05, + "loss": 3.6756, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.97231687350912e-05, + "loss": 3.6685, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971478278758067e-05, + "loss": 3.6704, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970639684007015e-05, + "loss": 3.6752, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969802727136337e-05, + "loss": 3.6727, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968964132385284e-05, + "loss": 3.6725, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968125537634232e-05, + "loss": 3.6663, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967286942883181e-05, + "loss": 3.6685, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966448348132129e-05, + "loss": 3.6722, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.96561139126145e-05, + "loss": 3.6578, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964772796510398e-05, + "loss": 3.6744, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963934201759346e-05, + "loss": 3.6733, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963095607008294e-05, + "loss": 3.6733, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622586501376146e-05, + "loss": 3.6713, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614200553865626e-05, + "loss": 3.6533, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605814606355106e-05, + "loss": 3.6811, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597428658844586e-05, + "loss": 3.6591, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9589059090137795e-05, + "loss": 3.6639, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580673142627275e-05, + "loss": 3.6569, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957228719511676e-05, + "loss": 3.6648, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956390124760624e-05, + "loss": 3.6709, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955551530009572e-05, + "loss": 3.6574, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954714573138893e-05, + "loss": 3.6648, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953875978387841e-05, + "loss": 3.6585, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953037383636789e-05, + "loss": 3.6692, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952198788885737e-05, + "loss": 3.6624, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951360194134685e-05, + "loss": 3.6763, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950521599383633e-05, + "loss": 3.6675, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949683004632581e-05, + "loss": 3.66, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948846047761902e-05, + "loss": 3.6564, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.94800745301085e-05, + "loss": 3.6614, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947168858259798e-05, + "loss": 3.6687, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946330263508746e-05, + "loss": 3.6665, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945491668757694e-05, + "loss": 3.6593, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446547118870155e-05, + "loss": 3.6556, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438161171359635e-05, + "loss": 3.6602, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429775223849115e-05, + "loss": 3.6574, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421389276338595e-05, + "loss": 3.6624, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413019707631804e-05, + "loss": 3.6602, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404633760121284e-05, + "loss": 3.6606, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396247812610764e-05, + "loss": 3.6621, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387861865100244e-05, + "loss": 3.6757, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937949229639345e-05, + "loss": 3.6666, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937110634888293e-05, + "loss": 3.6619, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936272040137241e-05, + "loss": 3.6629, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935433445386189e-05, + "loss": 3.6632, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934596488515511e-05, + "loss": 3.6582, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933757893764459e-05, + "loss": 3.6717, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932919299013407e-05, + "loss": 3.6682, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932080704262355e-05, + "loss": 3.6648, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931242109511303e-05, + "loss": 3.6483, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930405152640624e-05, + "loss": 3.6611, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929566557889572e-05, + "loss": 3.6484, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.92872796313852e-05, + "loss": 3.6665, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927889368387468e-05, + "loss": 3.6634, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927052411516789e-05, + "loss": 3.6571, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926213816765737e-05, + "loss": 3.6639, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925375222014685e-05, + "loss": 3.6636, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245366272636333e-05, + "loss": 3.6535, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923699670392954e-05, + "loss": 3.6567, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922861075641902e-05, + "loss": 3.6641, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.6525, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211838861397976e-05, + "loss": 3.6528, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920346929269119e-05, + "loss": 3.6515, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919508334518067e-05, + "loss": 3.6581, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918669739767015e-05, + "loss": 3.6768, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178311450159625e-05, + "loss": 3.6563, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169925502649105e-05, + "loss": 3.6567, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161539555138585e-05, + "loss": 3.6563, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.91531699864318e-05, + "loss": 3.6627, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914478403892128e-05, + "loss": 3.6622, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913639809141076e-05, + "loss": 3.654, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912801214390024e-05, + "loss": 3.6644, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911962619638972e-05, + "loss": 3.6445, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.91112402488792e-05, + "loss": 3.6497, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910287068017241e-05, + "loss": 3.6583, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909448473266189e-05, + "loss": 3.6541, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908609878515137e-05, + "loss": 3.6521, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907771283764085e-05, + "loss": 3.6596, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906934326893406e-05, + "loss": 3.6355, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906095732142354e-05, + "loss": 3.6566, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052571373913025e-05, + "loss": 3.6648, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044185426402505e-05, + "loss": 3.6602, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035815857695714e-05, + "loss": 3.6457, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027429910185194e-05, + "loss": 3.6519, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019043962674674e-05, + "loss": 3.6468, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010658015164154e-05, + "loss": 3.6614, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900228844645736e-05, + "loss": 3.6558, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899390249894684e-05, + "loss": 3.6527, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898551655143632e-05, + "loss": 3.6497, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.89771306039258e-05, + "loss": 3.6602, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896876103521901e-05, + "loss": 3.6529, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896037508770849e-05, + "loss": 3.65, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895198914019798e-05, + "loss": 3.6531, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894360319268746e-05, + "loss": 3.6525, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893521724517694e-05, + "loss": 3.6534, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892683129766642e-05, + "loss": 3.6605, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.89184453501559e-05, + "loss": 3.6441, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891007578144911e-05, + "loss": 3.6534, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890168983393859e-05, + "loss": 3.6617, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889330388642807e-05, + "loss": 3.6531, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888491793891755e-05, + "loss": 3.6546, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876548370210757e-05, + "loss": 3.6589, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868162422700236e-05, + "loss": 3.6471, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859776475189716e-05, + "loss": 3.6477, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851390527679196e-05, + "loss": 3.652, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843004580168676e-05, + "loss": 3.6671, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883463501146189e-05, + "loss": 3.6635, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882624906395137e-05, + "loss": 3.6503, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881786311644085e-05, + "loss": 3.6517, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880947716893033e-05, + "loss": 3.6538, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880110760022354e-05, + "loss": 3.6508, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879272165271302e-05, + "loss": 3.6557, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.87843357052025e-05, + "loss": 3.6652, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877594975769198e-05, + "loss": 3.6622, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876756381018146e-05, + "loss": 3.6454, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875919424147467e-05, + "loss": 3.6555, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.898914098739624, + "eval_runtime": 312.5322, + "eval_samples_per_second": 1220.965, + "eval_steps_per_second": 38.156, + "step": 686871 + }, + { + "epoch": 1.0, + "learning_rate": 3.875080829396415e-05, + "loss": 3.6518, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874242234645363e-05, + "loss": 3.6624, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873403639894311e-05, + "loss": 3.653, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872565045143259e-05, + "loss": 3.6504, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8717280882725806e-05, + "loss": 3.6456, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708894935215286e-05, + "loss": 3.6504, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870050898770476e-05, + "loss": 3.6515, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869212304019424e-05, + "loss": 3.6348, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683753471487455e-05, + "loss": 3.6462, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675367523976935e-05, + "loss": 3.6643, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866698157646641e-05, + "loss": 3.646, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865859562895589e-05, + "loss": 3.6429, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6597, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.6422, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.6535, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625068217717544e-05, + "loss": 3.6284, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616682270207024e-05, + "loss": 3.6311, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608296322696503e-05, + "loss": 3.6472, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599910375185983e-05, + "loss": 3.6404, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591524427675463e-05, + "loss": 3.6629, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858315485896867e-05, + "loss": 3.6421, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857476891145815e-05, + "loss": 3.6584, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856638296394763e-05, + "loss": 3.6415, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855799701643711e-05, + "loss": 3.6475, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854962744773032e-05, + "loss": 3.6364, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.85412415002198e-05, + "loss": 3.6457, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853285555270929e-05, + "loss": 3.6452, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852446960519877e-05, + "loss": 3.6471, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851608365768825e-05, + "loss": 3.639, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850771408898146e-05, + "loss": 3.6363, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849932814147094e-05, + "loss": 3.631, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849094219396042e-05, + "loss": 3.6482, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84825562464499e-05, + "loss": 3.6449, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474186677743106e-05, + "loss": 3.6456, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465800730232586e-05, + "loss": 3.6452, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457414782722066e-05, + "loss": 3.6495, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449028835211546e-05, + "loss": 3.6434, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440642887701026e-05, + "loss": 3.6443, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843227331899424e-05, + "loss": 3.6444, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842388737148372e-05, + "loss": 3.6419, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.84155014239732e-05, + "loss": 3.6452, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840711547646268e-05, + "loss": 3.6388, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839874590775589e-05, + "loss": 3.6434, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839035996024537e-05, + "loss": 3.6482, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838197401273485e-05, + "loss": 3.648, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837358806522433e-05, + "loss": 3.6453, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836520211771381e-05, + "loss": 3.6288, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835683254900702e-05, + "loss": 3.6524, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.83484466014965e-05, + "loss": 3.6344, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834006065398598e-05, + "loss": 3.6383, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833167470647546e-05, + "loss": 3.6354, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323305137768675e-05, + "loss": 3.6339, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314919190258155e-05, + "loss": 3.6489, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306533242747635e-05, + "loss": 3.6297, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298147295237115e-05, + "loss": 3.6415, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289761347726595e-05, + "loss": 3.6279, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828137540021607e-05, + "loss": 3.6431, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8273005831509284e-05, + "loss": 3.6357, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8264619883998764e-05, + "loss": 3.6512, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8256233936488244e-05, + "loss": 3.6454, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824784798897772e-05, + "loss": 3.6351, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823947842027093e-05, + "loss": 3.6317, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823109247276041e-05, + "loss": 3.6339, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822270652524989e-05, + "loss": 3.6399, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821432057773937e-05, + "loss": 3.6406, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820595100903259e-05, + "loss": 3.6345, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819756506152207e-05, + "loss": 3.6293, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818917911401154e-05, + "loss": 3.6371, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818079316650102e-05, + "loss": 3.6311, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.81724072189905e-05, + "loss": 3.6384, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816403765028371e-05, + "loss": 3.6349, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815565170277319e-05, + "loss": 3.6318, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814726575526267e-05, + "loss": 3.6392, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813887980775215e-05, + "loss": 3.6483, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813051023904537e-05, + "loss": 3.6398, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812212429153485e-05, + "loss": 3.6389, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811373834402433e-05, + "loss": 3.6343, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810535239651381e-05, + "loss": 3.6434, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8096982827807016e-05, + "loss": 3.6322, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8088596880296496e-05, + "loss": 3.6441, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.8080210932785976e-05, + "loss": 3.6441, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071824985275456e-05, + "loss": 3.6431, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063439037764936e-05, + "loss": 3.6281, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055069469058145e-05, + "loss": 3.6292, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046683521547625e-05, + "loss": 3.6231, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038297574037105e-05, + "loss": 3.6429, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029911626526585e-05, + "loss": 3.6349, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.80215420578198e-05, + "loss": 3.6353, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801315611030928e-05, + "loss": 3.639, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800477016279876e-05, + "loss": 3.638, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799638421528824e-05, + "loss": 3.6287, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798801464658145e-05, + "loss": 3.6313, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797962869907093e-05, + "loss": 3.6435, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797124275156041e-05, + "loss": 3.6246, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796285680404989e-05, + "loss": 3.6264, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.79544872353431e-05, + "loss": 3.627, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794610128783258e-05, + "loss": 3.6338, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793771534032206e-05, + "loss": 3.6498, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792932939281154e-05, + "loss": 3.6309, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920959824104754e-05, + "loss": 3.6334, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912573876594234e-05, + "loss": 3.6322, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904187929083714e-05, + "loss": 3.6361, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895801981573194e-05, + "loss": 3.6363, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.78874324128664e-05, + "loss": 3.632, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787904646535588e-05, + "loss": 3.634, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787066051784536e-05, + "loss": 3.6221, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786227457033484e-05, + "loss": 3.626, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785388862282432e-05, + "loss": 3.6318, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.78455026753138e-05, + "loss": 3.6294, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783713310660701e-05, + "loss": 3.627, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782874715909649e-05, + "loss": 3.6357, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782036121158597e-05, + "loss": 3.613, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781197526407546e-05, + "loss": 3.6305, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780360569536867e-05, + "loss": 3.6403, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779521974785815e-05, + "loss": 3.6361, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778683380034763e-05, + "loss": 3.6228, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777844785283711e-05, + "loss": 3.626, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777006190532659e-05, + "loss": 3.6217, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.77616923366198e-05, + "loss": 3.6327, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775330638910928e-05, + "loss": 3.6326, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744920441598757e-05, + "loss": 3.6346, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736534494088237e-05, + "loss": 3.6187, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728164925381446e-05, + "loss": 3.6401, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719778977870926e-05, + "loss": 3.6247, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771139303036041e-05, + "loss": 3.6274, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770300708284989e-05, + "loss": 3.6263, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.76946375141431e-05, + "loss": 3.632, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768625156663258e-05, + "loss": 3.6284, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767786561912206e-05, + "loss": 3.6321, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766947967161154e-05, + "loss": 3.622, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766111010290475e-05, + "loss": 3.6307, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765272415539423e-05, + "loss": 3.6389, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764433820788371e-05, + "loss": 3.6277, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763595226037319e-05, + "loss": 3.6298, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.76275826916664e-05, + "loss": 3.6371, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761919674415588e-05, + "loss": 3.6239, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610810796645366e-05, + "loss": 3.6262, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602424849134846e-05, + "loss": 3.6271, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7594038901624326e-05, + "loss": 3.6345, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585669332917535e-05, + "loss": 3.6427, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577283385407015e-05, + "loss": 3.6256, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568897437896495e-05, + "loss": 3.6297, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756051149038597e-05, + "loss": 3.629, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7552141921679184e-05, + "loss": 3.6282, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543755974168664e-05, + "loss": 3.6329, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535370026658144e-05, + "loss": 3.6382, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752698407914762e-05, + "loss": 3.636, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518598131637104e-05, + "loss": 3.6215, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751022856293032e-05, + "loss": 3.6296, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8977551460266113, + "eval_runtime": 312.6536, + "eval_samples_per_second": 1220.491, + "eval_steps_per_second": 38.141, + "step": 763190 + }, + { + "epoch": 0.0, + "learning_rate": 3.750184261541979e-05, + "loss": 3.6337, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749345666790927e-05, + "loss": 3.6312, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748507072039875e-05, + "loss": 3.6311, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747668477288823e-05, + "loss": 3.636, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746829882537771e-05, + "loss": 3.6401, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745992925667092e-05, + "loss": 3.6299, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74515433091604e-05, + "loss": 3.6282, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744315736164988e-05, + "loss": 3.6276, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743477141413936e-05, + "loss": 3.6292, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742640184543257e-05, + "loss": 3.6376, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741801589792206e-05, + "loss": 3.6336, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740962995041154e-05, + "loss": 3.6291, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740124400290102e-05, + "loss": 3.6324, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392874434194226e-05, + "loss": 3.6183, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384488486683706e-05, + "loss": 3.6316, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376102539173186e-05, + "loss": 3.6184, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367716591662666e-05, + "loss": 3.6185, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359347022955875e-05, + "loss": 3.6245, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350961075445355e-05, + "loss": 3.6204, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342575127934835e-05, + "loss": 3.6448, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334189180424315e-05, + "loss": 3.6359, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325819611717524e-05, + "loss": 3.6288, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317433664207004e-05, + "loss": 3.6269, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730904771669649e-05, + "loss": 3.6306, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730066176918597e-05, + "loss": 3.618, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729229220047918e-05, + "loss": 3.6296, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728390625296866e-05, + "loss": 3.6292, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727552030545814e-05, + "loss": 3.6092, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726713435794762e-05, + "loss": 3.6191, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725876478924083e-05, + "loss": 3.6189, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725037884173031e-05, + "loss": 3.6281, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724199289421979e-05, + "loss": 3.6291, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723360694670927e-05, + "loss": 3.6231, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722522099919875e-05, + "loss": 3.6337, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721685143049196e-05, + "loss": 3.6199, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208465482981445e-05, + "loss": 3.6311, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200079535470925e-05, + "loss": 3.6343, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191693587960405e-05, + "loss": 3.6209, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183324019253614e-05, + "loss": 3.6209, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174938071743094e-05, + "loss": 3.621, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166552124232574e-05, + "loss": 3.6154, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158166176722054e-05, + "loss": 3.6346, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149780229211534e-05, + "loss": 3.6276, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714141066050474e-05, + "loss": 3.6265, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713302471299422e-05, + "loss": 3.6276, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.71246387654837e-05, + "loss": 3.6214, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711625281797318e-05, + "loss": 3.6256, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.71078832492664e-05, + "loss": 3.6297, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709949730175588e-05, + "loss": 3.5915, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709111135424536e-05, + "loss": 3.6323, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708272540673484e-05, + "loss": 3.6193, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707435583802805e-05, + "loss": 3.6318, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706596989051753e-05, + "loss": 3.6258, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705758394300701e-05, + "loss": 3.6182, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704919799549649e-05, + "loss": 3.6089, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704081204798597e-05, + "loss": 3.6208, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7032442479279176e-05, + "loss": 3.629, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024056531768656e-05, + "loss": 3.6279, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015670584258136e-05, + "loss": 3.6357, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7007284636747616e-05, + "loss": 3.6178, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699891506804083e-05, + "loss": 3.6029, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699052912053031e-05, + "loss": 3.6369, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698214317301979e-05, + "loss": 3.6154, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697375722550927e-05, + "loss": 3.6055, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696538765680248e-05, + "loss": 3.6235, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695700170929196e-05, + "loss": 3.622, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694861576178144e-05, + "loss": 3.613, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694022981427092e-05, + "loss": 3.613, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693186024556413e-05, + "loss": 3.6074, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692347429805361e-05, + "loss": 3.6093, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691508835054309e-05, + "loss": 3.6309, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690670240303257e-05, + "loss": 3.6232, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898332834325786e-05, + "loss": 3.619, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889946886815266e-05, + "loss": 3.6132, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881560939304746e-05, + "loss": 3.6334, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873174991794226e-05, + "loss": 3.6172, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864805423087435e-05, + "loss": 3.6284, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856419475576915e-05, + "loss": 3.6132, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6848033528066395e-05, + "loss": 3.6146, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683964758055587e-05, + "loss": 3.6245, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831278011849084e-05, + "loss": 3.629, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822892064338564e-05, + "loss": 3.6146, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814506116828044e-05, + "loss": 3.624, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806120169317523e-05, + "loss": 3.6085, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679775060061074e-05, + "loss": 3.6125, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678936465310022e-05, + "loss": 3.6228, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.67809787055897e-05, + "loss": 3.6233, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677259275807917e-05, + "loss": 3.6126, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676422318937239e-05, + "loss": 3.6115, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675583724186187e-05, + "loss": 3.6151, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674745129435134e-05, + "loss": 3.6202, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673906534684082e-05, + "loss": 3.6203, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.67306793993303e-05, + "loss": 3.6065, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672230983062352e-05, + "loss": 3.6244, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713923883113e-05, + "loss": 3.6252, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670553793560248e-05, + "loss": 3.6241, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669715198809196e-05, + "loss": 3.5939, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668878241938517e-05, + "loss": 3.6139, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680396471874646e-05, + "loss": 3.6141, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6672010524364126e-05, + "loss": 3.625, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663624576853606e-05, + "loss": 3.6202, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655238629343086e-05, + "loss": 3.6158, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646852681832566e-05, + "loss": 3.6064, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638483113125775e-05, + "loss": 3.617, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630097165615255e-05, + "loss": 3.6083, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621711218104735e-05, + "loss": 3.6118, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613325270594215e-05, + "loss": 3.6068, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660495570188743e-05, + "loss": 3.6236, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659656975437691e-05, + "loss": 3.6069, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658818380686639e-05, + "loss": 3.6032, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657979785935587e-05, + "loss": 3.6043, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657141191184535e-05, + "loss": 3.6107, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656302596433483e-05, + "loss": 3.6144, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655465639562804e-05, + "loss": 3.609, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654627044811752e-05, + "loss": 3.6165, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537884500607e-05, + "loss": 3.6216, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652949855309648e-05, + "loss": 3.6043, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652112898438969e-05, + "loss": 3.6187, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651274303687917e-05, + "loss": 3.6144, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650435708936865e-05, + "loss": 3.6126, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649597114185813e-05, + "loss": 3.6128, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487601573151344e-05, + "loss": 3.6029, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479215625640824e-05, + "loss": 3.6145, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470829678130304e-05, + "loss": 3.6075, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462443730619784e-05, + "loss": 3.6145, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645407416191299e-05, + "loss": 3.613, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644568821440247e-05, + "loss": 3.6101, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643730226689195e-05, + "loss": 3.6091, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642891631938143e-05, + "loss": 3.5976, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642053037187091e-05, + "loss": 3.6241, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641216080316412e-05, + "loss": 3.606, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.64037748556536e-05, + "loss": 3.6271, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639538890814308e-05, + "loss": 3.6041, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638700296063257e-05, + "loss": 3.6186, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637863339192578e-05, + "loss": 3.6181, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637024744441526e-05, + "loss": 3.6047, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636186149690474e-05, + "loss": 3.6151, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635347554939422e-05, + "loss": 3.6051, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634510598068743e-05, + "loss": 3.6181, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633672003317691e-05, + "loss": 3.6178, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632833408566639e-05, + "loss": 3.607, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631994813815587e-05, + "loss": 3.6156, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311578569449076e-05, + "loss": 3.6083, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303192621938556e-05, + "loss": 3.6174, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294806674428036e-05, + "loss": 3.6067, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628642072691752e-05, + "loss": 3.6248, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627805115821073e-05, + "loss": 3.6079, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626966521070021e-05, + "loss": 3.6147, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626127926318969e-05, + "loss": 3.6102, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.890789031982422, + "eval_runtime": 309.3415, + "eval_samples_per_second": 1233.559, + "eval_steps_per_second": 38.55, + "step": 839510 + }, + { + "epoch": 1.0, + "learning_rate": 3.625289331567917e-05, + "loss": 3.6089, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624450736816865e-05, + "loss": 3.6079, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623613779946186e-05, + "loss": 3.6084, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622775185195134e-05, + "loss": 3.6136, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621936590444082e-05, + "loss": 3.6207, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.62109799569303e-05, + "loss": 3.6049, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202594009419774e-05, + "loss": 3.6064, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619422444071299e-05, + "loss": 3.6046, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185838493202476e-05, + "loss": 3.6085, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617745254569195e-05, + "loss": 3.6126, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616906659818143e-05, + "loss": 3.6056, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160697029474645e-05, + "loss": 3.6051, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152311081964125e-05, + "loss": 3.6112, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.61439251344536e-05, + "loss": 3.5926, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613553918694308e-05, + "loss": 3.6041, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612715323943256e-05, + "loss": 3.5957, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118783670725774e-05, + "loss": 3.5938, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611039772321525e-05, + "loss": 3.6036, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610201177570473e-05, + "loss": 3.5964, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093625828194214e-05, + "loss": 3.6157, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608525625948742e-05, + "loss": 3.6153, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.60768703119769e-05, + "loss": 3.6039, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606848436446638e-05, + "loss": 3.6034, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606009841695586e-05, + "loss": 3.6048, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605172884824907e-05, + "loss": 3.5921, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604334290073855e-05, + "loss": 3.6105, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603495695322803e-05, + "loss": 3.6039, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602657100571751e-05, + "loss": 3.5866, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601818505820699e-05, + "loss": 3.596, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.60098154895002e-05, + "loss": 3.5968, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600142954198968e-05, + "loss": 3.6014, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599304359447917e-05, + "loss": 3.6009, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598465764696865e-05, + "loss": 3.6024, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597627169945813e-05, + "loss": 3.607, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596790213075134e-05, + "loss": 3.5952, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595951618324082e-05, + "loss": 3.6113, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.59511302357303e-05, + "loss": 3.6098, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942744288219777e-05, + "loss": 3.5945, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934374719512986e-05, + "loss": 3.5992, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925988772002466e-05, + "loss": 3.5956, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917602824491946e-05, + "loss": 3.5931, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909216876981426e-05, + "loss": 3.6066, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900830929470906e-05, + "loss": 3.6045, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589246136076412e-05, + "loss": 3.607, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.58840754132536e-05, + "loss": 3.6022, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587568946574308e-05, + "loss": 3.6015, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586730351823256e-05, + "loss": 3.6022, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585893394952577e-05, + "loss": 3.602, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585054800201525e-05, + "loss": 3.5748, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584216205450473e-05, + "loss": 3.6091, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583377610699421e-05, + "loss": 3.5944, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582540653828742e-05, + "loss": 3.6084, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.58170205907769e-05, + "loss": 3.6017, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580863464326638e-05, + "loss": 3.595, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580024869575586e-05, + "loss": 3.5853, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579187912704907e-05, + "loss": 3.596, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783493179538555e-05, + "loss": 3.6135, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775107232028035e-05, + "loss": 3.5996, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766721284517515e-05, + "loss": 3.6144, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758335337006995e-05, + "loss": 3.5983, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5749965768300204e-05, + "loss": 3.5796, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741579820789684e-05, + "loss": 3.6139, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733193873279164e-05, + "loss": 3.5948, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724807925768644e-05, + "loss": 3.5847, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571643835706185e-05, + "loss": 3.6, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570805240955133e-05, + "loss": 3.5999, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569966646204081e-05, + "loss": 3.5861, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569128051453029e-05, + "loss": 3.5927, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568291094582351e-05, + "loss": 3.5815, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567452499831299e-05, + "loss": 3.5923, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566613905080247e-05, + "loss": 3.6031, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565775310329195e-05, + "loss": 3.5991, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564938353458516e-05, + "loss": 3.5994, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564099758707464e-05, + "loss": 3.5904, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563261163956412e-05, + "loss": 3.6055, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.56242256920536e-05, + "loss": 3.5999, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615856123346807e-05, + "loss": 3.6063, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607470175836287e-05, + "loss": 3.5895, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599084228325767e-05, + "loss": 3.5914, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590698280815246e-05, + "loss": 3.6005, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582312333304726e-05, + "loss": 3.608, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557394276459794e-05, + "loss": 3.5949, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556555681708742e-05, + "loss": 3.6015, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.55571708695769e-05, + "loss": 3.5843, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554878492206638e-05, + "loss": 3.5911, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554041535335959e-05, + "loss": 3.5966, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553202940584907e-05, + "loss": 3.6068, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552364345833855e-05, + "loss": 3.5878, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515257510828024e-05, + "loss": 3.5907, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550688794212124e-05, + "loss": 3.5959, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549850199461072e-05, + "loss": 3.5949, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.54901160471002e-05, + "loss": 3.5972, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548173009958968e-05, + "loss": 3.584, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473360530882896e-05, + "loss": 3.5971, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464974583372376e-05, + "loss": 3.6086, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456588635861856e-05, + "loss": 3.6025, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544820268835133e-05, + "loss": 3.5738, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439833119644545e-05, + "loss": 3.5871, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431447172134025e-05, + "loss": 3.5919, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.54230612246235e-05, + "loss": 3.6034, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541467527711298e-05, + "loss": 3.6007, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540628932960246e-05, + "loss": 3.5925, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5397919760895674e-05, + "loss": 3.5857, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389533813385154e-05, + "loss": 3.5978, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5381147865874634e-05, + "loss": 3.5839, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372761918364114e-05, + "loss": 3.5912, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364375970853594e-05, + "loss": 3.5889, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.53560064021468e-05, + "loss": 3.595, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534762045463628e-05, + "loss": 3.5912, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533923450712576e-05, + "loss": 3.5775, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533084855961524e-05, + "loss": 3.5855, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532247899090845e-05, + "loss": 3.5845, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531409304339793e-05, + "loss": 3.595, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530570709588741e-05, + "loss": 3.5867, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529732114837689e-05, + "loss": 3.5937, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528895157967011e-05, + "loss": 3.5966, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528056563215959e-05, + "loss": 3.5869, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527217968464907e-05, + "loss": 3.5999, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526379373713855e-05, + "loss": 3.5929, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5255424168431756e-05, + "loss": 3.5913, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5247038220921236e-05, + "loss": 3.5867, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238652273410716e-05, + "loss": 3.5803, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230266325900196e-05, + "loss": 3.5929, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5221880378389676e-05, + "loss": 3.5856, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213510809682885e-05, + "loss": 3.5943, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5205124862172365e-05, + "loss": 3.5902, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196738914661845e-05, + "loss": 3.589, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188352967151325e-05, + "loss": 3.585, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517998339844454e-05, + "loss": 3.5789, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517159745093402e-05, + "loss": 3.5985, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.51632115034235e-05, + "loss": 3.5858, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515482555591298e-05, + "loss": 3.6009, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514645598720619e-05, + "loss": 3.5848, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513807003969567e-05, + "loss": 3.596, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512968409218515e-05, + "loss": 3.595, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512129814467463e-05, + "loss": 3.5825, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511292857596784e-05, + "loss": 3.5926, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510454262845732e-05, + "loss": 3.5852, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.50961566809468e-05, + "loss": 3.6004, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508777073343628e-05, + "loss": 3.5952, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079401164729495e-05, + "loss": 3.5869, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5071015217218975e-05, + "loss": 3.5881, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062629269708455e-05, + "loss": 3.5911, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5054243322197935e-05, + "loss": 3.5951, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5045873753491144e-05, + "loss": 3.5826, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037487805980624e-05, + "loss": 3.6047, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5029101858470104e-05, + "loss": 3.5862, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020715910959584e-05, + "loss": 3.596, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012329963449064e-05, + "loss": 3.5875, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.891434907913208, + "eval_runtime": 309.9056, + "eval_samples_per_second": 1231.314, + "eval_steps_per_second": 38.479, + "step": 915830 + }, + { + "epoch": 0.0, + "learning_rate": 3.500396039474227e-05, + "loss": 3.5929, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499557444723175e-05, + "loss": 3.5866, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498718849972123e-05, + "loss": 3.5876, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497880255221071e-05, + "loss": 3.5916, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497041660470019e-05, + "loss": 3.5999, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496204703599341e-05, + "loss": 3.5863, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495366108848289e-05, + "loss": 3.5851, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494527514097237e-05, + "loss": 3.5847, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493688919346185e-05, + "loss": 3.5882, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492851962475506e-05, + "loss": 3.5851, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492013367724454e-05, + "loss": 3.5893, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491174772973402e-05, + "loss": 3.5875, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.49033617822235e-05, + "loss": 3.5929, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894992213516706e-05, + "loss": 3.5724, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886606266006186e-05, + "loss": 3.582, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878220318495666e-05, + "loss": 3.5764, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869834370985146e-05, + "loss": 3.5723, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486146480227836e-05, + "loss": 3.5843, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485307885476784e-05, + "loss": 3.576, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484469290725732e-05, + "loss": 3.5958, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.48363069597468e-05, + "loss": 3.5961, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482793739104001e-05, + "loss": 3.5837, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481955144352949e-05, + "loss": 3.5828, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481116549601897e-05, + "loss": 3.5861, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480277954850845e-05, + "loss": 3.57, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479440997980166e-05, + "loss": 3.5936, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478602403229114e-05, + "loss": 3.5803, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477763808478062e-05, + "loss": 3.5688, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.47692521372701e-05, + "loss": 3.5779, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760882568563316e-05, + "loss": 3.5755, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752496621052796e-05, + "loss": 3.5777, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744110673542276e-05, + "loss": 3.5808, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735724726031756e-05, + "loss": 3.5877, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472733877852123e-05, + "loss": 3.5815, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718969209814445e-05, + "loss": 3.5768, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4710583262303925e-05, + "loss": 3.5889, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702197314793405e-05, + "loss": 3.5886, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469381136728288e-05, + "loss": 3.5768, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4685441798576094e-05, + "loss": 3.5779, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4677055851065574e-05, + "loss": 3.5765, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668669903555053e-05, + "loss": 3.5703, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660283956044533e-05, + "loss": 3.5861, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465189800853401e-05, + "loss": 3.5841, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464352843982723e-05, + "loss": 3.5886, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.46351424923167e-05, + "loss": 3.5818, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462675654480618e-05, + "loss": 3.5772, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461837059729566e-05, + "loss": 3.5843, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.461000102858888e-05, + "loss": 3.583, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460161508107835e-05, + "loss": 3.5555, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459322913356783e-05, + "loss": 3.5869, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458484318605731e-05, + "loss": 3.5755, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457647361735053e-05, + "loss": 3.5864, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456808766984001e-05, + "loss": 3.5802, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455970172232949e-05, + "loss": 3.5793, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455131577481897e-05, + "loss": 3.5642, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454292982730845e-05, + "loss": 3.5731, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534560258601656e-05, + "loss": 3.5942, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526174311091136e-05, + "loss": 3.5812, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517788363580616e-05, + "loss": 3.5911, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509402416070096e-05, + "loss": 3.5783, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4501032847363305e-05, + "loss": 3.5577, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4492646899852785e-05, + "loss": 3.5971, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484260952342265e-05, + "loss": 3.574, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475875004831745e-05, + "loss": 3.5667, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446750543612496e-05, + "loss": 3.5808, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445911948861444e-05, + "loss": 3.5756, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445073354110392e-05, + "loss": 3.5701, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.44423475935934e-05, + "loss": 3.5707, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443397802488661e-05, + "loss": 3.5665, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442559207737609e-05, + "loss": 3.5722, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441720612986557e-05, + "loss": 3.5817, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440882018235505e-05, + "loss": 3.5775, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440045061364826e-05, + "loss": 3.581, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439206466613774e-05, + "loss": 3.5674, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438367871862722e-05, + "loss": 3.5875, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43752927711167e-05, + "loss": 3.5806, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4366923202409914e-05, + "loss": 3.5859, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358537254899394e-05, + "loss": 3.5702, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4350151307388874e-05, + "loss": 3.5716, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4341765359878354e-05, + "loss": 3.5854, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4333395791171563e-05, + "loss": 3.5835, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4325009843661043e-05, + "loss": 3.5747, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431662389615052e-05, + "loss": 3.5826, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430823794864e-05, + "loss": 3.5647, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429986837993321e-05, + "loss": 3.57, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429148243242269e-05, + "loss": 3.5767, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428309648491217e-05, + "loss": 3.5863, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427471053740165e-05, + "loss": 3.5651, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426632458989113e-05, + "loss": 3.5748, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425795502118435e-05, + "loss": 3.5745, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424956907367383e-05, + "loss": 3.5757, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424118312616331e-05, + "loss": 3.5778, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423281355745652e-05, + "loss": 3.5682, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224427609946e-05, + "loss": 3.5779, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421604166243548e-05, + "loss": 3.5848, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420765571492496e-05, + "loss": 3.5866, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419926976741444e-05, + "loss": 3.5521, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190900198707646e-05, + "loss": 3.5723, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182514251197126e-05, + "loss": 3.5708, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4174128303686606e-05, + "loss": 3.5845, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165742356176086e-05, + "loss": 3.5843, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.41573727874693e-05, + "loss": 3.5706, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414898683995878e-05, + "loss": 3.5669, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414060089244826e-05, + "loss": 3.5749, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413221494493774e-05, + "loss": 3.5699, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412382899742722e-05, + "loss": 3.5713, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411545942872043e-05, + "loss": 3.5669, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410707348120991e-05, + "loss": 3.5767, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409868753369939e-05, + "loss": 3.572, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409030158618887e-05, + "loss": 3.5587, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408193201748208e-05, + "loss": 3.5639, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407354606997156e-05, + "loss": 3.5664, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406516012246104e-05, + "loss": 3.5751, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056774174950526e-05, + "loss": 3.5662, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048404606243735e-05, + "loss": 3.5759, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4040018658733215e-05, + "loss": 3.5738, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031632711222695e-05, + "loss": 3.573, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4023246763712175e-05, + "loss": 3.5749, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4014877195005384e-05, + "loss": 3.5754, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4006491247494864e-05, + "loss": 3.5726, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3998105299984344e-05, + "loss": 3.5666, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.3989719352473824e-05, + "loss": 3.561, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398134978376703e-05, + "loss": 3.5753, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397296383625651e-05, + "loss": 3.5674, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396457788874599e-05, + "loss": 3.5751, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395619194123548e-05, + "loss": 3.568, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394782237252869e-05, + "loss": 3.5704, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393943642501817e-05, + "loss": 3.5685, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393105047750765e-05, + "loss": 3.5618, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392266452999713e-05, + "loss": 3.5751, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.39142785824866e-05, + "loss": 3.57, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390590901377982e-05, + "loss": 3.5825, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.38975230662693e-05, + "loss": 3.5635, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388913711875878e-05, + "loss": 3.5737, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388076755005199e-05, + "loss": 3.5778, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387238160254147e-05, + "loss": 3.564, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386399565503095e-05, + "loss": 3.5702, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855609707520434e-05, + "loss": 3.5694, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384722376000991e-05, + "loss": 3.58, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383885419130312e-05, + "loss": 3.5787, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.38304682437926e-05, + "loss": 3.5722, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3822082296282076e-05, + "loss": 3.5679, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3813696348771556e-05, + "loss": 3.572, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380532678006477e-05, + "loss": 3.5771, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379694083255425e-05, + "loss": 3.5606, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788554885043725e-05, + "loss": 3.5877, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780168937533205e-05, + "loss": 3.5671, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377179936882642e-05, + "loss": 3.5745, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.37634134213159e-05, + "loss": 3.5688, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.89314866065979, + "eval_runtime": 334.2706, + "eval_samples_per_second": 1141.563, + "eval_steps_per_second": 35.675, + "step": 992150 + }, + { + "epoch": 1.0, + "learning_rate": 3.375502747380538e-05, + "loss": 3.5718, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374664152629486e-05, + "loss": 3.5669, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738271957588076e-05, + "loss": 3.5669, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372988601007755e-05, + "loss": 3.5762, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372150006256703e-05, + "loss": 3.5781, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371311411505651e-05, + "loss": 3.5707, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370472816754599e-05, + "loss": 3.5665, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.36963585988392e-05, + "loss": 3.5638, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368797265132868e-05, + "loss": 3.569, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367958670381816e-05, + "loss": 3.5687, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367120075630764e-05, + "loss": 3.5692, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662831187600854e-05, + "loss": 3.574, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654445240090334e-05, + "loss": 3.571, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3646059292579814e-05, + "loss": 3.5543, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637673345069294e-05, + "loss": 3.5642, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.36293037763625e-05, + "loss": 3.5574, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362091782885198e-05, + "loss": 3.5497, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361253188134146e-05, + "loss": 3.5679, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360414593383094e-05, + "loss": 3.5577, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359577636512415e-05, + "loss": 3.572, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358739041761363e-05, + "loss": 3.5787, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357900447010311e-05, + "loss": 3.5642, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357061852259259e-05, + "loss": 3.5657, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356224895388581e-05, + "loss": 3.568, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355386300637529e-05, + "loss": 3.5515, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354547705886477e-05, + "loss": 3.5745, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353709111135425e-05, + "loss": 3.5614, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352872154264746e-05, + "loss": 3.5565, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352033559513694e-05, + "loss": 3.5585, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351194964762642e-05, + "loss": 3.5547, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.35035637001159e-05, + "loss": 3.5598, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3495194131409106e-05, + "loss": 3.5638, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486808183898586e-05, + "loss": 3.5711, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3478422236388066e-05, + "loss": 3.5608, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3470036288877546e-05, + "loss": 3.5587, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346165034136703e-05, + "loss": 3.5633, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345328077266024e-05, + "loss": 3.5729, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344489482514972e-05, + "loss": 3.5568, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.34365088776392e-05, + "loss": 3.5603, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342812293012868e-05, + "loss": 3.5604, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341975336142189e-05, + "loss": 3.5585, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341136741391137e-05, + "loss": 3.5617, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340298146640085e-05, + "loss": 3.567, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339459551889033e-05, + "loss": 3.574, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338622595018354e-05, + "loss": 3.5635, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337784000267302e-05, + "loss": 3.5608, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.33694540551625e-05, + "loss": 3.5618, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336106810765198e-05, + "loss": 3.5645, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3352698538945195e-05, + "loss": 3.5397, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3344312591434675e-05, + "loss": 3.5685, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3335926643924155e-05, + "loss": 3.5576, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3327540696413635e-05, + "loss": 3.5676, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3319171127706844e-05, + "loss": 3.5623, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3310785180196324e-05, + "loss": 3.5581, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302399232685804e-05, + "loss": 3.5502, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3294013285175284e-05, + "loss": 3.5505, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328564371646849e-05, + "loss": 3.5755, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327725776895797e-05, + "loss": 3.5597, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326887182144745e-05, + "loss": 3.5779, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326048587393693e-05, + "loss": 3.5594, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325211630523015e-05, + "loss": 3.5471, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324373035771963e-05, + "loss": 3.5765, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323534441020911e-05, + "loss": 3.5592, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322695846269859e-05, + "loss": 3.5443, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.32185888939918e-05, + "loss": 3.5567, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321020294648128e-05, + "loss": 3.5615, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320181699897076e-05, + "loss": 3.5509, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319343105146024e-05, + "loss": 3.555, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318504510394972e-05, + "loss": 3.5497, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317667553524293e-05, + "loss": 3.5493, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316828958773241e-05, + "loss": 3.5664, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315990364022189e-05, + "loss": 3.5608, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315151769271137e-05, + "loss": 3.5598, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314314812400458e-05, + "loss": 3.5512, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313476217649406e-05, + "loss": 3.5676, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312637622898354e-05, + "loss": 3.56, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311799028147302e-05, + "loss": 3.5717, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310962071276623e-05, + "loss": 3.5517, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310123476525571e-05, + "loss": 3.5558, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309284881774519e-05, + "loss": 3.5655, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308446287023467e-05, + "loss": 3.565, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307609330152788e-05, + "loss": 3.5592, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306770735401736e-05, + "loss": 3.565, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305932140650684e-05, + "loss": 3.5506, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305093545899633e-05, + "loss": 3.5509, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042565890289536e-05, + "loss": 3.5599, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034179942779016e-05, + "loss": 3.5654, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025793995268496e-05, + "loss": 3.5553, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017408047757976e-05, + "loss": 3.553, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300902210024745e-05, + "loss": 3.5553, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000652531540665e-05, + "loss": 3.5579, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2992266584030145e-05, + "loss": 3.5556, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2983880636519625e-05, + "loss": 3.5537, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975511067812834e-05, + "loss": 3.5575, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2967125120302314e-05, + "loss": 3.5681, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2958739172791794e-05, + "loss": 3.5677, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295035322528128e-05, + "loss": 3.5368, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2941967277770754e-05, + "loss": 3.5529, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293359770906397e-05, + "loss": 3.5505, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292521176155345e-05, + "loss": 3.5673, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291682581404292e-05, + "loss": 3.5639, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.29084398665324e-05, + "loss": 3.5572, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290007029782562e-05, + "loss": 3.5442, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.28916843503151e-05, + "loss": 3.561, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288329840280457e-05, + "loss": 3.5524, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287491245529405e-05, + "loss": 3.5534, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286654288658727e-05, + "loss": 3.5484, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285815693907675e-05, + "loss": 3.5571, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284977099156623e-05, + "loss": 3.557, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2841401422859443e-05, + "loss": 3.5416, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2833015475348923e-05, + "loss": 3.5503, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824629527838397e-05, + "loss": 3.5421, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2816243580327877e-05, + "loss": 3.5583, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2807857632817357e-05, + "loss": 3.5527, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799471685306836e-05, + "loss": 3.5554, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2791085737796316e-05, + "loss": 3.5577, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2782699790285796e-05, + "loss": 3.5537, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774330221579005e-05, + "loss": 3.5547, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2765944274068485e-05, + "loss": 3.558, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275755832655797e-05, + "loss": 3.5589, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274917237904745e-05, + "loss": 3.5489, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274080281034066e-05, + "loss": 3.5422, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273241686283014e-05, + "loss": 3.5575, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272403091531962e-05, + "loss": 3.5509, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.27156449678091e-05, + "loss": 3.5557, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270727539910231e-05, + "loss": 3.547, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269888945159179e-05, + "loss": 3.5562, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269050350408127e-05, + "loss": 3.5524, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268211755657075e-05, + "loss": 3.5475, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267374798786396e-05, + "loss": 3.5503, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266536204035344e-05, + "loss": 3.5577, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2656976092842926e-05, + "loss": 3.5686, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2648590145332406e-05, + "loss": 3.5462, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2640220576625615e-05, + "loss": 3.5499, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2631834629115095e-05, + "loss": 3.562, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2623448681604575e-05, + "loss": 3.5484, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2615062734094055e-05, + "loss": 3.5514, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2606693165387264e-05, + "loss": 3.5489, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2598307217876744e-05, + "loss": 3.5625, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2589921270366224e-05, + "loss": 3.5617, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581535322855704e-05, + "loss": 3.5542, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2573149375345184e-05, + "loss": 3.5491, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256477980663839e-05, + "loss": 3.5542, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255639385912787e-05, + "loss": 3.5567, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254800791161736e-05, + "loss": 3.5447, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253962196410684e-05, + "loss": 3.5723, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253125239540005e-05, + "loss": 3.5496, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252286644788953e-05, + "loss": 3.5574, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251448050037901e-05, + "loss": 3.5513, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.893498659133911, + "eval_runtime": 381.9007, + "eval_samples_per_second": 999.189, + "eval_steps_per_second": 31.225, + "step": 1068470 + }, + { + "epoch": 0.0, + "learning_rate": 3.250609455286849e-05, + "loss": 3.5813, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249770860535797e-05, + "loss": 3.5487, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248932265784745e-05, + "loss": 3.5492, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248093671033693e-05, + "loss": 3.5585, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247255076282641e-05, + "loss": 3.5568, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246418119411962e-05, + "loss": 3.5571, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.24557952466091e-05, + "loss": 3.5506, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244740929909858e-05, + "loss": 3.5463, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243902335158806e-05, + "loss": 3.55, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243065378288127e-05, + "loss": 3.5561, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242226783537075e-05, + "loss": 3.551, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241388188786023e-05, + "loss": 3.5564, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405495940349706e-05, + "loss": 3.5546, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239712637164292e-05, + "loss": 3.5343, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.23887404241324e-05, + "loss": 3.5484, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238035447662188e-05, + "loss": 3.5372, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2371968529111355e-05, + "loss": 3.5327, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236359896040457e-05, + "loss": 3.5524, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235521301289405e-05, + "loss": 3.5385, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234682706538353e-05, + "loss": 3.5591, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233844111787301e-05, + "loss": 3.5634, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.233007154916623e-05, + "loss": 3.5441, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232168560165571e-05, + "loss": 3.5521, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231329965414518e-05, + "loss": 3.5506, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304930085438396e-05, + "loss": 3.5354, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296544137927876e-05, + "loss": 3.5555, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288158190417356e-05, + "loss": 3.5415, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227977224290683e-05, + "loss": 3.5397, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227138629539631e-05, + "loss": 3.5428, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2263016726689525e-05, + "loss": 3.5367, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2254630779179005e-05, + "loss": 3.5392, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2246244831668485e-05, + "loss": 3.5511, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2237858884157964e-05, + "loss": 3.5549, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222948931545118e-05, + "loss": 3.5413, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2221103367940654e-05, + "loss": 3.5418, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2212717420430134e-05, + "loss": 3.5459, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.2204331472919613e-05, + "loss": 3.5617, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219596190421283e-05, + "loss": 3.5396, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.21875759567023e-05, + "loss": 3.5444, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217919000919178e-05, + "loss": 3.5438, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217080406168126e-05, + "loss": 3.5367, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216243449297447e-05, + "loss": 3.5453, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215404854546396e-05, + "loss": 3.5519, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214566259795344e-05, + "loss": 3.5568, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213727665044292e-05, + "loss": 3.5467, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212890708173613e-05, + "loss": 3.5432, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212052113422561e-05, + "loss": 3.5439, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211213518671509e-05, + "loss": 3.5506, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210374923920457e-05, + "loss": 3.522, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095379670497776e-05, + "loss": 3.5474, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2086993722987256e-05, + "loss": 3.5446, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078607775476736e-05, + "loss": 3.5545, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2070221827966216e-05, + "loss": 3.5415, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061852259259425e-05, + "loss": 3.5388, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205346631174891e-05, + "loss": 3.5365, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204508036423839e-05, + "loss": 3.5343, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203669441672787e-05, + "loss": 3.5565, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202832484802108e-05, + "loss": 3.5461, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201993890051056e-05, + "loss": 3.5594, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201155295300004e-05, + "loss": 3.5418, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200316700548952e-05, + "loss": 3.5289, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199479743678273e-05, + "loss": 3.5626, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198641148927221e-05, + "loss": 3.539, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197802554176169e-05, + "loss": 3.5312, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196963959425117e-05, + "loss": 3.5405, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196127002554438e-05, + "loss": 3.5433, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952884078033866e-05, + "loss": 3.534, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944498130523346e-05, + "loss": 3.539, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1936112183012825e-05, + "loss": 3.5352, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927742614306035e-05, + "loss": 3.5353, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919356666795515e-05, + "loss": 3.5475, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1910970719284995e-05, + "loss": 3.5471, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902584771774474e-05, + "loss": 3.5418, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1894215203067684e-05, + "loss": 3.5351, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1885829255557164e-05, + "loss": 3.5539, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1877443308046643e-05, + "loss": 3.5428, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1869057360536123e-05, + "loss": 3.5504, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186068779182933e-05, + "loss": 3.537, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185230184431882e-05, + "loss": 3.5392, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.18439158968083e-05, + "loss": 3.5449, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183552994929778e-05, + "loss": 3.5476, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182716038059099e-05, + "loss": 3.5427, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181877443308047e-05, + "loss": 3.5513, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181038848556995e-05, + "loss": 3.5403, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180200253805943e-05, + "loss": 3.5317, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179363296935264e-05, + "loss": 3.5413, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178524702184212e-05, + "loss": 3.5508, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.17768610743316e-05, + "loss": 3.536, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176847512682108e-05, + "loss": 3.5378, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1760105558114286e-05, + "loss": 3.5364, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175171961060377e-05, + "loss": 3.5417, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174333366309325e-05, + "loss": 3.5391, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173494771558273e-05, + "loss": 3.5398, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172656176807221e-05, + "loss": 3.5423, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171819219936542e-05, + "loss": 3.5447, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.17098062518549e-05, + "loss": 3.5561, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170142030434438e-05, + "loss": 3.518, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169303435683386e-05, + "loss": 3.5395, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168466478812707e-05, + "loss": 3.5354, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167627884061655e-05, + "loss": 3.5495, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166789289310603e-05, + "loss": 3.5471, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165950694559551e-05, + "loss": 3.5408, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165113737688872e-05, + "loss": 3.5302, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642751429378207e-05, + "loss": 3.5416, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634365481867686e-05, + "loss": 3.5384, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625979534357166e-05, + "loss": 3.5353, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617609965650376e-05, + "loss": 3.5314, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1609224018139856e-05, + "loss": 3.5362, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600838070629335e-05, + "loss": 3.5431, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592452123118815e-05, + "loss": 3.5267, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1584082554412025e-05, + "loss": 3.5348, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575696606901504e-05, + "loss": 3.5221, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567310659390984e-05, + "loss": 3.5445, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1558924711880464e-05, + "loss": 3.5321, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1550555143173673e-05, + "loss": 3.5375, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154216919566316e-05, + "loss": 3.5427, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153378324815264e-05, + "loss": 3.5425, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152539730064212e-05, + "loss": 3.5321, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151702773193533e-05, + "loss": 3.5425, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150864178442481e-05, + "loss": 3.5428, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150025583691429e-05, + "loss": 3.5277, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149186988940377e-05, + "loss": 3.5241, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148350032069698e-05, + "loss": 3.5433, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147511437318646e-05, + "loss": 3.536, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146672842567594e-05, + "loss": 3.539, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145834247816542e-05, + "loss": 3.5334, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144997290945863e-05, + "loss": 3.5378, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441586961948114e-05, + "loss": 3.5378, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1433201014437594e-05, + "loss": 3.5299, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424815066927074e-05, + "loss": 3.5299, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141644549822028e-05, + "loss": 3.5464, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140805955070976e-05, + "loss": 3.5502, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139967360319924e-05, + "loss": 3.5328, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139128765568872e-05, + "loss": 3.5343, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138291808698193e-05, + "loss": 3.5425, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137453213947141e-05, + "loss": 3.5324, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136614619196089e-05, + "loss": 3.5373, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135776024445037e-05, + "loss": 3.5351, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134939067574358e-05, + "loss": 3.5494, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134100472823307e-05, + "loss": 3.5429, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133261878072255e-05, + "loss": 3.5383, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132423283321203e-05, + "loss": 3.5332, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315863264505237e-05, + "loss": 3.5405, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307477316994717e-05, + "loss": 3.5394, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1299091369484196e-05, + "loss": 3.5271, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290705421973676e-05, + "loss": 3.5545, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282335853266886e-05, + "loss": 3.5323, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273949905756365e-05, + "loss": 3.5452, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265563958245845e-05, + "loss": 3.5348, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.894916534423828, + "eval_runtime": 303.5582, + "eval_samples_per_second": 1257.06, + "eval_steps_per_second": 39.284, + "step": 1144790 + }, + { + "epoch": 1.0, + "learning_rate": 3.1257178010735325e-05, + "loss": 3.5363, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248808442028534e-05, + "loss": 3.5332, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124042249451802e-05, + "loss": 3.5349, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.12320365470075e-05, + "loss": 3.5408, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223650599496974e-05, + "loss": 3.5412, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121528103079019e-05, + "loss": 3.5386, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120689508327967e-05, + "loss": 3.5326, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119850913576915e-05, + "loss": 3.5327, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119012318825862e-05, + "loss": 3.5339, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118175361955184e-05, + "loss": 3.538, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117336767204132e-05, + "loss": 3.535, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.11649817245308e-05, + "loss": 3.5371, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115659577702027e-05, + "loss": 3.5414, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114822620831349e-05, + "loss": 3.5204, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1139840260802975e-05, + "loss": 3.5305, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113145431329245e-05, + "loss": 3.5202, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112306836578193e-05, + "loss": 3.5222, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114698797075144e-05, + "loss": 3.5319, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106312849564624e-05, + "loss": 3.5257, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.10979269020541e-05, + "loss": 3.5336, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108954095454358e-05, + "loss": 3.5483, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108117138583679e-05, + "loss": 3.5329, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072785438326266e-05, + "loss": 3.533, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064399490815746e-05, + "loss": 3.5351, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1056013543305226e-05, + "loss": 3.5251, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104764397459844e-05, + "loss": 3.537, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103925802708792e-05, + "loss": 3.5214, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.10308720795774e-05, + "loss": 3.5299, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102248613206688e-05, + "loss": 3.5252, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.10141165633601e-05, + "loss": 3.5207, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100573061584957e-05, + "loss": 3.5283, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099734466833905e-05, + "loss": 3.5287, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098895872082853e-05, + "loss": 3.5394, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098058915212174e-05, + "loss": 3.5304, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097220320461122e-05, + "loss": 3.5222, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.09638172571007e-05, + "loss": 3.5271, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095543130959018e-05, + "loss": 3.5469, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0947061740883395e-05, + "loss": 3.5233, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938675793372875e-05, + "loss": 3.5305, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930289845862355e-05, + "loss": 3.5253, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921903898351835e-05, + "loss": 3.5206, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913534329645044e-05, + "loss": 3.5269, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0905148382134524e-05, + "loss": 3.5409, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0896762434624004e-05, + "loss": 3.5398, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888376487113484e-05, + "loss": 3.5315, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0880006918406693e-05, + "loss": 3.5287, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087162097089617e-05, + "loss": 3.5241, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086323502338565e-05, + "loss": 3.538, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085484907587513e-05, + "loss": 3.5082, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084647950716835e-05, + "loss": 3.5306, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083809355965783e-05, + "loss": 3.5282, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082970761214731e-05, + "loss": 3.5376, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082132166463679e-05, + "loss": 3.5294, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081293571712627e-05, + "loss": 3.5152, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080456614841948e-05, + "loss": 3.5267, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079618020090896e-05, + "loss": 3.512, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078779425339844e-05, + "loss": 3.5455, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077940830588792e-05, + "loss": 3.5288, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077103873718113e-05, + "loss": 3.5473, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076265278967061e-05, + "loss": 3.5242, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075426684216009e-05, + "loss": 3.5173, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074588089464957e-05, + "loss": 3.5403, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073751132594278e-05, + "loss": 3.5191, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072912537843226e-05, + "loss": 3.5209, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072073943092174e-05, + "loss": 3.5231, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071235348341122e-05, + "loss": 3.5309, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070398391470443e-05, + "loss": 3.5184, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069559796719391e-05, + "loss": 3.5217, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068721201968339e-05, + "loss": 3.5182, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067882607217287e-05, + "loss": 3.5181, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067045650346608e-05, + "loss": 3.5331, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066207055595556e-05, + "loss": 3.5314, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065368460844504e-05, + "loss": 3.5241, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064529866093452e-05, + "loss": 3.5248, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636929092227736e-05, + "loss": 3.5363, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628543144717216e-05, + "loss": 3.5244, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620157197206696e-05, + "loss": 3.5343, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611771249696176e-05, + "loss": 3.5241, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603401680989385e-05, + "loss": 3.5225, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0595015733478865e-05, + "loss": 3.5313, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586629785968345e-05, + "loss": 3.5312, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578243838457825e-05, + "loss": 3.5287, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0569874269751034e-05, + "loss": 3.533, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0561488322240514e-05, + "loss": 3.5282, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553102374729994e-05, + "loss": 3.5117, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0544716427219474e-05, + "loss": 3.5264, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053634685851269e-05, + "loss": 3.5338, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052796091100217e-05, + "loss": 3.5237, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051957496349165e-05, + "loss": 3.5228, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051118901598113e-05, + "loss": 3.5219, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050281944727434e-05, + "loss": 3.5252, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.049443349976382e-05, + "loss": 3.5212, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.04860475522533e-05, + "loss": 3.5255, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.047766160474278e-05, + "loss": 3.5261, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046929203603599e-05, + "loss": 3.5282, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.046090608852547e-05, + "loss": 3.5416, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045252014101495e-05, + "loss": 3.5054, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044413419350443e-05, + "loss": 3.52, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043576462479764e-05, + "loss": 3.5242, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042737867728712e-05, + "loss": 3.5319, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.04189927297766e-05, + "loss": 3.5321, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410606782266084e-05, + "loss": 3.5254, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402237213559293e-05, + "loss": 3.5143, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393851266048773e-05, + "loss": 3.5242, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385465318538253e-05, + "loss": 3.5266, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0377079371027733e-05, + "loss": 3.5181, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368709802320945e-05, + "loss": 3.5149, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360323854810425e-05, + "loss": 3.5236, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351937907299905e-05, + "loss": 3.5307, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343551959789385e-05, + "loss": 3.5089, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335182391082594e-05, + "loss": 3.5224, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326796443572074e-05, + "loss": 3.5075, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318410496061554e-05, + "loss": 3.5268, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0310024548551037e-05, + "loss": 3.5201, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301654979844246e-05, + "loss": 3.5224, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293269032333726e-05, + "loss": 3.5266, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284883084823206e-05, + "loss": 3.5238, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276497137312686e-05, + "loss": 3.519, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.02681275686059e-05, + "loss": 3.5275, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025974162109538e-05, + "loss": 3.5278, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.025135567358486e-05, + "loss": 3.5134, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024296972607434e-05, + "loss": 3.5099, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234600157367548e-05, + "loss": 3.5266, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226214209857028e-05, + "loss": 3.5201, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217828262346508e-05, + "loss": 3.5269, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020944231483599e-05, + "loss": 3.5144, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.02010727461292e-05, + "loss": 3.5245, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019268679861868e-05, + "loss": 3.5209, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018430085110816e-05, + "loss": 3.5176, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017591490359764e-05, + "loss": 3.5123, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167545334890852e-05, + "loss": 3.5297, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159159387380332e-05, + "loss": 3.5356, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150773439869812e-05, + "loss": 3.5187, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142387492359292e-05, + "loss": 3.5172, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.01340179236525e-05, + "loss": 3.5273, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012563197614198e-05, + "loss": 3.5183, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011724602863146e-05, + "loss": 3.521, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108876459924674e-05, + "loss": 3.5222, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100490512414154e-05, + "loss": 3.5335, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092104564903634e-05, + "loss": 3.5258, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083718617393114e-05, + "loss": 3.5242, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075332669882594e-05, + "loss": 3.5171, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066963101175806e-05, + "loss": 3.5274, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058577153665286e-05, + "loss": 3.5233, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050191206154766e-05, + "loss": 3.5106, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004180525864424e-05, + "loss": 3.5434, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033435689937455e-05, + "loss": 3.5217, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025049742426935e-05, + "loss": 3.5284, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016663794916415e-05, + "loss": 3.5189, + "step": 1220608 + }, + { + "epoch": 1.03, + "eval_loss": 3.897914409637451, + "eval_runtime": 303.3783, + "eval_samples_per_second": 1257.806, + "eval_steps_per_second": 39.307, + "step": 1221110 + }, + { + "epoch": 0.0, + "learning_rate": 3.000827784740589e-05, + "loss": 3.4889, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999989189989537e-05, + "loss": 3.5178, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999150595238485e-05, + "loss": 3.518, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998312000487433e-05, + "loss": 3.5298, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974750436167544e-05, + "loss": 3.5239, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966364488657024e-05, + "loss": 3.5247, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957978541146504e-05, + "loss": 3.5158, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949592593635984e-05, + "loss": 3.5178, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941223024929193e-05, + "loss": 3.518, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932837077418673e-05, + "loss": 3.5236, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924451129908153e-05, + "loss": 3.5188, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9916065182397636e-05, + "loss": 3.5243, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907695613690845e-05, + "loss": 3.5275, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899309666180325e-05, + "loss": 3.5094, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890923718669805e-05, + "loss": 3.5136, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882537771159285e-05, + "loss": 3.5083, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874168202452498e-05, + "loss": 3.5042, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865782254941978e-05, + "loss": 3.5179, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857396307431457e-05, + "loss": 3.5158, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9849010359920937e-05, + "loss": 3.5154, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840640791214147e-05, + "loss": 3.5341, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832254843703626e-05, + "loss": 3.5174, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823868896193106e-05, + "loss": 3.5201, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981548294868259e-05, + "loss": 3.515, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.98071133799758e-05, + "loss": 3.5154, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979872743246528e-05, + "loss": 3.5193, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.979034148495476e-05, + "loss": 3.5065, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978195553744424e-05, + "loss": 3.5154, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977358596873745e-05, + "loss": 3.5124, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976520002122693e-05, + "loss": 3.5039, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975681407371641e-05, + "loss": 3.5162, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974842812620589e-05, + "loss": 3.5117, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.97400585574991e-05, + "loss": 3.5226, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.973167260998858e-05, + "loss": 3.5186, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972328666247806e-05, + "loss": 3.5113, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714900714967543e-05, + "loss": 3.5137, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706531146260753e-05, + "loss": 3.5294, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698145198750232e-05, + "loss": 3.5073, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689759251239712e-05, + "loss": 3.5155, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681373303729192e-05, + "loss": 3.5139, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9673003735022405e-05, + "loss": 3.5012, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664617787511885e-05, + "loss": 3.5123, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656231840001365e-05, + "loss": 3.5281, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647845892490845e-05, + "loss": 3.5228, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639476323784054e-05, + "loss": 3.5112, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631090376273534e-05, + "loss": 3.5196, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622704428763014e-05, + "loss": 3.5099, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614318481252497e-05, + "loss": 3.5176, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605948912545706e-05, + "loss": 3.4936, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597562965035186e-05, + "loss": 3.5146, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589177017524666e-05, + "loss": 3.5212, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580791070014146e-05, + "loss": 3.5169, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957242150130736e-05, + "loss": 3.5156, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956403555379684e-05, + "loss": 3.5021, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955564960628632e-05, + "loss": 3.5141, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.95472636587758e-05, + "loss": 3.4974, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538894090069008e-05, + "loss": 3.5329, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530508142558487e-05, + "loss": 3.5127, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522122195047967e-05, + "loss": 3.529, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513736247537447e-05, + "loss": 3.5101, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950536667883066e-05, + "loss": 3.5054, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949698073132014e-05, + "loss": 3.5204, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948859478380962e-05, + "loss": 3.5088, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.94802088362991e-05, + "loss": 3.5096, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.947183926759231e-05, + "loss": 3.5086, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463453320081792e-05, + "loss": 3.5146, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455067372571272e-05, + "loss": 3.5037, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446681425060752e-05, + "loss": 3.5084, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943831185635396e-05, + "loss": 3.4987, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942992590884344e-05, + "loss": 3.5058, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942153996133292e-05, + "loss": 3.5175, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.94131540138224e-05, + "loss": 3.5212, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404784445115614e-05, + "loss": 3.5092, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396398497605093e-05, + "loss": 3.5091, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9388012550094573e-05, + "loss": 3.5172, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379626602584053e-05, + "loss": 3.5151, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371257033877262e-05, + "loss": 3.5134, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362871086366746e-05, + "loss": 3.5152, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354485138856226e-05, + "loss": 3.5073, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9346099191345706e-05, + "loss": 3.5154, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337729622638915e-05, + "loss": 3.5168, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329343675128395e-05, + "loss": 3.5162, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320957727617875e-05, + "loss": 3.5197, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312571780107355e-05, + "loss": 3.5116, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9304202211400567e-05, + "loss": 3.4942, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295816263890047e-05, + "loss": 3.5135, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287430316379527e-05, + "loss": 3.5153, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9279044368869007e-05, + "loss": 3.5117, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270674800162216e-05, + "loss": 3.51, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.92622888526517e-05, + "loss": 3.5026, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925390290514118e-05, + "loss": 3.5165, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924551695763066e-05, + "loss": 3.503, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923714738892387e-05, + "loss": 3.5098, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.922876144141335e-05, + "loss": 3.5114, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922037549390283e-05, + "loss": 3.5117, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921198954639231e-05, + "loss": 3.5269, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920361997768552e-05, + "loss": 3.4972, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195234030175e-05, + "loss": 3.4992, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918684808266448e-05, + "loss": 3.5136, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917846213515396e-05, + "loss": 3.5167, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.917009256644717e-05, + "loss": 3.5186, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161706618936653e-05, + "loss": 3.5152, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153320671426133e-05, + "loss": 3.4976, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144934723915613e-05, + "loss": 3.5108, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136565155208822e-05, + "loss": 3.5152, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128179207698302e-05, + "loss": 3.4997, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119793260187782e-05, + "loss": 3.5007, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111407312677262e-05, + "loss": 3.5117, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9103037743970475e-05, + "loss": 3.5146, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094651796459954e-05, + "loss": 3.4929, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086265848949434e-05, + "loss": 3.5028, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077879901438914e-05, + "loss": 3.4992, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069510332732123e-05, + "loss": 3.5115, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061124385221607e-05, + "loss": 3.5044, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052738437711087e-05, + "loss": 3.5057, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904435249020056e-05, + "loss": 3.5118, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035982921493776e-05, + "loss": 3.516, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027596973983256e-05, + "loss": 3.5007, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019211026472736e-05, + "loss": 3.5133, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010825078962212e-05, + "loss": 3.511, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002455510255428e-05, + "loss": 3.5047, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994069562744908e-05, + "loss": 3.4911, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985683615234388e-05, + "loss": 3.5111, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897729766772386e-05, + "loss": 3.5046, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968928099017077e-05, + "loss": 3.5153, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896054215150656e-05, + "loss": 3.4988, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952156203996034e-05, + "loss": 3.5106, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943770256485514e-05, + "loss": 3.5047, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893540068777873e-05, + "loss": 3.5, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892701474026821e-05, + "loss": 3.4965, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918628792757686e-05, + "loss": 3.5171, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910242845247166e-05, + "loss": 3.5204, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901873276540382e-05, + "loss": 3.5098, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893487329029862e-05, + "loss": 3.4971, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885101381519335e-05, + "loss": 3.5137, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876715434008815e-05, + "loss": 3.5032, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886834586530203e-05, + "loss": 3.5105, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859959917791507e-05, + "loss": 3.5067, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851573970280987e-05, + "loss": 3.5156, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843188022770467e-05, + "loss": 3.5076, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834818454063683e-05, + "loss": 3.5113, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882643250655316e-05, + "loss": 3.5035, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881804655904264e-05, + "loss": 3.5118, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880966061153212e-05, + "loss": 3.5087, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801291042825336e-05, + "loss": 3.4983, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.879290509531481e-05, + "loss": 3.5279, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878451914780429e-05, + "loss": 3.5059, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877613320029377e-05, + "loss": 3.5095, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876776363158698e-05, + "loss": 3.5091, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875937768407646e-05, + "loss": 3.5035, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8982632160186768, + "eval_runtime": 323.5957, + "eval_samples_per_second": 1179.221, + "eval_steps_per_second": 36.852, + "step": 1297430 + }, + { + "epoch": 1.0, + "learning_rate": 2.875099173656594e-05, + "loss": 3.5029, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874260578905542e-05, + "loss": 3.5058, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873423622034863e-05, + "loss": 3.5143, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725850272838113e-05, + "loss": 3.5082, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717464325327593e-05, + "loss": 3.5158, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8709078377817073e-05, + "loss": 3.4999, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700708809110282e-05, + "loss": 3.5036, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692322861599762e-05, + "loss": 3.5005, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683936914089242e-05, + "loss": 3.515, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675550966578722e-05, + "loss": 3.5014, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8667181397871935e-05, + "loss": 3.5127, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658795450361415e-05, + "loss": 3.5097, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865042588165463e-05, + "loss": 3.4967, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8642039934144104e-05, + "loss": 3.4966, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633653986633584e-05, + "loss": 3.4927, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625268039123067e-05, + "loss": 3.4978, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616882091612547e-05, + "loss": 3.4993, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608496144102027e-05, + "loss": 3.5008, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8600110196591507e-05, + "loss": 3.4998, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591724249080987e-05, + "loss": 3.5227, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583354680374196e-05, + "loss": 3.5021, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574968732863676e-05, + "loss": 3.5048, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566582785353156e-05, + "loss": 3.505, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855819683784264e-05, + "loss": 3.4992, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854982726913585e-05, + "loss": 3.5031, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.854144132162533e-05, + "loss": 3.4924, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533055374114808e-05, + "loss": 3.5007, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524669426604288e-05, + "loss": 3.4982, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.85162998578975e-05, + "loss": 3.4877, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850791391038698e-05, + "loss": 3.5031, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849952796287646e-05, + "loss": 3.4976, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849114201536594e-05, + "loss": 3.5085, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.848277244665915e-05, + "loss": 3.5028, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847438649914863e-05, + "loss": 3.4938, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.846600055163811e-05, + "loss": 3.5049, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457614604127593e-05, + "loss": 3.5146, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449245035420802e-05, + "loss": 3.4905, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440859087910282e-05, + "loss": 3.5038, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432473140399762e-05, + "loss": 3.4977, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8424087192889242e-05, + "loss": 3.4904, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415717624182454e-05, + "loss": 3.4975, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407331676671934e-05, + "loss": 3.5132, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398945729161414e-05, + "loss": 3.5059, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390559781650894e-05, + "loss": 3.499, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382190212944103e-05, + "loss": 3.5067, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373804265433583e-05, + "loss": 3.4985, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365418317923063e-05, + "loss": 3.5032, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8357032370412547e-05, + "loss": 3.484, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348662801705756e-05, + "loss": 3.4957, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340276854195236e-05, + "loss": 3.5042, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331890906684716e-05, + "loss": 3.5065, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323504959174196e-05, + "loss": 3.5004, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315135390467408e-05, + "loss": 3.4884, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306749442956888e-05, + "loss": 3.5032, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298363495446368e-05, + "loss": 3.481, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289977547935848e-05, + "loss": 3.514, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281607979229057e-05, + "loss": 3.5006, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273222031718537e-05, + "loss": 3.517, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264836084208017e-05, + "loss": 3.4967, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.82564501366975e-05, + "loss": 3.4924, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824808056799071e-05, + "loss": 3.5034, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823969462048019e-05, + "loss": 3.4999, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823130867296967e-05, + "loss": 3.4932, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822292272545915e-05, + "loss": 3.4896, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214553156752362e-05, + "loss": 3.5043, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820616720924184e-05, + "loss": 3.4922, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819778126173132e-05, + "loss": 3.4876, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.81893953142208e-05, + "loss": 3.4916, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.818102574551401e-05, + "loss": 3.4925, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817263979800349e-05, + "loss": 3.503, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.816425385049297e-05, + "loss": 3.507, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155867902982454e-05, + "loss": 3.495, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147498334275663e-05, + "loss": 3.4948, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8139112386765143e-05, + "loss": 3.5011, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130726439254623e-05, + "loss": 3.4998, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122340491744103e-05, + "loss": 3.5007, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113970923037315e-05, + "loss": 3.501, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105584975526795e-05, + "loss": 3.4955, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8097199028016275e-05, + "loss": 3.5043, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088813080505755e-05, + "loss": 3.5008, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080443511798964e-05, + "loss": 3.5053, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8072057564288444e-05, + "loss": 3.5028, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063671616777924e-05, + "loss": 3.4979, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055285669267408e-05, + "loss": 3.4825, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046916100560617e-05, + "loss": 3.4996, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038530153050097e-05, + "loss": 3.5028, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8030144205539577e-05, + "loss": 3.4976, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021774636832786e-05, + "loss": 3.4999, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801338868932227e-05, + "loss": 3.4907, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800500274181175e-05, + "loss": 3.5003, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799661679430123e-05, + "loss": 3.4913, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988247225594438e-05, + "loss": 3.4984, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979861278083918e-05, + "loss": 3.4923, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971475330573398e-05, + "loss": 3.4994, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963089383062878e-05, + "loss": 3.5071, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795471981435609e-05, + "loss": 3.4944, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.794633386684557e-05, + "loss": 3.4796, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793794791933505e-05, + "loss": 3.5011, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792956197182453e-05, + "loss": 3.5025, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.792119240311774e-05, + "loss": 3.505, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912806455607223e-05, + "loss": 3.4982, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904420508096703e-05, + "loss": 3.4872, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7896034560586183e-05, + "loss": 3.4913, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887648613075656e-05, + "loss": 3.5029, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879262665565136e-05, + "loss": 3.4865, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870876718054616e-05, + "loss": 3.4873, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.78624907705441e-05, + "loss": 3.4987, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854121201837308e-05, + "loss": 3.5029, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845735254326788e-05, + "loss": 3.4783, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837349306816268e-05, + "loss": 3.4919, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828963359305748e-05, + "loss": 3.4854, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.782059379059896e-05, + "loss": 3.4974, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.781220784308844e-05, + "loss": 3.4951, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780382189557792e-05, + "loss": 3.4841, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.77954359480674e-05, + "loss": 3.5044, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778706637936061e-05, + "loss": 3.4989, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777868043185009e-05, + "loss": 3.4853, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.777029448433957e-05, + "loss": 3.499, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776190853682905e-05, + "loss": 3.4978, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753538968122262e-05, + "loss": 3.4903, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745153020611742e-05, + "loss": 3.4771, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736767073101222e-05, + "loss": 3.4992, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.77283811255907e-05, + "loss": 3.4894, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7720011556883914e-05, + "loss": 3.4983, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711625609373394e-05, + "loss": 3.4852, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703239661862874e-05, + "loss": 3.4938, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694853714352354e-05, + "loss": 3.4978, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686484145645563e-05, + "loss": 3.4879, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7678098198135043e-05, + "loss": 3.4784, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669712250624523e-05, + "loss": 3.5073, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661326303114003e-05, + "loss": 3.5062, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652956734407215e-05, + "loss": 3.4948, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644570786896695e-05, + "loss": 3.485, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636184839386175e-05, + "loss": 3.5031, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627798891875655e-05, + "loss": 3.4902, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619429323168864e-05, + "loss": 3.4922, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7611043375658348e-05, + "loss": 3.493, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602657428147828e-05, + "loss": 3.5017, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594271480637308e-05, + "loss": 3.4917, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585901911930517e-05, + "loss": 3.4989, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577515964419997e-05, + "loss": 3.4903, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569130016909477e-05, + "loss": 3.5003, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560744069398957e-05, + "loss": 3.4939, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755237450069217e-05, + "loss": 3.4869, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754398855318165e-05, + "loss": 3.5124, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753560260567113e-05, + "loss": 3.4943, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.752721665816061e-05, + "loss": 3.4944, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518847089453818e-05, + "loss": 3.4949, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.75104611419433e-05, + "loss": 3.4886, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.901379346847534, + "eval_runtime": 342.3147, + "eval_samples_per_second": 1114.737, + "eval_steps_per_second": 34.836, + "step": 1373750 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 8.908915894534656e+17, + "trial_name": null, + "trial_params": null +}